Auf geht's

Statistics

AetherEdge - Liquidity Sweep & Raid Detector🖊️ Overview AetherEdge Liquidity Sweep & Raid Detector is a professional-grade smart money analysis tool that exposes institutional stop hunts (liquidity raids) and Equal Highs/Lows liquidity pools in real time. By integrating ATR-based significance filters, three-tier sweep confirmation modes, and projected stop hunt zones, it visualizes "who, where, and why" liquidity is being taken—enabling traders to follow institutional footprints with both reversal and continuation entries. 🔶 Key Features ATR-Adaptive Pivot Detection: Extracts only meaningful swings Equal Highs/Lows Detection: Auto-marks liquidity pools 3 Sweep Confirmation Modes: Wick Only / Close Back / Wick + Close Back Stop Hunt Zone Projection: Boxes mark institutional revisit zones 3 Zone Management Modes: Keep / Fade on Touch / Remove on Touch Reversal Candle Requirement: Filters false sweeps Break of Structure (BOS): Auto-detects structural shifts ATR Wick Size Filter: Eliminates shallow sweeps Pending Sweep System: Configurable max-bars window for close-back confirmation Statistics Dashboard: Bull/Bear sweep counts, EQH/EQL, active hot zones 🧠 Technical Architecture This indicator implements core ICT/SMC concepts via pivot array management and a pending state machine to deliver a professional liquidity-tracking engine. Significance Pivot Layer: ta.pivothigh/low for confirmed swing detection ATR × multiplier filters out "noise swings" Arrays manage 50 historical pivots (price, bar, swept flag) Equal Highs/Lows Detection: Scans pivots within eqLookback |currentPivot - prevPivot| ≤ ATR × tolerance for equality Draws horizontal line at midpoint with optional right-extension Sweep Detection Engine: Wick Only: Wick breaks pivot + immediate inside close + reversal confirmation Close Back: Wick breaks, then close returns inside within sweepMaxBars Wick + Close Back: Both conditions met (highest precision) Pending arrays handle multi-stage confirmation asynchronously Stop Hunt Zones: Box generated at sweep point with zoneHeightATR height Extended zoneExtend bars right Lifecycle managed via Fade / Remove / Keep on touch BOS Detection: Unswept pivot's close-break marks structural shift Memory Management: maxObjects FIFO-prunes all lines/labels/boxes ⚙️ Recommended Settings & Tuning Guide Crypto Defaults: BTC (15M–1H): pivLen=10, atrMinMult=0.3, sweepMode=Wick + Close Back (standard) ETH (5M–15M): pivLen=8, sweepMaxBars=4 for faster confirmation SOL (high-vol): atrMinMult=0.5, sweepMinWick=0.4 for stricter filter XRP (range): eqTolerance=0.15 to relax equality detection Sweep Mode Selection: Wick Only: High frequency, day trading / scalping Close Back: Medium frequency, most balanced Wick + Close Back: Highest precision, swing trading (recommended) Zone Management: Fade on Touch: Preserves history, tracks revisits (recommended) Remove on Touch: Cleaner charts Keep: Full retention, long-term analysis Tuning: Too many signals: atrMinMult=0.5, sweepMinWick=0.5 Too few signals: requireReverse=false, sweepMaxBars=5 Better EQ accuracy: eqMinDistance=5 to suppress clusters 💡 How to Use in Practice Bullish Sweep (Low Grab) → Long: Buy the bounce after institutions raid downside stops Bearish Sweep (High Grab) → Short: Sell after upside stop hunt EQH/EQL → Liquidity Targets: Price likely magnetizes here Stop Hunt Zone Revisit: Once-swept zones often retest BOS + Sweep Combined: Strongest structural shift confirmation AetherEdge Synergy: WaveTrend Enhanced OS Extreme + Bullish Sweep = max-conviction bottom Self-Evolving S/R Grid strong support + Low Grab = institutional-sync entry SuperTrend Multi-Factor Bull flip + BOS Up = trend ignition capture Multi-TF Strategy: 1H EQH for liquidity map → 15M sweep for entry → 5M for precision timing ⚠️ Important Notes Pivot Lag: pivLen-bar delay inherent (no real-time detection) ATR Filter Dependency: Sweep detection drops in low-volatility regimes Close Back Pending: Auto-cancels after sweepMaxBars—watch for missed signals EQ Over-detection: Large eqLookback may match outdated pivots Zone Revisit: Probabilistic, not guaranteed Sweeps in Strong Trends: Can be confused with breakouts—context confirmation required 🚨 Disclaimer This indicator is a technical analysis tool provided for educational and research purposes only and does not constitute financial advice. Liquidity sweeps and stop hunt zones represent probabilistic market behavior patterns and do not guarantee profits. All trading decisions are made at your own risk and should be accompanied by proper risk management.
Pine Script® Indikator
von AetherEdge
AetherEdge Multi-Feature Neural Divergence Hunter🖊️ Overview AetherEdge Multi-Feature Neural Divergence Hunter is a revolutionary divergence engine that simultaneously detects divergences across 6 independent oscillators and self-evolves neural weights based on each feature's empirical accuracy. Every feature (RSI/MACD/Stoch/CCI/MFI/MOM) detects both Regular and Hidden divergences in parallel, and Softmax-normalized dynamic weights evaluate confluence. With its 3D visual encoding (color × size × shape), the type and strength of every signal is identifiable at a glance — a next-generation divergence hunter. 🔶 Key Features 6 Parallel Oscillator Detection: RSI / MACD Hist / Stochastic / CCI / MFI / Momentum Up to 12 Divergence Variants (2 types × 6 features) tracked simultaneously Softmax Neural Weight Learning: Auto-redistribution based on empirical accuracy Reward-Based Weight Updates: Bonus for correct, penalty for wrong Confluence Counting: Separate Regular/Hidden tracking, combined for trigger 3D Visual Encoding: Color: REG Bull/Bear, HID Bull/Bear, MIXED — 5-class system Size: tiny→huge based on confluence count (5 levels) Shape: Regular=triangle, Hidden=arrow, Mixed=label Composite Neural Oscillator: Weighted average centered display Confluence Glow: Background opacity reflects strength Per-Feature Accuracy Tracking: Individual hit-rate records Dynamic Divergence Lines: Width and style identify type 🧠 Technical Architecture This indicator is a neural-weight-learning system processing 6 oscillators in parallel. Feature Normalization: RSI/Stoch/MFI: Native 0-100 MACD Hist/CCI/Momentum: Normalized to 0-100 over 100-bar range Pivot Storage Method (Pine v5 compatible): Eliminates dynamic history access by storing previous-pivot oscillator values 12 slots managed: prevPL_rsi, prevPL_macd, ... Divergence Detection (per feature): Regular Bull: Price LL + Oscillator HL Hidden Bull: Price HL + Oscillator LL Regular Bear: Price HH + Oscillator LH Hidden Bear: Price LH + Oscillator HH Distance filter: minBarsBet ≤ pivot gap ≤ maxBarsBet Neural Weight Learning: Evaluates return after rewardLook bars per signal Correct (ret > 0): w += learnRate × |ret| × 100 Wrong (ret < 0): w -= learnRate × |ret| × 50 (asymmetric penalty) Weight constraint: Softmax Normalization (temperature τ): w_i = exp((rawW_i - max) / τ) / Σexp(...) Low τ → concentrate on best; High τ → uniform Composite Neural Oscillator: nnOsc = Σ(value_i × w_i) / Σw_i - 50 3-bar EMA smoothing, 5-zone state detection 3D Visual Encoding: Color = type, Size = strength, Shape = category — 3-dimensional information transmission ⚙️ Recommended Settings & Tuning Guide Crypto Defaults: BTC (4H): pivotLen=5, minConfluence=2, learnRate=0.08 (standard) ETH (1H): pivotLen=4, minConfluence=2, rewardLook=8 SOL (high-vol): pivotLen=6, minConfluence=3, rewardLook=12 XRP (short-term): pivotLen=3, minConfluence=2, rewardLook=5 Pivot Sensitivity: pivotLen=3: high-sensitivity, noisy pivotLen=5: standard pivotLen=8–10: HTF, certainty-focused Confluence Threshold: minConfluence=1: many signals, false positives minConfluence=2: standard (recommended) minConfluence=3: curated, fewer minConfluence=4+: ultra-curated, rare Learning Parameters: learnRate=0.05: conservative, stable learnRate=0.08: standard learnRate=0.15: fast, unstable risk softmaxTemp=0.5: elite concentration (focus on best 1-2) softmaxTemp=1.5: standard (balanced) softmaxTemp=3.0: uniform (diversity) Feature Selection Strategy: Oscillator-focus: RSI + Stoch + MFI (momentum group) Trend-focus: MACD + CCI + Momentum Full parallel: All 6 ON (recommended, NN auto-curates) 💡 How to Use in Practice 5+ Confluence + REG MIXED: Strongest reversal signal (huge size emphasis) 3 REG Bull + NN 80%: High-probability reversal-buy candidate 3 HID Bull: Trend-continuation pullback buy MIXED (REG+HID): Transition zone / unstable market Neural Oscillator Usage: EXTREME OB (>35): Overheated, watch for reversal EXTREME OS (<-35): Bottom zone, watch for bounce OS zero-cross + divergence: Direction confirmation Learning Maturity Check: Per-feature Acc% > 60%: feature is reliable Acc% < 45%: feature is failing, ignore Many Pending: still learning, wait AetherEdge Synergy: SMC AI Confidence Engine: A+ zone + 5× confluence = ultimate alignment NeuraNet Predictor: Direction match + REG MIXED = double confirmation RL Signal Optimizer: CONFIDENT + divergence = strong entry All-in-One Dashboard: HIGH-CONVICTION + huge label = supreme reversal signal ⚠️ Important Notes Pivot Lag: Divergence confirms pivotLen bars later (no real-time detection) Weight Reset: Chart reload resets weight learning Learning Maturity: Per-feature Acc% reliable only after Signals ≥ 20 Overfitting Risk: High learnRate + long runtime may over-skew weights Hidden Divergence Nature: Continuation signal — avoid counter-trend misuse MIXED Interpretation: Simultaneous REG+HID = transitional confusion, be cautious Feature Disabling: Turning off unused features improves weight allocation 🚨 Disclaimer This indicator is an advanced divergence-analysis tool for educational and research purposes only and does not constitute financial advice. Neural weight learning is a stochastic optimization method and does not guarantee future profits. Divergences suggest reversal or continuation possibilities but do not guarantee outcomes. Use with thorough validation and proper risk management.
Pine Script® Indikator
von AetherEdge
AetherEdge Hybrid Quantum-Inspired Predictor🖊️ Overview AetherEdge Hybrid Quantum-Inspired Predictor is a next-generation 3-class (UP/DOWN/SIDE) probability prediction engine that fuses three heterogeneous models: a quantum-mechanical wavefunction approach, a K-Nearest Neighbors historical analog search, and a self-learning neural network. Born-rule probabilities derived from complex amplitudes ψ, distance-weighted K-NN voting, and Softmax-based self-optimizing neurons all converge into a single ensemble distribution. With a complete visualization system featuring a radar chart, pie chart, and historical analogs, it decodes the market's "superposition state." 🔶 Key Features 3-Layer Hybrid Architecture: Quantum + KNN + Neural Quantum Layer: Complex wavefunction ψ, Gaussian amplitudes, decoherence, phase KNN Layer: K-nearest analog search in 3D feature space Neural Layer: Online gradient descent + Softmax + Weight decay 3-Class Classification: UP/DOWN/SIDE probability distribution 3 Core Features: Price Structure / Liquidity / Sentiment Proxy On-Chart Radar Chart: 3-axis visualization On-Chart Pie Chart: Instant state distribution view Historical Analogs Display: Top-3 similar past patterns Quantum Internal State Monitor: Re(ψ), Im(ψ), |ψ|², entropy State Flip Markers: Auto-detection of directional transitions Strategy Suggestion Engine: LONG BIAS / SHORT BIAS / RANGE FADE, etc. 🧠 Technical Architecture This indicator is designed as an ensemble predictor of three heterogeneous models. Feature Engineering: Price Structure: EMA20/50/100 + RSI + ATR-deviation composite (tanh normalized) Liquidity: Close position + wick asymmetry + VWAP deviation + sweep detection Sentiment Proxy: Vol-Z + price-volume divergence + A/D + volume spike Quantum Layer: Wavefunction Construction: ψ_state = Σ A·e^(iθ) per feature Gaussian Amplitude: A(f, target) = exp(-(f-target)²/(2σ²)) Phase Intensity: θ = f × qPhase × π/2 + offset Born Rule: P_state = |ψ|² / Σ|ψ|² Decoherence: P' = (1-γ)·P + γ/3 for quantum→classical transition Quantum Coherence: 1 - H/log(3) state clarity KNN Layer: Euclidean distance search in 3D feature space Distance-weighted voting w = 1/(1+d) Aggregates labels (UP/DOWN/SIDE) at past kHorizon-bar future Records Top-3 analogs (rank, distance, realized return) Neural Layer: 3-class Softmax classifier (3 inputs → 3 outputs, 12 parameters) Cross-Entropy Gradient: g = p - target Update Rule: w_new = w·decay - lr·g·feature Weight Decay: Prevents overfitting + forgets old patterns Ensemble Integration: Weighted average: P = (q·P_q + k·P_k + n·P_n) / Σw After normalization, max-probability class becomes dominant state Strategy Engine: domProb ≥ 0.55 + UP → LONG BIAS domProb ≥ 0.55 + DOWN → SHORT BIAS domProb ≥ 0.55 + SIDE → RANGE FADE confidence < 0.15 → HIGH UNCERTAINTY ⚙️ Recommended Settings & Tuning Guide Crypto Defaults: BTC (4H): qWeight=0.35, kWeight=0.35, nWeight=0.30, kK=20 ETH (1H): qWeight=0.30, kWeight=0.40, nWeight=0.30, kHorizon=5 SOL (high-vol): qSigma=1.5, qDecoher=0.15, kThresh=0.5 XRP (short-term): kHorizon=3, kThresh=0.2, nLR=0.02 Quantum Layer: qWeight=0.20: Conservative (suppress quantum contribution) qWeight=0.35: Standard qWeight=0.50: Experimental (quantum-dominant) qSigma=0.8: Sharp (clear states) qSigma=1.2: Standard qSigma=2.0: Smooth (high uncertainty) qDecoher=0.05: Pure quantum qDecoher=0.10: Standard qDecoher=0.30: Strong classical approximation KNN Layer: kK=10: Curated matches (sharp) kK=20: Standard kK=40: Smooth (conservative) kLookback=300: Lightweight kLookback=500: Standard kLookback=1000: Long-term patterns kThresh=0.2%: Sensitive (short TF) kThresh=0.3%: Standard kThresh=0.5%: Conservative (long TF) Neural Layer: nLR=0.005: Cautious learning (stable) nLR=0.015: Standard nLR=0.05: Fast adaptation (unstable) nDecay=0.999: Long-term memory nDecay=0.997: Standard nDecay=0.99: Quick forgetting 💡 How to Use in Practice LONG BIAS + High Q-Coherence: Strongest buy signal, consider entry SHORT BIAS + High Confidence: Strongest sell signal, build short RANGE FADE: Range strategies, sell premium, fade both extremes HIGH UNCERTAINTY: Reduce positions, observe mode State Flip → UP: Early trend transition, early entry All Top-3 Analogs Same Direction: Strong historical evidence, raise confidence 3-Model Consensus: Quantum/KNN/Neural all UP → highest confidence 3-Model Divergence: Split opinion, exercise caution Dir Bias > 0.3: Strong upward bias Vol Anomaly Detected: Suspend forecasts during normal-time logic AetherEdge Synergy: Self-Evolving S/R Grid: LONG BIAS + support reaction = high-win-rate entry Volatility Regime GAN: SHORT BIAS + EXPAND forecast = powerful drop setup SMC AI Confidence: 3-model consensus + high-conf zone = conviction entry Neural Divergence Hunter: State Flip + divergence = reversal confirmation ⚠️ Important Notes Initial Learning Period: Neural & KNN immature until bar_index > 110 Model Divergence: Split opinions signal weak signal strength Quantum is Approximation: Mathematical analogy, not actual quantum computing History Dependent: Cannot handle unprecedented market events Computation Load: Radar & pie rendering slightly heavy Repaint: Runs at barstate.islast, displayed only at last bar Neural Weights: Reset to defaults on chart reload Confidence < 0.15: Near-uniform distribution, recommend avoiding trades 🚨 Disclaimer This indicator is an advanced hybrid prediction tool for educational and research purposes only and does not constitute financial advice. "Quantum-inspired" is a mathematical analogy, not actual quantum computing. The 3-model ensemble prediction is a probabilistic method and does not guarantee future price movements. Use with thorough validation and proper risk management.
Pine Script® Indikator
von AetherEdge
Mani_Legit Script (Like and follow if it helps you)Mani_Legit is an advanced all-in-one trading indicator built for traders looking for cleaner market structure, trend confirmation, liquidity concepts, and AI-style confluence in one system. It includes multiple customizable tools and visual options that can be turned on or off depending on your trading style. This script was designed to help simplify chart analysis while giving traders more flexibility and control over their setups. Explore the settings, test what works best for you, and make it your own. If this indicator helps you, consider leaving a like and following my account for future updates. Thank you and trade safe.
Pine Script® Indikator
von Big_j_moves
AetherEdge Volatility Regime GAN Simulator🖊️ Overview AetherEdge Volatility Regime GAN Simulator is a next-generation volatility forecasting engine that encodes the current market state as a 6-dimensional feature vector, performs K-NN search against a historical database of up to 500 bars, and generates 100 Monte Carlo paths of likely future trajectories. By integrating Haar wavelet decomposition, Softmax-weighted sampling, and K-means regime clustering, it visualizes the future σ distribution as a complete fan chart and histogram. Inspired by Generative Adversarial Networks, it reconstructs future scenarios from historical market patterns — an innovative simulator for the modern trader. 🔶 Key Features 3-Scale Volatility: Short/Medium/Long σ (annualized) Haar Wavelet Decomposition: high/mid/low frequency triple-scale 6D Feature Vector: σ-z (×3) + VoV-z + Wavelet-z (×2) K-NN Analog Search: Top-K nearest historical states Softmax-Weighted Sampling: Temperature τ controls similarity allocation Monte Carlo Path Generation: 100 paths build future distribution K-Means Regime Clustering: CALM/NORMAL/ELEVATED/STRESSED/EXTREME/CRISIS Fan Chart Visualization: P5-P95, P25-P75, median line Terminal Distribution Histogram: σ_T probability density Complete Statistical Dashboard: E , median, CI90, skew, regime distribution Match Quality Indicator: ⟨d⟩ assesses analog availability 🧠 Technical Architecture This indicator is designed as a history-based generative model. Feature Engineering: Log-return ret = ln(close/close ) 3-scale stdev × √(annFactor) for annualized σ Haar wavelet: |W_s| = √(s/2) × |mean_recent - mean_older| 200-bar z-score normalization (outlier robust) 6D Feature Vector: z1=σS, z2=σM, z3=σL, z4=VoV, z5=W_hi, z6=W_mid K-NN Search: Euclidean distance d = √Σ(z_now - z_hist)² Top kNeighbors selected Softmax Sampling: w_i = exp(-d_i / τ) / Σexp(-d_j / τ) Low τ → focus on closest, High τ → diversify Monte Carlo Path Generation: Per simulation: cumulative probability samples a neighbor σ-ratio projection pathVol = volS × (histFutVol / nVol) Innovation noise + noiseAmp × volS × U(-0.5, 0.5) Quantile Computation: P5/P25/P50/P75/P95 extracted at each time step Fan chart + smooth polyline rendering K-Means Clustering: 2D space (σ-z, VoV-z) classified into 4-6 regimes Lloyd's algorithm for kmIters iterations σ-z ascending sort (regime 0 = calmest) Match Quality Metric: ⟨d⟩ < 1.0: TIGHT (high reliability) ⟨d⟩ < 2.5: LOOSE (moderate) ⟨d⟩ ≥ 2.5: POOR (no analog → warning) ⚙️ Recommended Settings & Tuning Guide Crypto Defaults: BTC (Daily): volLen=20, annFactor=365, historyLen=500 ETH (4H): volLen=14, volMed=42, kNeighbors=15 SOL (high-vol): volLen=10, nSims=200, noiseAmp=0.12 XRP (short-term): volLen=14, forecastLen=10, kNeighbors=15 History Depth: historyLen=200: lightweight, recent only historyLen=500: standard (recommended) historyLen=1000+: long-term pattern reference K-NN Settings: kNeighbors=10: curated, sharp forecast kNeighbors=20: standard (balanced) kNeighbors=50: smooth, conservative Temperature Parameter: tempSample=0.3: elite concentration (focus on nearest) tempSample=1.0: standard (recommended) tempSample=3.0: diversification (high uncertainty) Monte Carlo: nSims=50: lightweight, low-resolution nSims=100: standard nSims=200+: high-resolution histogram Noise Amplitude: noiseAmp=0.05: conservative (history-faithful) noiseAmp=0.08: standard noiseAmp=0.15: exploratory (unknown scenarios) Regime Count: nRegimes=3: coarse (simple) nRegimes=4: standard nRegimes=6: granular (CALM→CRISIS) 💡 How to Use in Practice EXPAND forecast + STRESSED: Buy options / strengthen hedges CONTRACT forecast + CALM: Range strategies / sell premium Narrow CI90 + TIGHT match: High-confidence forecast, execute strategy Wide CI90 + POOR match: Unknown territory, exercise caution P95 > 2× volS: Tail-risk alert, reduce position Regime Transition Detection: CALM → ELEVATED: Caution mode STRESSED → EXTREME: Crisis approaching EXTREME → STRESSED: Storm passing Skew Interpretation: right-tail: Upside risk dominant (vol spike possible) symmetric: Standard scenario left-tail: Downside risk dominant (vol crash possible) AetherEdge Synergy: SMC AI Confidence Engine: CONTRACT forecast + high-conf zone = compression breakout setup Self-Evolving S/R Grid: EXPAND forecast + line cluster = breakout preparation Neural Divergence Hunter: STRESSED + divergence = elevated reversal probability All-in-One Dashboard: Regime + direction = comprehensive judgment ⚠️ Important Notes History Dependency: Waits for bar_index > 210 to accumulate history (no early rendering) POOR Match Warning: ⟨d⟩ > 3.0 indicates low forecast reliability History-Based Prediction: Cannot handle unprecedented market events Fan Chart Width: Wide CI90 indicates high uncertainty Repaint Behavior: Runs only on barstate.islast, displayed at last bar Computation Load: Large nSims × forecastLen may slow rendering Cluster Initialization Sensitivity: K-means convergence depends on initial values (increase kmIters for stability) 🚨 Disclaimer This indicator is an advanced volatility-simulation tool for educational and research purposes only and does not constitute financial advice. GAN-style Monte Carlo prediction is a stochastic simulation method and does not guarantee future volatility. Historical patterns may not repeat — particularly during unprecedented events, the forecast may fail. Use with thorough validation and proper risk management.
Pine Script® Indikator
von AetherEdge
AetherEdge NeuraNet Trend Predictor🖊️ Overview AetherEdge NeuraNet Trend Predictor is a next-generation AI-driven trend forecasting indicator that fully implements a true Multi-Layer Perceptron (MLP) neural network in Pine Script. Nine-dimensional features flow through input → hidden → output layers, with weights self-updating every bar via backpropagation + Nesterov momentum + L2 regularization. This is the pinnacle of machine learning engines on TradingView—a system that perpetually evolves with market structure changes. 🔶 Key Features True MLP Implementation: 9-H-1 architecture (hidden 3–12 neurons) Online Learning: Deterministic gradient descent updating weights every bar Nesterov-Style Momentum: Accelerated convergence via gradient inertia L2 Regularization: Overfitting suppression Xavier Initialization: Theoretically optimal weight init Binary Cross-Entropy Loss: Optimal for probabilistic prediction 9-D Feature Engine: Price/EMA/RSI/ATR/Volume/MACD/BB/DMI/Structure Robust Normalization: z-score based statistical standardization Live Accuracy Tracking: Cumulative prediction accuracy % Loss EMA Monitoring: Visualized learning progress Network Visualization: Real-time input → hidden activation → output Probability Bar (right edge): 10-tier prediction visualization Confidence Computation: Auto-calculated via |prob - 0.5| × 2 AI VERDICT: 5-tier decision support messaging 🧠 Technical Architecture This indicator is an advanced neural network implementation grounded in genuine deep learning theory. Network Structure: Input layer: 9 neurons (feature vector) Hidden layer: 3–12 neurons (tanh activation) Output layer: 1 neuron (sigmoid, probability) Total params: 9×H + H + H + 1 Feature Engineering (9-D): f1: Price/EMA Fast deviation f2: EMA Spread (Fast vs Slow) f3: RSI normalized f4: ATR% z-score f5: Volume z-score (log-transformed) f6: MACD Histogram normalized f7: Bollinger Band Position f8: DMI differential f9: Structural position (high/low range) Forward Pass: h_j = tanh(Σ x_i × W1_ij + b1_j) prob = sigmoid(Σ h_j × W2_j + b2) Backpropagation: Output error: err = ŷ - y (BCE gradient) Hidden error: δ = err × W2 × (1 - h²) (tanh derivative) L2-regularized gradient: g = δ × x + λ × W Nesterov update: v = β×v - η×g; W += v Target Signal: Next bar direction (close > close ) Warmup: Signals activate after 200 bars of training Learning Statistics: Train Steps / Accuracy / Loss EMA / 100-bar Loss ⚙️ Recommended Settings & Tuning Guide Crypto Defaults: BTC (1H–4H): Standard (Hidden=6, η=0.05, β=0.9) ETH (15M–1H): Hidden=8, η=0.03 for precision SOL (high-vol): λ=0.005 to enhance overfitting suppression XRP (range): Hidden=4, η=0.07 for rapid adaptation Learning Rate (η): 0.01–0.03: Stability-focused, long-term trends 0.05: Balanced (recommended) 0.1–0.2: Fast adaptation for regime shifts Hidden Neurons: 3–4: Simple, low overfit risk 6: Balanced (recommended) 8–12: High capacity, requires sufficient data Warmup Period: 200 bars: Standard 500 bars: High-precision focus 100 bars: Quick activation Thresholds: Conservative: Long=0.75, Short=0.25, MinConf=0.7 Standard: Long=0.65, Short=0.35, MinConf=0.6 Aggressive: Long=0.6, Short=0.4, MinConf=0.5 💡 How to Use in Practice VERDICT = STRONG LONG CONVICTION: Neural net at >80% conviction—strongest entry Accuracy > 55%: Network in hot streak, high signal trust Accuracy < 50%: Regime shift in progress, stand aside Loss EMA declining: Learning healthy, precision improving Confidence > 70%: High-quality signal, full position consideration Feature panel watch: All features unidirectional = multi-faceted consensus Hidden activations: ●●● (strong) aligned = internal network consensus Probability bar extreme (>90%): Watch for reversal risk AetherEdge Synergy: All-in-One Dashboard HIGH-CONVICTION + NeuraNet STRONG = dual AI confirmation Self-Evolving S/R Grid strong line + NeuraNet aligned = ML × RL fusion Liquidity Sweep Bull Sweep + NeuraNet > 0.8 = institutional + AI sync Multi-TF: 4H for direction → 1H for NeuraNet wait → 15M for precision entry ⚠️ Important Notes Learning Reset: Weights initialize on every chart reload—warmup mandatory Initial Warmup: Minimum 200 bars required before predictions Accuracy Metric: Cumulative; treat <100 samples as preliminary Overfit Risk: Excess Hidden + low λ = overfitting—balance carefully Diverging η: η > 0.2 risks weight explosion—use cautiously Regime Changes: Sudden market shifts temporarily reduce Accuracy, auto-recovers Compute Load: Hidden=12 is heavy—use 6 on low-spec setups 🚨 Disclaimer This indicator is a machine learning demonstration provided for educational and research purposes only and does not constitute financial advice. Neural network predictions are statistical estimates based on historical patterns and do not guarantee future profits. Do not blindly trust AI model outputs—combine with independent analysis and proper risk management.
Pine Script® Indikator
von AetherEdge
AetherEdge Regime-Aware Trend Channel🖊️ Overview AetherEdge Regime-Aware Trend Channel is a next-generation dynamic channel system in which K-means clustering automatically classifies the market into three regimes — Range, Trend, and Volatile — and generates regime-specific channels in real time. Unlike conventional one-size-fits-all channels, it identifies the market's underlying character through unsupervised machine learning and reshapes itself accordingly. Upon breakout, it projects a confidence-decaying forward cone, visualizing "where price is likely heading next." 🔶 Key Features Automatic K-means Regime Classification: 4 features × 3 clusters Regime-Specific Channels: Optimal length & width per Range/Trend/Volatile Dynamic Retraining: Centroids recompute every recalcBars to track shifts Breakout Detection: ATR threshold + confirmation bars filter false breaks Forward Projection: Confidence-decaying cone for projBars after breakout Regime Color Visualization: Blue=Range / Green=Trend / Orange=Volatile Stats Panel: Real-time regime, centroid, and feature display Multi-Timeframe Friendly: Self-adapting design across all timeframes 🧠 Technical Architecture This indicator is an adaptive channel AI built around unsupervised K-means learning. 4-Dimensional Feature Vector: ①EMA21–50 divergence (f1: trend strength) ②Normalized stdev (f2: volatility) ③High–low range / ATR (f3: range-ness) ④EMA21 slope (f4: directionality) — multidimensional market character. Min-Max Normalization: All features scaled to 0–1 over trainBars window for fair distance computation. K-means Clustering: regimeK centroids initialized evenly across trainBars → maxIter iterations of nearest-centroid assignment → centroid update until convergence. Centroid Classification: trendScore = c1 + c4, volaScore = c2, rangeScore = 1 − c3 − c1; the maximum determines regime type per centroid. Real-time Prediction: Computes Euclidean distance from current vector to all centroids; nearest centroid's regimeType is adopted. Adaptive Channel Engine: Different lengths (chRangeLen / chTrendLen / chVolaLen) per regime extract highs/lows, scaled by WidthMul × ATR. Breakout Detection: Triggered when deviation exceeds breakATRMul × ATR for breakConfirmBars consecutive bars. Forward Projection: Cone-shaped confidence band drawn projBars ahead with projDecay exponential decay. ⚙️ Recommended Settings & Tuning Guide Crypto Defaults: BTC (4H): trainBars=500, regimeK=3, recalcBars=50, featureWin=20 ETH (1H): trainBars=400, regimeK=3, recalcBars=40, chTrendLen=50 SOL/XRP (15M): trainBars=300, regimeK=3, recalcBars=30, featureWin=15 Long-Term (1D): trainBars=800, regimeK=4, recalcBars=80, chTrendLen=100 Tuning Guide: Granular classification: regimeK=4–5 (requires more data) Fast response: recalcBars=20 for frequent retraining (heavier load) Stability priority: recalcBars=100, maxIter=20 for robust centroids Trend-following: trendWidthMul=2.5 for wider breakout tolerance Mean-reversion: rangeWidthMul=0.8 for tight Range channels Volatile markets: volaWidthMul=3.0 to suppress false signals Conservative breakouts: breakConfirmBars=3, breakATRMul=0.7 💡 How to Use in Practice Range Strategy: In blue regimes, fade extremes — mean-reversion plays Trend Strategy: In green regimes, buy dips / sell rallies — trend-following Volatile Strategy: In orange regimes, reduce size and await clean breaks Breakout Follow-through: Enter in cone direction; consider TP at cone tail Regime Shift Signal: Color changes mark regime transitions = strategy switch points Multi-Timeframe: Higher-TF regime + lower-TF channel edges for entry precision AetherEdge Synergy: When Adaptive Fibonacci AI ratios align with channel edges → ultra-high-confidence zones ⚠️ Important Notes Regime classification is inactive until trainBars of data accumulates K-means is initialization-sensitive; classification may fluctuate at retraining moments Too-short recalcBars destabilizes centroids and adds noise Sudden regime shifts may incur a few bars of lag Excessive regimeK fragments data per cluster, reducing classification accuracy The projection cone is a probabilistic forecast, not a price guarantee 🚨 Disclaimer This indicator is provided for educational and research purposes only and does not constitute financial advice. K-means classification and projection forecasts are based on historical data and do not guarantee future performance. All trading decisions are made at your own risk and should be accompanied by proper risk management.
Pine Script® Indikator
von AetherEdge
AetherEdge SMC AI Confidence Engine🖊️ Overview AetherEdge SMC AI Confidence Engine is a next-generation SMC engine fusing Smart Money Concepts—the language of institutional footprints—with 8-factor AI confidence scoring and kNN pattern matching. It auto-detects the three pillars of smart-money zones (Order Blocks, Fair Value Gaps, Liquidity Sweeps) and instantly delivers an A+ to D conviction grade by integrating eight weighted factors: structure integrity, displacement, volume, MTF consensus, kNN similarity, imbalance, freshness, and confluence. A data-driven SMC intelligence that answers the eternal question: "Which zone is real?" 🔶 Key Features 3 Core SMC Zone Detection: Order Block / Fair Value Gap / Liquidity Sweep 8-Factor AI Scoring: Structure / Displacement / Volume / MTF / kNN / Imbalance / Freshness / Confluence kNN Pattern Matching: 5-D feature space, K-nearest historical analogs A+/A/B/C/D Grades: Intuitive five-tier conviction ranking 3-Layer MTF Consensus: 1H / 4H / D triple confirmation BOS/CHoCH Detection: Auto-identifies structural breaks Mitigation Tracking: Records zone-touch events; Fresh/Mitigated state Confluence Detection: Auto-bonuses overlapping zones Dynamic Visualization: Transparency, border & size scale with score Top-Zone Detail Panel: Full 8-factor breakdown with bar visualization Ranking Table: Up to 10 zones sorted by composite score Custom Weights: Tune all 8 factors to fit your trading style 🧠 Technical Architecture This indicator elevates SMC theory into a statistical / machine-learning framework, delivering industry-leading smart-money intelligence. Zone Detection Logic: Order Block: Strong displacement (ATR×1.5+) + volume Z>0.5 + BOS triggers backward scan to last opposite-colored candle FVG: 3-bar gap exceeding ATR × fvgMinSize Liquidity Sweep: Recent swing pierced by sweepTol × ATR then reversal close 8-Factor Scoring (each normalized 0–100): Structure Integrity — trend alignment + BOS bonus Displacement Strength — birth-time displacement magnitude Volume Profile — birth-time volume Z-score MTF Consensus — sum of 3 HTF EMA20/50 slopes (–3 to +3) kNN Pattern Match — 5-D feature K-NN average forward magnitude Imbalance Ratio — zone size ÷ ATR Freshness/Age — exp(-age/150) decay, –30 if mitigated Confluence Score — bonus per overlapping zone kNN Engine: Features: displacement / volZ / bodyRatio / atrRatio / rangeRatio 300-bar history buffer, K=5 nearest by Euclidean distance Average 5-bar-forward absolute move scored probabilistically Weighted Composite: composite = Σ(factor_i × weight_i) / Σweights Dynamic Update: All active zones rescored every confirmed bar Grade Mapping: ≥85=A+, ≥75=A, ≥65=B, ≥50=C, <50=D ⚙️ Recommended Settings & Tuning Guide Crypto Defaults: BTC (4H–D): Pivot=5, OBLookback=50, MTF=4H/D/W ETH (1H–4H): Pivot=5, fvgMinSize=0.3, MTF=1H/4H/D (standard) SOL (high-vol): Pivot=7, sweepTol=0.15, fvgMinSize=0.4 XRP (short-swing): Pivot=3, OBLookback=30, MTF=15M/1H/4H Pivot Length (structure sensitivity): 3: agile, noisy 5: standard 7–10: major-structure only, HTF use FVG Min Size: 0.2: catch fine gaps 0.3: standard 0.5: strong FVGs only Weight Tuning by Style: Trend Follower: Structure↑, MTF↑, Displacement↑ Counter-Trader: kNN↑, Freshness↑, Imbalance↑ Scalper: Volume↑, Displacement↑, Freshness↑ Swing Trader: MTF↑, Confluence↑, Structure↑ Min Score Display: 40: standard (hide D) 65: B+ only, clean view 75: A+ only, ultra-curated kNN Config: K=3: sharp similarity, unstable K=5: standard K=10–15: smooth, averaged 💡 How to Use in Practice A+ Zones (≥85%): Gold-bordered ultimate-conviction zones, primary thesis A Zones (75–85%): High quality, multi-factor agreement, entry candidates B Zones (65–75%): Reference level, combine with other evidence C/D (<65%): Information only, generally ignore Fresh + A+: Untouched apex zone, optimal ambush Mitigated + High Score: Past battlefield, high re-test reaction probability Confluence Areas: OB + FVG + Sweep overlap = institutional decision zones Trade Scenarios: Bull OB A+ + MTF Strong Bull: Golden pullback long Bear FVG A + Liquidity Sweep up-pierce: Short opportunity BOS Up + Recent A+ Zone: Trend-confirmation entry AetherEdge Synergy: Self-Evolving S/R Grid: A+ zone + strong S/R line overlap = ultimate alignment LSTM Forecaster: Bullish prediction + Bull OB A+ = dual AI conviction NeuraNet Predictor: Direction match + zone reach = high-probability entry All-in-One Dashboard: HIGH-CONVICTION + A+ zone = supreme alignment Multi-TF Workflow: Identify A+ zones on D/4H → precise entry on 1H/15M ⚠️ Important Notes kNN Warm-up: <300 bars yields unstable similarity, fixed 50-score Zone Cap: Oldest zones auto-pruned beyond maxZones Weight Normalization: Auto-normalized regardless of total—relative influence MTF Lag: HTF references confirmed bars; first few bars unfinalized Detection Delay: Pivots confirm pivotlen bars later; real-time slight delay Zone Overlap: Same OB may be detected multiple times—use as confluence signal 🚨 Disclaimer This indicator is an SMC analysis support tool provided for educational and research purposes only and does not constitute financial advice. AI confidence scores are probabilistic indicators based on mathematical approximation and do not guarantee future profits. Scores are one input among many—combine with independent analysis and proper risk management.
Pine Script® Indikator
von AetherEdge
AetherEdge Liquidity Void Detector🖊️ Overview AetherEdge Liquidity Void Detector is a next-generation indicator that fuses liquidity sweep detection with a NeuraLib-style multivariate probability model to visualize the hidden "price vacuum zones" (Liquidity Voids) lurking in the market. It probabilizes the footprints left by smart money through an AI sigmoid function and forecasts the unfilled zones price is destined to revisit. The full institutional logic of Sweep → Void generation → Fill prediction is automated end-to-end. 🔶 Key Features Automatic Liquidity Sweep Detection: Wick, rejection, and confirmation logic NeuraLib-Style Probability Model: 4 features × weighted sigmoid for Void probability Dynamic Void Zone Generation: ATR-based size filter + adjacent merging Fill Direction Prediction: Arrows visualizing where price must go Target Line Drawing: Clear Fill price markers Volume Anomaly Confirmation: Dual-validation via Z-score + burst multiplier Probability Labels: Numerical confidence per Void Stats Panel: Active Void count and average probability in real time 🧠 Technical Architecture This indicator is a sophisticated liquidity analysis engine merging Smart Money Concepts (SMC) with a machine-learning-style probability model. Liquidity Sweep Detection: Detects temporary breaks of recent highs/lows over sweepLookback bars followed by wick rejection. Confirmed when upperWick/candleRng ≥ sweepWick, rejection ≥ sweepRejection × ATR, and a reversal candle prints. 4-Feature Probability Model: ①sweepStrength (rejection/ATR) ②volZ (volume Z-score) ③priceImpulse (3-bar move/ATR) ④gapMagnitude (open gap/ATR). NeuraLib-style Sigmoid Scoring: p(void) = σ(1.8·sweep + 0.9·volZ + 0.6·impulse + 0.4·gap − 1.2). Logistic-regression-style scoring with pretrained-style fixed weights. Volume Anomaly Confirmation: Triggered by volZ > volZThreshold OR volume > volMA × volBurstMul to suppress false positives. Void Zone Generation: Boundaries determined by sweep direction. Bullish Void = vacuum below; Bearish Void = vacuum above. Adjacent Merging: Auto-merges Voids within voidMergeATR × ATR proximity to reduce visual noise. Lifecycle Management: Voids expire after voidMaxBars or transition to filled when price reaches them. Fill Urgency Decay: fillUrgencyDecay exponentially decays urgency over time, prioritizing fresh Voids. ⚙️ Recommended Settings & Tuning Guide Crypto Defaults: BTC (4H): sweepLookback=20, voidProbMin=0.55, volZThreshold=2.5 ETH (1H): sweepLookback=15, voidProbMin=0.60, sweepWick=0.65 SOL/XRP (15M): sweepLookback=12, voidProbMin=0.50, volBurstMul=2.5 Long-Term (1D): sweepLookback=30, voidProbMin=0.65, voidMaxBars=150 Tuning Guide: High-frequency signals: voidProbMin=0.45, sweepWick=0.5 for looser detection High-quality only: voidProbMin=0.70, sweepConfirm=2 for precision priority Volatile markets: volZThreshold=3.0, volBurstMul=3.0 for stricter anomaly criteria Quiet markets: sweepRejection=0.3, voidMinSize=0.3 for higher sensitivity Scalping: voidExtendBars=20, fillUrgencyDecay=0.90 for short-term projection Swing: voidExtendBars=80, voidMaxBars=150 for long-term Void tracking 💡 How to Use in Practice Sweep → Reversal: Upward sweep + high-probability Bearish Void = short opportunity Void Fill Trades: Enter along Fill direction arrow toward target line Unfilled Zone Targets: Use high-probability Voids as profit targets Multi-Timeframe: Sweep on lower TF inside higher-TF Void = sniper entries Volume Anomaly Confirmation: Z-score + volBurst together = likely institutional flow AetherEdge Synergy: Overlap with Regime-Aware Trend Channel boundaries → ultra-high-confidence zones Avoid: Voids below 0.55 probability or sweeps without volume anomaly ⚠️ Important Notes Liquidity Void is a hypothesis based on SMC; fills are not guaranteed News-driven moves may behave outside model assumptions Excessively low voidProbMin produces signal overload and noise Weights are fixed and not optimized per specific instrument Increasing confirmation bars boosts accuracy but adds latency Merging may consolidate multiple Voids into one zone 🚨 Disclaimer This indicator is provided for educational and research purposes only and does not constitute financial advice. Liquidity Void detection and probability modeling are based on historical data and fixed-weight coefficients, with no guarantee of future performance. All trading decisions are made at your own risk and should be accompanied by proper risk management.
Pine Script® Indikator
von AetherEdge
ICT Killzones [by fantasio]# ICT Killzones & Pivots --- **ICT Killzones & Pivots** visualizes the main institutional trading sessions based on Michael Huddleston's ICT (Inner Circle Trader) methodology: Asia, London, NY AM, NY Lunch and NY PM. **🕐 Killzones** Colored session boxes with customizable labels, transparency and text display. **📐 Pivots** High/low pivot lines per session, with optional midpoint. Extend until mitigated or past mitigation, for the most recent session or all of them. Optional price labels on left or right side of the chart. **📅 Day / Week / Month** Opening price lines with optional High/Low levels and period separators. **⏰ Opening Prices & Timestamps** Up to 8 custom opening price lines (True Day Open, etc.) and 4 vertical timestamp lines. **📊 Range Table** Per-session range display with configurable average length. **⚙️ Settings** Timezone, timeframe limit, line styles, label size and transparency are all fully customizable. Drawings above the selected timeframe are automatically hidden. **🔔 Alerts** Pivot breaks and HTF High/Low breaks supported. --- *ICT session and pivot concepts are based on the methodology developed by Michael Huddleston (Inner Circle Trader).*
Pine Script® Indikator
von Fantasio2020
Next Bar UP/DOWN Volume-Weighted Predictor📊 AI Volume-Weighted Predictor Trading Strategy 1. High-Volume Long Setup (Bullish Breakout) Entry Condition: Next Bar UP probability is 80% or higher. Vol Status shows "🔥 High Vol Bullish" (Current volume > 20-period Volume MA with a bullish bar). EMA 1, 2, 3 are in a perfect bullish alignment (EMA 5 > EMA 10 > EMA 20). Execution: Open a Long / Buy position at the open of the next bar. Target Price: Take profits at the EMA(5) Predict price or when Vol Status shifts to "Low Volume." 2. High-Volume Short Setup (Bearish Breakdown) Entry Condition: Next Bar DOWN probability is 80% or higher. Vol Status shows "💥 High Vol Bearish" (Current volume > 20-period Volume MA with a bearish bar). EMA 1, 2, 3 are in a perfect bearish alignment (EMA 5 < EMA 10 < EMA 20). Execution: Open a Short / Sell position at the open of the next bar. Target Price: Take profits at the EMA(5) Predict price or when Vol Status shifts to "Low Volume." 3. Risk Management & False Breakout Filters Low Volume Filter: If Vol Status displays "💤 Low Volume", skip the trade even if the probability is above 70%. Price moves without volume are highly prone to reversals. Stop Loss (SL): Place your stop loss 1.5x ATR below the entry price for Longs, or 1.5x ATR above the entry price for Shorts. Alternatively, use the current EMA 20 line as a hard stop. Trailing Stop: Once the trade moves into profit, trail your stop loss along the EMA 10 line to secure gains.
Pine Script® Indikator
von wie77
Internal & External MSSHere is a quick breakdown of what it does and its key features: Dual Tracking (Internal vs. External): It calculates two different sets of market swings simultaneously. It tracks smaller, short-term price movements (Internal MSS) and larger, structural price movements (External MSS). Overlap Prevention: To keep your chart clean, if a short-term Internal shift and a long-term External shift occur at the exact same price level, the script is programmed to only draw the more significant External level. Wick vs. Body Calculation: You can toggle the settings to define market structure using either the extreme highs/lows of the candle wicks, or the real bodies (open/close) of the candles. Smart Label Placement: Breakout lines are drawn horizontally from the broken swing point, and text labels (like "E-MSS" or "i-MSS") automatically float above or below the lines so they don't collide with the drawings. Fully Customizable Visuals: Through the settings menu, you can easily change the line colors, thickness, dashed/solid styles, and the exact text used for the labels without needing to edit the code again.
Pine Script® Indikator
von marstradesict
AetherEdge Adaptive LSTM-inspired Forecaster🖊️ Overview AetherEdge Adaptive LSTM-inspired Forecaster is a next-generation price forecasting engine that recreates the core machinery of the LSTM (Long Short-Term Memory) neural network—the cornerstone of deep learning—directly in Pine Script. Featuring a multi-layered memory structure of forget, input, output gates and cell state, augmented by an Attention mechanism that dynamically references the most relevant past moments, plus residual connections that bypass training instability, it fuses multi-timeframe features to render 1–30 bar price forecasts and uncertainty bands with exceptional fidelity. 🔶 Key Features LSTM-style Cell: Full implementation of forget/input/output gates + cell state Parallel Hidden Units: 3–16 units with diverse time constants τ for layered memory Attention Mechanism: Similarity + recency-decayed weighted context Residual Connection: Skip connection bypassing vanishing-gradient pitfalls Multi-Timeframe Features: HTF (1H) + HHTF (4H) hierarchical inputs 8-D Input Vector: retZ / volZ / RSI / Slope / Mom / HTF Ret / HTF Bias / HHTF Bias Multi-Step Forecast: 1–30 bar projection lines Uncertainty Bands: √t-decay confidence intervals (inner 1σ / outer 2σ) 3 Band Methods: Residual Std / ATR / Hybrid Hidden Unit Visualization: τ, Cell, Hidden & activity bars per unit Attention Heatmap: 30-bar attention weight distribution Hit Score: Real-time evaluation of last forecast accuracy Bullish/Bearish Flip & Band-Breach Alerts 🧠 Technical Architecture This indicator is an industry-leading neural forecasting engine fully reconstructing the mathematical essence of LSTM, the apex of RNN-family models, in Pine Script. LSTM Cell Equations (per unit u): Forget Gate f_t = σ(W_f · x_t + b_f) — past memory retention Input Gate i_t = σ(W_i · x_t + b_i) — new information intake Candidate g_t = tanh(W_g · x_t + b_g) — new memory candidate Output Gate o_t = σ(W_o · x_t + b_o) — exposure to hidden state Cell Update c_t = f_t ⊙ c_{t-1} + i_t ⊙ g_t Hidden h_t = o_t ⊙ tanh(c_t) τ Diversity: Each unit assigned distinct τ, processing short-to-long memory in parallel Pseudo-Weight Generation: Deterministic sin/cos phase for stable initialization MTF Influence Boost: Input gate amplified by HHTF Bias magnitude Attention: Score = h_curr × h_past − |h_curr − h_past|×0.5 + recency decay Softmax normalization (temperature-adjustable) → context = weighted mean Residual Path: Upper-half units add raw retZ × residualMix × (1-τ) Output Projection: h_aggregated × σ_returns × 0.5 + Attention + Residual contributions Uncertainty Model: σ_h = σ_base × fanOut^h × √h (band widens with horizon) Decay Forecast: Multi-step uses stepRet × 0.82^(h-1) (extrapolation decay suppresses overshoot) ⚙️ Recommended Settings & Tuning Guide Crypto Defaults: BTC (4H–D): Hidden=8, Seq=30, Forecast=10 (standard) ETH (1H–4H): Hidden=10, Seq=40, MTF Weight=0.4 SOL (high-vol): Hidden=12, Forget=0.88, fanOut=1.20 XRP (short-bias): Hidden=6, Seq=20, Forecast=5 Hidden Units (Memory Capacity): 3–5: Lightweight, short-pattern specialized 8: Standard (recommended) 12–16: Rich memory, heavier compute Sequence Length (Attention Range): 20: Recency-focused 30: Standard 50–100: Long context, lower TFs Learning Rate α (lrBase): 0.05–0.10: Conservative, smooth 0.15: Standard 0.25–0.50: Agile, noisier Forget Gate Base: 0.85–0.90: Agile forgetting, regime-shift responsive 0.92: Standard 0.95–0.98: Long memory, range-favoring Attention Temperature: 0.5–1.0: Sharp focus, specific-pattern referencing 1.5: Standard 2.5–5.0: Even attention, stable but dull Band Method: Residual Std: Empirical, most precise ATR: Simple, valid early Hybrid: Geometric mean, robust 💡 How to Use in Practice Strong Bullish Forecast: σ-breach prediction + positive attention = long entry Strong Bearish Forecast: Opposite, short consideration Band Breach: Price exceeded ±2σ band, overheating warning Forecast Flip: expectedRet zero-cross, early regime-shift signal Hit Score > 70%: Last forecast accurate, current trustworthy Hit Score < 40%: Sudden volatility regime, low confidence—wait Hidden Unit Activity: Multiple units same direction = strong consensus; mixed = regime transition Attention Heatmap purple-dominant: Strong reference to past similar pattern, repeating-scenario likely Attention dispersed: No precedent, novel territory—tread cautiously AetherEdge Synergy: KNN Regime Classifier: Trending▲ + LSTM bullish forecast = dual AI conviction NeuraNet Predictor: Direction agreement amplifies signal Self-Evolving S/R Grid: LSTM band edges ≈ S/R lines = strong reaction candidates All-in-One Dashboard: HIGH-CONVICTION + Hit Score > 70% = ultimate alignment Multi-TF: 4H LSTM direction → 1H strategy selection → 15M precision entry ⚠️ Important Notes Pseudo-Weights: No pre-trained weights; deterministic phase-based approximation Learning Reset: Cell states wipe on reload; rebuild required First 50 Bars: States unfinalized, forecasts invalid Compute Load: Hidden=16 + Seq=100 is heavy; use 8/30 on low-spec MTF lookahead_off: No future-peeking, real-time integrity guaranteed Multi-Step Drift: Error accumulates with horizon; Forecast=5–10 recommended Bands are Probabilistic: σ-range exceedance can occur; not absolute ceilings/floors 🚨 Disclaimer This indicator is a deep-learning-inspired forecasting model provided for educational and research purposes only and does not constitute financial advice. LSTM-style predictions are mathematical approximations and do not guarantee future profits. Forecast accuracy depends on market conditions, asset, and timeframe. Combine with independent analysis and proper risk management.
Pine Script® Indikator
von AetherEdge
AetherEdge KNN Regime Classifier🖊️ Overview AetherEdge KNN Regime Classifier is an innovative memory-based machine learning regime classifier that fully implements the k-Nearest Neighbors (k-NN) algorithm in Pine Script. It memorizes up to 2,000 historical patterns, retrieves the k most similar past patterns matching the current 8-dimensional feature vector, and classifies the market into five regimes (Trending Up / Trending Down / Range / Breakout / Reversal) in real time via majority voting. Each regime's forward returns and historical win-rate are statistically tracked, providing multi-dimensional data-driven trade support. 🔶 Key Features True k-NN Implementation: k tunable from 3–50, odd numbers preferred Memory Bank: Up to 2,000 patterns stored, FIFO auto-discard 3 Distance Metrics: Euclidean / Manhattan / Cosine 2 Voting Schemes: Majority / Distance-weighted (1/d) 5 Regime Classification: Trending▲ / Trending▼ / Range / Breakout / Reversal Forward-Looking Validation: Each pattern verified against N-bar future return 8-D Feature Vector: ADX/DMI/BBW/RSI/Volume/Slope/Position/ROC Live Win-Rate Table: Statistical edge of each regime visualized KNN Distance Heatmap: Nearest-to-farthest distance distribution Vote Distribution Bars: % bars showing votes per regime Confidence Computation: Auto-derived from vote concentration Regime Background Tinting: Instant chart-wide regime visibility High-Confidence Regime Shift Alert: Triggered at Confidence > 85% 🧠 Technical Architecture This indicator is a top-tier regime classification engine fully implementing k-NN, the flagship of memory-based (lazy) learning. k-NN Algorithm: Compute query vector q = Calculate distance d(q, m_i) to all memory patterns Select top-k by ascending distance Vote: argmax_l Σ w_i × Distance Metrics: Euclidean: √Σ(q_i - m_i)² — standard geometric Manhattan: Σ|q_i - m_i| — outlier-robust Cosine: 1 - (q·m)/(|q||m|) — direction-focused Weighting Schemes: Majority: Plain vote Distance-weighted: w = 1/(d + ε) — closer = stronger Feature Engineering (8-D): f1: ADX strength (trend presence) f2: DMI differential (direction) f3: BBW ratio (volatility expansion) f4: RSI normalized (momentum) f5: Volume z-score (liquidity) f6: Linear Regression Slope (structural tilt) f7: Range Position (within high-low) f8: ROC (rate of change) Regime Labeling Rules: Breakout: BBW > 1.5×avg AND Volume > 1.8×avg AND |ROC| > 1.0 Reversal: RSI extreme AND ROC sign flipped Trending Up: ADX > 25 AND DI+ > DI- AND Slope > 0 Trending Down: ADX > 25 AND DI- > DI+ AND Slope < 0 Range: ADX < 18 AND BBW < 1.2×avg Forward-Looking Validation: Win/loss decided after N (default 5) bars Memory Management: Staging queue → committed after forward window → FIFO once size exceeded ⚙️ Recommended Settings & Tuning Guide Crypto Defaults: BTC (4H–D): k=15, Memory=500, Forward=5 (standard) ETH (1H–4H): k=11, Cosine, Forward=8 SOL (high-vol): k=21, Manhattan (outlier-robust) XRP (range-heavy): k=9, Forward=3 for short-horizon edge k Tuning: k=3–7: High sensitivity, noisy k=11–15: Balanced (recommended) k=21–31: Smooth, may dilute rare patterns Memory Size: 300: Lightweight, recent-trend focused 500: Standard 1000–2000: Long-term stats, heavy compute Forward Bars: 3: Scalping 5: Standard 10–15: Swing-oriented Distance Metric Selection: Euclidean: Standard, balanced Manhattan: High-vol assets, outlier-heavy Cosine: Pattern-shape focus, magnitude-agnostic 💡 How to Use in Practice Trending▲ + Confidence > 70%: Optimal trend-following entry Breakout detected: Activate volatility-breakout strategies Reversal warning: Reduce trend-follow size, consider counter-trend Range: Range/grid strategies fit Win-Rate Table analysis: Discover statistically dominant regimes for your asset Avg Ret monitoring: Trending▲ with high +Avg Ret = trend-follow valid Confidence < 50%: Vote dispersion, regime unclear—reduce size Heatmap green-dominant: Abundant similar patterns, high prediction trust Heatmap red-dominant: Uncharted territory—proceed cautiously AetherEdge Synergy: NeuraNet Predictor: KNN Trending▲ + NeuraNet > 0.7 = dual AI conviction Self-Evolving S/R Grid: Breakout regime + line breach = strong entry All-in-One Dashboard: HIGH-CONVICTION + high KNN confidence = ultimate alignment Multi-TF: 4H KNN regime → 1H strategy selection → 15M precision entry ⚠️ Important Notes Learning Reset: Memory wipes on chart reload; rebuild required Min Samples (50): Classification disabled prior; wait phase mandatory FIFO Memory: Old patterns auto-discarded for regime adaptation Compute Load: Memory=2000 + k=50 is heavy; use 500/15 on low-spec Feature NaN: Features undefined initially; accumulation starts after structLen+50 bars Rare regimes: Reversal/Breakout occur infrequently; small N = unstable stats Forward Window Lag: Most recent N bars not yet labeled; memory commit delayed 🚨 Disclaimer This indicator is a machine learning demonstration provided for educational and research purposes only and does not constitute financial advice. k-NN classification results derive from statistical similarity to past patterns and do not guarantee future profits. Reliability depends on market conditions, asset, and timeframe. Combine with independent analysis and proper risk management.
Pine Script® Indikator
von AetherEdge
Precision ORB FrameworkPrecision ORB Clean v17 is part of the Precision ORB Framework — a structured futures trading model developed around opening range behavior, VWAP positioning, liquidity sweeps, market acceptance, and clean breakout confirmation. This framework was built specifically for NQ and index futures execution, combining: • Opening Range Breakouts (ORB) • VWAP trend alignment • Liquidity sweep detection • Acceptance candle confirmation • Trend bias filtering • REV? rejection warnings • Dynamic TP1 / TP2 targeting • Price discovery grid targets The companion “Precision Entry Assistant” indicator was developed alongside this framework to assist with lower timeframe execution, market state filtering, and cleaner trade timing. This is not intended to be a prediction tool or signal-selling script. The framework is designed to help traders structure decision-making around momentum, liquidity, volatility expansion, and disciplined execution.
Pine Script® Indikator
von stuartant540
Wavelet Energy Cascade [forexobroker]Wavelet Energy Cascade decomposes close into 4 dyadic Haar wavelet scales (lengths 1, 2, 4, 8) and tracks their energies. Coarse-scale dominance over fine-scale signals trending; fine-scale dominance signals noise. The coarse Haar smoothed line provides the entry trigger. Distinct from any moving average: wavelets are a multi-resolution decomposition with explicit energy bookkeeping per scale. 🔶 ALGORITHM 1. Haar coefficient at scale s = (avg of s most recent - avg of s prior) / sqrt(2). 2. Compute coefficients h1, h2, h4, h8. 3. Energy_s = math.sum(h_s^2, lookback) — squared coefficients summed over a rolling window. 4. fine = e1 + e2; coarse = e4 + e8. 5. Trending regime when coarse > k * fine. 6. Coarse Haar smoother (sma(close, 8)) provides the entry-trigger reference. 🔶 SIGNAL LOGIC - Buy: trending AND close crosses coarse line up AND h8 > 0 AND not already long AND cooldown elapsed AND barstate.isconfirmed. - Sell: trending AND close crosses coarse line down AND h8 < 0. - Position-lock state machine. 🔶 INPUTS - Energy Lookback (default 40) - Coarse / Fine Dominance k (default 1.5) - Cooldown Bars (default 4) - Visual: dashboard, glow, coarse line, buy / sell colors 🔶 ALERTS WEC Buy, WEC Sell, WEC Any Signal, WEC Trend Start, WEC Trend End, WEC Strong Trend, WEC Cross Up, WEC Cross Down, WEC Webhook JSON. 🔶 LIMITATIONS - Haar is the simplest wavelet (orthogonal, but with sharp edges); for smoother decomposition, Daubechies-like wavelets would help — at higher Pine cost. - Only 4 scales; missing very-low or very-high frequencies if they matter for the asset. - Energy lookback dominates the smoothing trade-off; smaller = more responsive, noisier. - The h8 sign gate ensures direction agrees with the coarse-scale wavelet; rare divergences are filtered.
Pine Script® Indikator
von forexobroker
AetherEdge Adaptive Fibonacci AI🖊️ Overview AetherEdge Adaptive Fibonacci AI is a machine-learning-driven adaptive Fibonacci engine that completely transcends traditional static ratios. A KNN (K-Nearest Neighbors) algorithm extracts the most similar historical regimes from up to 2,000 prior bars and learns which golden ratios actually worked in those analogous conditions. It then probabilistically computes a breakout probability for each level — a revolutionary tool that visualizes "which Fib will hold" as a forward-looking forecast. 🔶 Key Features Dynamic Swing Detection: ATR-based filtering of meaningful swings only KNN Similarity Engine: 6-dimensional feature × cosine similarity matching Adaptive Fibonacci: Learns ratios that worked in similar regimes 3 Modes: Standard (fixed) / Adaptive (learned) / Hybrid (fused) Breakout Probability Forecast: % probability displayed per level 3-Tier Color Coding: High / Mid / Low breakout probability Predicted Extension Lines: 1.272 / 1.618 / 2.0 projection rendering Dynamic Line Width: Higher similarity = thicker emphasis Stats Panel: Visualizes similarity, ratio adoption, and processing state 🧠 Technical Architecture This indicator is a KNN-driven Fibonacci AI that "learns from the past." Swing Detection: pivothigh / pivotlow at swingLen, filtered by minSwingATR × ATR to eliminate noise. Swing ID tracking minimizes recomputation. 6-Dimensional Feature Vector: ①Return (f_ret) ②Volatility ratio (f_volaRatio) ③Volume ratio (f_volRatio) ④EMA slope (f_slope) ⑤Range position (f_rangePos) ⑥Normalized RSI (f_rsi) — vectorizes current market state. Cosine Similarity: Computes similarity between the current vector and each historical state vector, quantifying regime resemblance on a -1 to 1 scale. KNN Search: Scans historyBars range with sampleStep intervals, extracts top-K (knnK) similar states. similarityMin threshold filters out low-quality matches. Level Harvesting: Reverse-engineers reactive price levels from analogous regimes, matches them against candidateRatios (18 ratios from 0.146 to 2.618), and accumulates them into adaptiveRatios. Weighted Voting: Each ratio is quality-scored via similarity-weighted voting. Breakout Probability: Calculated from price behavior (break vs. respect) around each level over probLookback bars. Hybrid Mode: Combines standard Fibs with adaptive Fibs to harness both worlds. ⚙️ Recommended Settings & Tuning Guide Crypto Defaults: BTC (4H): swingLen=10, knnK=8, historyBars=2000, similarityMin=0.55 ETH (1H): swingLen=8, knnK=10, historyBars=1500, similarityMin=0.50 SOL/XRP (15M): swingLen=6, knnK=12, historyBars=1200, similarityMin=0.45 Long-Term (1D): swingLen=15, knnK=6, historyBars=3000, similarityMin=0.60 Tuning Guide: Precision: similarityMin=0.70, knnK=5 for ultra-selective matching Maximum learning: historyBars=4000, sampleStep=2 to maximize data Speed priority: sampleStep=5, featureLen=15 to reduce load Trending markets: includeExt=true, showBeyond=true for projection emphasis Range markets: adaptMode=Adaptive to prioritize learned ratios Beginners: adaptMode=Hybrid offers the safest standard + AI dual view 💡 How to Use in Practice High-Probability Bounce: colLowProb (green) levels are strong S/R — bounce entry candidates Breakout Plays: colHighProb (red) levels signal high break expectation — follow-through trades Adaptive Edge: Non-standard ratios (0.65, 0.707, etc.) appearing in Adaptive mode are regime-specific key levels Extension Targets: Use 1.272 / 1.618 / 2.0 projections for take-profit Multi-Timeframe: Higher TF adaptive Fibs + lower TF entry refinement AetherEdge Synergy: When Neural OB Evolution elite OBs overlap an adaptive Fib → confluence powerhouse zone ⚠️ Important Notes The first several hundred bars lack training data, so Adaptive mode may not function well early on Increasing historyBars improves accuracy but raises computational load (trade-off) Effectiveness drops during sudden regime shifts that have no historical analog Levels are not drawn until swings confirm (swingLen bars later) KNN processing executes on bar close — real-time reflection occurs on the next bar Excessively large featureLen risks over-referencing outdated patterns 🚨 Disclaimer This indicator is provided for educational and research purposes only and does not constitute financial advice. KNN similarity and probability forecasts are based on historical data and do not guarantee future performance. All trading decisions are made at your own risk and should be accompanied by proper risk management.
Pine Script® Indikator
von AetherEdge
Cloud Institutional Bands | Rainbow MatrixGENERAL OVERVIEW The Cloud Institutional Bands is a statistical price-envelope indicator that maps institutional accumulation and exhaustion zones using deviation channels built on a Log-Normal regression anchored to a dynamic VWAP. Instead of treating the chart as a series of fixed support and resistance levels, the indicator continuously classifies the current price into one of four statistical regimes — and colors the chart accordingly. The main goal of this indicator is to give traders a clean, automatic read on how stretched price is relative to its own statistical baseline — without having to manually identify trend strength, overextension, or exhaustion zones bar by bar. Every band you see on the chart represents a specific deviation from the volume-weighted regression base, and every color tells you which statistical zone is currently active. It plots four pairs of deviation bands (eight bands in total: four above the regression base and four below), each calibrated to a Fibonacci-proportioned sigma multiplier. Combined with the dynamic VWAP and the Zone Info Panel, the indicator gives a complete read on directional bias, statistical position, and proximity to extreme zones — all from a single visual. This indicator was developed for traders who already understand band-based indicators (Bollinger, Keltner, Donchian) and want a statistically corrected envelope that handles asymmetric price distributions properly, particularly during volatility expansion phases. WHAT IS THE THEORY BEHIND THIS INDICATOR? Most envelope indicators on TradingView — Bollinger Bands, Keltner Channels, and their derivatives — share a common architectural choice: they apply standard deviation directly to the price series, using a Simple Moving Average (or similar linear estimator) as the central tendency. This treats price as a symmetric variable. The problem: price is not symmetric. Price has a hard floor at zero and unbounded upside. Its returns follow a log-normal distribution, not a normal one. Applying linear statistics to asymmetric data introduces a systematic bias — bands that are too wide on one side and too narrow on the other, especially during volatility expansion. This bias becomes most visible at exactly the moments traders need accuracy most: trend climaxes, blow-off tops, capitulation lows. This indicator addresses that bias by performing the regression in log space. The price series is first transformed via the natural logarithm, the linear regression is fitted on the log-prices, the standard deviation of the residuals is computed, and the resulting deviation bands are exponentiated back to price space. The math is standard — what makes it useful is applying it to a series that actually follows the underlying distribution it assumes. Why traders use it: each band represents a probabilistic boundary. When price sits between the regression base and the first deviation band, it is statistically inside its normal operating range — equilibrium. When price crosses into the second band, the move has crossed into directional territory. The third band marks the threshold beyond which most of the impulse has already happened — exhaustion. The fourth band marks the tail of the distribution — a Black Swan event in Taleb's sense — where less than 1% of candles reach under normal conditions. The dynamic VWAP overlay adds a second dimension: directional bias. While the regression bands tell you how stretched price is, the VWAP tells you whether the volume-weighted average favors buyers or sellers. Together they give a two-axis read on every bar: directional bias plus statistical zone. CLOUD INSTITUTIONAL BANDS FEATURES The indicator includes 6 main features: Log-Normal Regression Engine Fibonacci-Proportioned Deviation Bands Dynamic VWAP with Glow Rainbow Zone Fills Zone Info Panel (HUD) Black Swan Alerts Multilingual interface and full customization across all visual layers. LOG-NORMAL REGRESSION ENGINE 🔹 What It Does The core of the indicator. Every bar, the engine performs four operations: ◇ Transforms the price series (hlc3) into log space via the natural logarithm. ◇ Fits a linear regression through the log-prices over the configured lookback window. ◇ Computes the standard deviation of the residuals — the gap between actual log-price and the regression line. ◇ Exponentiates the regression line and the deviation bands back to price space. The result is a statistical baseline (the Base Line) and four pairs of deviation bands that respect the asymmetric nature of price distribution. 🔹 Method The regression base is calculated using a standard linear regression on the log-price series. This is the classic least-squares fit — every bar in the lookback window contributes equally. The result is a baseline that represents where the market would be statistically if it were tracking its own trend perfectly. 🔹 Period The Band Period input sets the rolling lookback window for both the regression and the standard deviation calculation. Larger values produce smoother, wider bands that respond slowly to new price action. Smaller values produce tighter, more reactive bands that follow recent volatility more closely. The default is 200 bars, calibrated for the 223-minute Bitcoin chart. For other instruments and timeframes, the period should be adjusted to match the natural cycle length of the asset. FIBONACCI-PROPORTIONED DEVIATION BANDS 🔹 The Four Sigma Multipliers Instead of plotting bands at integer multiples of the standard deviation (1σ, 2σ, 3σ), this indicator uses Fibonacci-inspired proportions: ◇ ±1.50σ — Breathing Zone (yellow above, green below) ◇ ±1.85σ — Alert Zone (orange above, teal below) ◇ ±2.75σ — Exhaustion Zone (red above, blue below) ◇ ±3.85σ — Black Swan Zone (purple above, aqua below) Each multiplier corresponds to a different probabilistic regime: ◇ Breathing Zone: equilibrium. Most candles operate inside this range. Low conviction, no signal. ◇ Alert Zone: directional move in progress. Trend is asserting itself. Watch for follow-through. ◇ Exhaustion Zone: most of the impulse has already happened. Pullback probability rising. New entries in trend direction have unfavorable risk-reward. ◇ Black Swan Zone: statistical extreme. Less than 1% of candles reach this band under normal market conditions. Elevated probability of either mean reversion or volatility regime change. snapshot DYNAMIC VWAP WITH GLOW 🔹 What It Does A Volume-Weighted Moving Average is plotted alongside the regression bands, using the same lookback window. The VWAP renders in teal when price trades above it (bullish bias) and in red when price trades below (bearish bias). 🔹 Glow Effect The VWAP line carries a proximity-based glow: the closer price gets to the VWAP, the more intense the glow becomes. This visual cue prepares the eye for proximity to a high-liquidity zone, where reactions often occur. 🔹 Why It Matters The regression bands tell you how stretched price is. The VWAP tells you what bias the volume-weighted average favors. Together they give a complete read on every bar: ◇ Price above VWAP and inside Breathing Zone: healthy uptrend. ◇ Price above VWAP and at +2.75σ: uptrend in exhaustion. ◇ Price below VWAP and at -3.85σ: capitulation or imminent reversal. RAINBOW ZONE FILLS 🔹 What They Show The space between adjacent deviation bands is filled with a semi-transparent color matching the zone palette. This makes the current zone immediately visible without having to read the Z-Score number — the chart background tells you the regime at a glance. 🔹 Toggleable Fills can be turned off for traders who prefer to see only the band lines themselves. The lines alone (with the Base Line and VWAP) still provide all the information; the fills are a visual aid to make zone identification faster. ZONE INFO PANEL (HUD) 🔹 What It Shows A compact corner panel reports three live values: ◇ ZONE — the name of the currently active zone (e.g., "ALERT — HIGH RISK ZONE", "EQUILIBRIUM — BASE LINE") ◇ DEV. — the current Z-Score, expressed in standard deviations (e.g., "+2.44σ") ◇ VWAP — the current position relative to the dynamic VWAP ("VWAP: BUY ZONE" or "VWAP: SELL ZONE") 🔹 Why It Helps The HUD removes the need to interpret colors and band positions visually. It tells you in plain language where price is, how stretched it is, and which direction the volume-weighted bias is leaning. Useful for live trading where decisions need to happen quickly. 🔹 Customization The HUD can be positioned in any of the four chart corners and rendered in any of five font sizes. The display language is controlled by the System Language input. snapshot BLACK SWAN ALERTS 🔹 What Triggers The indicator fires an alert when price touches the ±3.85σ band — the Black Swan zone. Two separate alerts are available: one for the upper extreme (potential capitulation top), one for the lower extreme (potential capitulation bottom). 🔹 How They Fire Alerts are gated by barstate.isconfirmed, which means they only trigger on the close of the bar that touched the band — not intra-bar. This prevents false signals from wicks that get rejected before the bar closes. 🔹 Frequency Each alert uses alert.freq_once_per_bar, ensuring no duplicate firings on the same candle. MULTILINGUAL INTERFACE The indicator supports five languages for the HUD display and alert messages: English (default), Português, Español, Русский, and 中文 (Chinese). Code, comments, and configuration tooltips remain in English regardless of the selected language. For reference, the English text of all multilingual UI strings used in the HUD and alerts: ◇ BLACK SWAN — EXTREME HIGH / BLACK SWAN — EXTREME LOW ◇ BUYING EXHAUSTION / SELLING EXHAUSTION ◇ ALERT — HIGH RISK ZONE / ALERT — LOW RISK ZONE ◇ INSTITUTIONAL BREATHING ZONE ◇ EQUILIBRIUM — BASE LINE ◇ VWAP: BUY ZONE / VWAP: SELL ZONE ◇ ZONE: / DEV.: / VWAP: ◇ Black Swan Alert High: "Price at 4th standard deviation — EXTREME HIGH. High probability of severe reversal." ◇ Black Swan Alert Low: "Price at 4th standard deviation — EXTREME LOW. High probability of explosive reversal." HOW TO USE This indicator is not a signal generator. It is a state classifier: it tells you which statistical zone the current price is in, and how that zone relates to the volume-weighted bias. 🔹 Reading the Chart ◇ Identify the current Z-Score from the Zone Info Panel. ◇ Note the active zone color in the panel and on the chart fills. ◇ Combine with VWAP position for directional context. 🔹 Tactical Reading ◇ Z-Score between -1.50 and +1.50: market is in equilibrium. Mean-reversion strategies have higher edge than breakout strategies. ◇ Z-Score crossing ±1.85: breakout in progress. Trend-following entries have higher edge than fade entries. ◇ Z-Score at ±2.75: trend is mature. Trailing stops should be tightened. New entries in trend direction have unfavorable risk-reward. ◇ Z-Score touching ±3.85: Black Swan touch. Statistically the tail. Mean reversion has elevated probability — but Black Swans can also indicate regime change, where volatility expands and a new range opens. Use the Black Swan Alert to catch these events. 🔹 Multi-Timeframe Reading ◇ On lower timeframes (1m, 5m, 15m), the bands react to micro-trends and serve as dynamic support and resistance. ◇ On higher timeframes (1h, 4h, daily), the bands map macro regime — the outer bands at higher timeframes represent multi-day exhaustion zones. INPUTS EXPLAINED 🔹 System Language Display language for the HUD and alert messages. Options: English (default), Português, Español, Русский, 中文 (Chinese). 🔹 Band Period (bars) Rolling lookback for the Log-Normal regression and the VWAP. Range 50–500, default 200. Higher values produce smoother, wider bands; lower values produce tighter, more reactive bands. 🔹 Show Thermal Zone Fills Toggle for the semi-transparent rainbow fills between adjacent bands. 🔹 Show Black Swan Glow (4th Std Dev) Toggle for the glow effect on the outermost ±3.85σ bands. The glow intensifies as price approaches the band. 🔹 Show Base Line (Gravitational Center) Toggle for the regression central line — the statistical baseline around which the bands are computed. 🔹 Show Dynamic VWAP (Macro) Toggle for the volume-weighted reference line with proximity glow. 🔹 Show Zone Info Panel Toggle for the corner HUD reporting current zone, Z-Score, and VWAP position. 🔹 Panel Position Position of the HUD on the chart. Four corners available: Top Right (default), Top Left, Bottom Right, Bottom Left. 🔹 Font Size HUD font size. Options: Tiny (default), Small, Normal, Large, Huge. 🔹 Black Swan Alert (4th Std Dev touch) Toggle for the alerts that fire when price touches the ±3.85σ band. Two alerts: one for the upper extreme, one for the lower extreme. IMPORTANT NOTES The Cloud Institutional Bands works on any timeframe. The Band Period default of 200 is calibrated for the 223-minute chart and may need adjustment for other timeframes — a good rule of thumb is to set the period to approximately one full daily cycle for the chart timeframe (e.g., 288 bars for 5-minute charts, 96 bars for 15-minute charts). The indicator works best on instruments with reliable volume data: crypto perpetual contracts, large-cap equities, major forex pairs. On low-volume instruments, the dynamic VWAP component becomes less reliable, though the regression bands continue to function correctly. Alerts fire once per confirmed bar. Historical bars never repaint after they close. The live bar updates intra-bar as expected for a real-time indicator. The four sigma multipliers (1.50, 1.85, 2.75, 3.85) are intentionally non-standard. They are Fibonacci-inspired proportions, not arbitrary choices, and they map to four behavioral regimes derived from observation rather than to integer statistical thresholds. Pine Script v6. Open-source under Mozilla Public License 2.0. UNIQUENESS The Cloud Institutional Bands is unique in three ways. First, it performs the regression in log space, addressing the asymmetric nature of price distribution that linear estimators (such as the Simple Moving Average used by Bollinger Bands) fail to account for. This produces bands that behave correctly during volatility expansion phases, where standard envelopes show systematic bias. Second, it uses Fibonacci-proportioned sigma multipliers (1.50, 1.85, 2.75, 3.85) instead of integer steps, mapping the bands to four behavioral regimes — breathing, alert, exhaustion, and Black Swan — that correspond to observable phases of institutional order flow rather than to arbitrary thresholds. Third, it integrates a dynamic VWAP overlay with proximity-based glow alongside the regression bands, giving traders a two-axis read on every bar: how stretched price is statistically, and which direction the volume-weighted bias favors. The combination of log-space regression, Fibonacci sigma calibration, and integrated VWAP context produces a statistical envelope that behaves differently from standard band-based indicators, particularly at trend climaxes and capitulation events where standard envelopes are least reliable.
Pine Script® Indikator
von rainbowmatrix
AetherEdge Neural Order Block Evolution🖊️ Overview AetherEdge Neural Order Block Evolution is a next-generation ICT/SMT tool that auto-detects institutional order blocks (OBs) and isolates only "elite OBs" through neural-network-style weighted scoring. Four core features — volume anomaly, liquidity sweeps, MTF consensus, and displacement — are aggregated via sigmoid activation, ruthlessly eliminating noise OBs and rendering only the true zones defended by smart money. This is the ultimate order block engine that visualizes institutional footprints with AI precision. 🔶 Key Features Swing Pivot Detection: High-precision displacement-based OB identification Neural Quality Score: 4-feature × weighted × sigmoid aggregation Volume Anomaly Detection: Z-score-based abnormal volume scoring Liquidity Score: Cluster detection + liquidity sweep recognition MTF Consensus System: 3-timeframe trend bias integration Displacement Score: ATR-based impulse strength evaluation Elite OB Highlighting: Top-scored OBs marked with gold border Lifecycle Management: Mitigated OBs preserved as history Proximity Highlighting: Visual emphasis when price approaches OB Stats Panel: Tracks created / broken / respected counts 🧠 Technical Architecture This indicator is a neural evaluation engine designed to "decode institutional intent." OB Detection: After swingLen pivot detection, scans within obLookback for the Last Up/Down Candle. Only candidates with displacement ≥ displaceMult × ATR qualify as OBs. Volume Anomaly Score: Volume at OB formation Z-scored against 20-bar mean/std, then sigmoid-normalized to 0–1. Abnormal volume = institutional footprint. Liquidity Score: Counts price clusters near OB level over 30 bars (liquidity pool detection) + identifies liquidity sweep patterns (e.g., sharp reversal after low sweep). MTF Consensus: Retrieves close > EMA21 bias from mtf1/mtf2/mtf3. Aggregated with weights 1.0/1.2/1.5 (higher TF prioritized) and sigmoid-converted. Displacement Score: Displacement size normalized by ATR, excess over displaceMult threshold sigmoid-mapped. Neural Aggregation: Linear combination of 4 scores via wVolume / wLiquidity / wMTF / wDisplace yields final quality score. OBs below qualityMin are excluded. Lifecycle: Break detected via mitigationMode (Wick / Close) and breakBuf × ATR. With keepBroken, OBs migrate to historyOBs and persist for historyBars. Stats Tracking: totalCreated / Broken / Respects metrics for performance visualization. ⚙️ Recommended Settings & Tuning Guide Crypto Defaults: BTC (4H): swingLen=5, displaceMult=1.5, qualityMin=0.55, MTF=4H/D/W ETH (1H): swingLen=4, displaceMult=1.3, qualityMin=0.50, MTF=1H/4H/D SOL/XRP (15M): swingLen=3, displaceMult=1.2, qualityMin=0.45, MTF=15M/1H/4H Long-Term (1D): swingLen=8, displaceMult=2.0, qualityMin=0.60, MTF=D/W/M Weight Tuning: Trending markets: Raise wMTF=0.40, wDisplace=0.30 Range markets: Raise wLiquidity=0.40, wVolume=0.35 Elite-only display: qualityMin=0.70 + maxBlocks=4 Maximum visibility: qualityMin=0.40 + maxBlocks=12 Early detection: obLookback=20 for wider search Strict mode: displaceMult=2.0 for only powerful displacements 💡 How to Use in Practice Elite OB Reversal: Gold-bordered OBs are top-priority entry zones MTF Consensus Play: High sMTF OBs align with the macro-trend fortress Post-Sweep OB: High sLiq OBs form after institutional stop hunts — extremely strong zones Mitigation Strategy: Trade the first touch of an unmitigated OB History OB Analysis: Broken historic OBs are future support/resistance flip candidates AetherEdge Combinations: When KNN Breakout Fortress strong walls overlap an OB → ironclad zone ⚠️ Important Notes Too-small swingLen creates excessive, noisy OBs MTF settings must be higher than the current chart timeframe Liquidity score depends on the prior 30 bars — accuracy drops on early bars sVol becomes unreliable on assets without volume data Neural weights should sum to approximately 1.0 for balanced scoring 🚨 Disclaimer This indicator is provided for educational and research purposes only and does not constitute financial advice. Neural scores and OB quality evaluations are based on historical data and do not guarantee future performance. All trading decisions are made at your own risk and should be accompanied by proper risk management.
Pine Script® Indikator
von AetherEdge
AetherEdge RL Signal Optimizer🖊️ Overview AetherEdge RL Signal Optimizer is a truly self-optimizing signal engine powered by a complete Q-Learning (TD-learning) implementation. It discretizes the market into 18 states, explores Long/Short/Skip actions through trial-and-error, updates Q-values via the Bellman equation, and dynamically balances exploration vs exploitation through ε-greedy decay. Combined with statistical TP/SL learning from MFE/MAE tracking, it is a living reinforcement-learning system where both policy and risk-management evolve with every trade. 🔶 Key Features Full Q-Learning Implementation (TD(0)): 18 states × 3 actions Q-table ε-Greedy Exploration: Auto-decay from 30% → 5%, solving the exploration/exploitation dilemma State Discretization: Trend(3) × RSI(3) × Volatility(2) = 18 states Reward Function: n-step ATR-normalized return + skip penalty MFE/MAE Learning: Statistical TP/SL estimation from up to 200 trades Dynamic TP/SL: Quantile-based optimal levels (TP=70%, SL=85% confidence) Q-Spread Confidence: Best vs second-best Q gap as conviction proxy Q-Table Heatmap: All 18 states visualized with color-graded Q-values Learning Progress Bar: EXPLORING → MIXING → EXPLOITING phases Performance Tracking: Win rate, avg reward, recent 50-reward MA Current-State Highlight: On-chart directional box 🧠 Technical Architecture This indicator is a complete reinforcement-learning agent running natively on TradingView. State Space (18 states): Trend Index: EMA20-50 spread (Bear/Flat/Bull) RSI Index: Low/Mid/High Volatility Index: ATR short/long ratio (Low/High) Combined: state = trend×6 + rsi×2 + vol Action Space (3 actions): 0=Long, 1=Short, 2=Skip Q-Update (Bellman Equation): Q(s,a) ← Q(s,a) + α × Reward Function: Long → r = (close - close ) / ATR Short → r = -(close - close ) / ATR Skip → r = skipPenalty (-0.05) ε-Greedy Policy: With probability ε: random exploration; else greedy Linear decay: epsStart → epsEnd over epsDecayLen Pseudo-random: sin(seed×12.9898 + 78.233) for reproducibility TP/SL Learning Engine: Track MFE/MAE for trackBars after each signal Separate Long/Short buffers, max 200 trades each TP = 70th percentile of MFE; SL = 85th percentile of MAE Safe defaults when data insufficient (TP=2.0×, SL=1.5×ATR) Q-Spread Confidence: Signal fires only if best - second_best ≥ minConfidence State Coverage Tracking: Percentage of (state, action) cells visited ⚙️ Recommended Settings & Tuning Guide Crypto Defaults: BTC (4H): α=0.15, γ=0.90, epsDecay=500 (standard) ETH (1H): α=0.20, γ=0.85, epsDecay=300 (fast-learn) SOL (high-vol): α=0.10, γ=0.92, epsDecay=800 (careful) XRP (short-term): α=0.25, epsDecay=200, rewardLook=2 Q-Learning Hyperparameters: α (Learning Rate): 0.05–0.10: conservative, noise-resilient 0.15: standard 0.25–0.40: fast adaptation, unstable risk γ (Discount): 0.80: short-term view, immediate reward 0.90: standard 0.95–0.99: long-term strategy, delayed reward ε Decay: 200: rapid learning, low data 500: standard 1000+: thorough exploration, HTF use TP/SL Optimization: tpConfidence=0.5: conservative TP (early profit) tpConfidence=0.7: standard tpConfidence=0.9: greedy TP (miss risk) slConfidence=0.85: standard (tolerate 85% drawdowns) Min Q-Spread: 0.05: many signals, noise included 0.15: standard 0.30: ultra-curated, fewer opportunities 💡 How to Use in Practice EXPLOITING phase (ε≤0.08): Maximum signal trust, live trading EXPLORING phase (ε>0.20): Learning, signals are reference only MIXING phase: Transitional, observe carefully CONFIDENT + LONG/SHORT: Sufficient Q-spread, entry candidate UNCERTAIN: Ambiguous state, skip recommended Q-Table Observation: All-green rows: bullish bias learned High Visits = high cell reliability "—" displayed: unvisited cells, insufficient data Trade Scenarios: Bull · RSI↓ · LoVol with max Q : Pullback-buy pattern learned Bear · RSI↑ · HiVol with max Q : Bounce-sell pattern learned Learned TP/SL with 1:2.5 R:R: Trade only after statistical edge confirmed AetherEdge Synergy: SMC AI Confidence Engine: A+ zone + RL Long = double rationale NeuraNet Predictor: Direction match + RL CONFIDENT = high probability Self-Evolving S/R Grid: Strong line touch + RL signal = supreme alignment All-in-One Dashboard: HIGH-CONVICTION + RL EXPLOITING = ultimate confluence ⚠️ Important Notes Learning Reset Issue: Q-table resets on chart reload or timeframe change—relearning required Initial Learning Period: Run at least epsDecayLen × 1.5 bars before live use State Coverage: <50% means many unvisited states; 80%+ recommended for stability Overfitting Risk: High α over-fits to recent noise; HTF requires lower α MFE/MAE Buffer: At least 20+ trades needed for reliable TP/SL Pseudo-Random: bar_index-based, so same moment yields same exploration Signal Latency: Operates on barstate.isconfirmed; signals confirm after bar close 🚨 Disclaimer This indicator is a reinforcement-learning demonstration for educational and research purposes only and does not constitute financial advice. Q-Learning is a stochastic optimization method and does not guarantee future profits. Learning outcomes depend strongly on environment and data; past performance does not predict future results. Use with thorough validation and proper risk management.
Pine Script® Indikator
von AetherEdge
Roll Spread Estimator [forexobroker]Roll Spread Estimator implements Roll (1984) — the bid-ask bounce induces negative serial covariance in observed returns. Spread = 2 * sqrt(-cov(r , r )) when cov is negative. Tight spread = liquid market = clean breakouts; wide spread = thin = breakouts to fade. Signals fire on EMA cross during a tight regime. Stacked-flag visual signature distinct from any other hero indicator. 🔶 ALGORITHM 1. r0 = close - close ; r1 = close - close . 2. cov(r0, r1) = sma(r0 * r1, N) - sma(r0, N) * sma(r1, N). 3. Spread = 2 * sqrt(-cov) when cov < 0; otherwise 0. 4. Quantile q (e.g., 70th percentile) over rolling window. 5. Tight regime when spread <= q. 6. EMA cross within tight fires entries. 🔶 SIGNAL LOGIC - Buy: tight AND close crosses EMA up AND not already long AND cooldown elapsed AND barstate.isconfirmed. - Sell: tight AND close crosses EMA down. - Position-lock state machine. 🔶 INPUTS - Cov Window (default 40) - Tight Spread Quantile (default 0.7) - Pullback EMA Length (default 8) - Cooldown Bars (default 4) - Visual: dashboard, glow (3 stacked flags), spread channel, buy / sell colors 🔶 ALERTS RSE Buy, RSE Sell, RSE Any Signal, RSE Tight Start, RSE Tight End, RSE Bounce, RSE EMA Up, RSE EMA Down, RSE Webhook JSON. 🔶 LIMITATIONS - Roll's estimator assumes the bid-ask bounce is the dominant source of negative covariance; trend-following autocorrelation can produce positive cov, in which case the estimator is undefined and returns 0. - Forex and equities show clear bid-ask bounces; pure spot-market crypto is less consistent. - The stacked-flag visual uses 3 overlapping flags for a thicker appearance — visually distinct but slightly heavier draw. - Quantile-based threshold means tight is *relative* to recent history, not absolute.
Pine Script® Indikator
von forexobroker