AI SuperTrend [PickMyTrade]THE PROBLEM WITH A FIXED MULTIPLIER
Every standard SuperTrend applies the same ATR multiplier across all market conditions — the same constant during a strong trending breakout, a narrow choppy range, and a volatility spike. A value calibrated for one regime is miscalibrated for the others. Most traders compensate by manually switching timeframes or parameters. This script automates that decision.
The question it asks: what if the ATR multiplier were selected from historical bars that most resembled the current market regime — matched by Hurst state and volatility rank — rather than set by the user as a fixed constant?
────────────────────────────────────────
THREE AI LAYERS
Layer 1 — Hurst Exponent (Regime Gate)
The Hurst Exponent is computed via Rescaled Range (R/S) Analysis. It measures the degree of long-range dependence (memory) in the price series:
H ≥ 0.55 → Persistent (trending) — SuperTrend active, signals enabled
H ≈ 0.50 → Random walk — candles turn gray, no signal generated
H ≤ 0.45 → Anti-persistent (mean-reverting) — signals suppressed
The Hurst gate is the first filter. Signals only fire when market structure is historically associated with persistence — not randomness or mean-reversion.
Layer 2 — Garman-Klass Volatility Rank
Garman-Klass (1980) estimates realized volatility from OHLC prices rather than close-to-close returns, capturing intrabar price range and making it more sensitive to volatility changes. The current reading is percentile-ranked against recent history (0–100%) and used as the second feature dimension for the KNN search.
Layer 3 — KNN Multiplier Optimizer
K-Nearest Neighbors searches a rolling memory bank of feature pairs from previous bars. For each current bar it finds the K most similar historical bars by Euclidean distance in that 2D feature space. From those neighbors it retrieves the ATR multipliers that were in effect — weighted by the profitability of the bar that followed. The result is the AI Multiplier: a context-aware value drawn from the most similar past conditions, not a fixed constant.
────────────────────────────────────────
WHAT YOU SEE ON THE CHART
Candle color — the defining visual. Orange = bull trend regime, blue = bear trend regime, gray = random walk or mean-reverting. The regime state is readable on every bar without checking the table.
Signals — ● (circle) marks trend flips with Hurst ≥ 0.65, the high-conviction threshold. ▲▼ (triangle) marks standard threshold crossings. No signal fires in gray (random or mean-reverting) regimes.
SL / TP lines — dashed lines drawn automatically at each signal bar, sized from current ATR × the AI Multiplier active at that bar.
Info table (top right) — live display of Hurst value, Regime label, Direction, AI Multiplier, Vol Rank, and KNN memory bar count. Shows WARMUP until KNN has stored enough bars to begin optimizing.
────────────────────────────────────────
HOW TO USE
A signal requires all three conditions to be true simultaneously:
KNN is warmed up (table shows ● LIVE)
Hurst confirms a trending regime (H ≥ Trend Threshold input)
Price is on the correct side of the EMA filter
Circle signals (●) indicate Hurst has exceeded 0.65 — stronger persistence than the standard threshold. Triangle signals (▲▼) are at the user-defined threshold. Gray candles indicate the market is not in a trending regime; reducing exposure or standing aside is appropriate during those periods.
The regime background shading (faint orange or blue fill) shows when the SuperTrend is in an active directional state.
────────────────────────────────────────
INPUTS
AI Engine — Hurst Lookback, KNN Neighbors (K), KNN Memory (bars), Trend Threshold, Mean-Revert Threshold
SuperTrend — ATR Length, Base Multiplier, Volatility Window, EMA Period
Visual — Bull/Bear colors, SL/TP lines toggle, SL ATR Multiplier, Risk:Reward ratio, Regime Background
Display — Zen Mode (hides labels and table), Show Info Table
ALERTS
Three alert conditions: Long Signal, Short Signal, Any Signal.
────────────────────────────────────────
NOTES
KNN requires warmup equal to the KNN Memory setting before the AI Multiplier activates. During warmup the base multiplier scaled by Hurst and volatility rank is used instead.
No repainting. All signals are confirmed on bar close. KNN stores lagged values only.
Garman-Klass citation: Garman, M. & Klass, M. (1980). On the Estimation of Security Price Volatilities from Historical Data. Journal of Business , 53(1), 67–78.
指标
Hurst Exponent Strategy [Fast + Weekly]## Overview
The **Hurst Exponent Strategy ** is an advanced quantitative tool that calculates the Hurst Exponent ($H$) using the Rescaled Range ($R/S$) analysis. Instead of tracking directional momentum or price overlays, this indicator measures the **statistical memory** and fractal dimension of financial time series to detect market regimes.
It helps traders identify whether an asset is trending, mean-reverting, or trapped in a state of pure noise (chaos).
---
## The Mathematics of Market Regimes
The indicator evaluates the price action and plots values between 0 and 1, anchored to a theoretical center line of **0.5 (Random Walk)**:
- **$H > 0.60$ (Trend / Persistent):** The market possesses long-term memory. Price movements tend to be followed by movements in the same direction. Ideal for trend-following strategies.
- **$H < 0.45$ (Elastic / Anti-Persistent):** The market behaves like a rubber band (Mean Reversion). Price movements are consistently followed by reversals. Ideal for grid, mean-reversion, or range-bound strategies.
- **$0.45 \le H \le 0.60$ (Chaos / Random Walk):** The price action mimics a Brownian motion. Movements are random, noise is high, and directional edge is minimal.
---
## Dual Timeframe Framework
To avoid fighting macro market structures, this script calculates two separate Hurst metrics simultaneously:
1. **Fast Hurst (Cyan Line):** Calculated on the current chart timeframe. It responds quickly to micro-regime shifts, pinpointing when a consolidation is breaking into a trend or expanding into chaos.
2. **Macro Hurst (Orange Line):** Multi-timeframe execution locked exclusively to the **Weekly ("W") chart**. It acts as a structural filter, keeping you aligned with the true macro nature of the asset.
Both exponents feature an optional built-in **Smoothing filter (SMA)** to remove high-frequency mathematical noise without heavily lagging the structural reading.
---
## Real-Time Informative Legend
The top-right dashboard monitors the live mathematical output of both exponents:
- Displays exact numerical values down to 4 decimal places.
- Dynamically classifies the market state into **TREND** (Green), **ELASTICO** (Red), or **CAOS** (Gray) for instant visual confirmation.
---
Disclaimer: This tool calculates mathematical probabilities based on historical fractal dimensions. It does not provide entry/exit arrows or guarantee profits. Use it as a regime filter alongside your preferred execution strategy. 指标
Statistical Mean-Reversion Engine [SMRE]## Statistical Mean-Reversion Engine (SMRE)
SMRE is an open-source mean-reversion indicator that combines a rigorous statistical core with up to eight optional confirmation layers, designed primarily for index-futures trading on intraday timeframes (1-minute through 1-hour).
### What it does
For every bar, SMRE fits an Ornstein-Uhlenbeck (OU) process to the recent price series via linear regression on lag-1 prices, yielding four outputs:
- **μ (the mean)** — the equilibrium price the series is reverting to
- **θ (mean-reversion speed)** — how strongly the series pulls back to μ
- **HL (half-life)** — how many bars it takes to revert halfway
- **σ_eq (stationary residual variance)** — used to z-score the current price
The current price's z-score against μ (the "OU Z") is the primary signal. When |OU Z| exceeds a configurable threshold, a mean-reversion entry is considered — but only after the script also confirms that the recent price series is genuinely stationary using three orthogonal statistical tests:
- **Hurst exponent** must be below 0.55 (i.e., the series is not persistently trending)
- **Augmented Dickey-Fuller** t-statistic must be below -2.86 (rejects unit root)
- **Variance Ratio** test at q=4 must be below 1.0 (variance grows sub-linearly with horizon)
If all four conditions pass, the L1 (statistical core) signal fires.
### Why the multi-layer structure (mashup justification)
A single OU-based mean-reversion signal works well in stationary regimes but degrades in trending or volatile conditions. SMRE addresses this by validating each potential entry through up to eight orthogonal confirmation channels, each measuring something the others do not:
- **L2 — Volatility Regime (6-state):** Classifies market state via VIX, ADX, and realized volatility. Suppresses signals during high-trend conditions (regime 6, "Spike") where mean-reversion historically fails.
- **L3 — Spot-Futures Basis (Kalman filter):** Tracks the deviation between actual and theoretical futures pricing. Statistically significant basis dislocations often resolve via mean-reversion.
- **L4 — Options Surface:** Computes ATM implied volatility from straddle pricing and a skew z-score from OTM put/call ratio. Optional; requires user to provide option symbols.
- **L5 — Microstructure:** Blends rolling VWAP and session-anchored VWAP z-scores with VPIN (a volume-clock toxicity proxy) and order-flow imbalance. Captures flow-based exhaustion.
- **L6 — Gamma Walls (GEX) OR Put-Call Ratio:** Two mutually exclusive options. GEX requires OI symbols at five strikes; PCR requires a single broker-published PCR feed. Both detect option-driven price magnets.
- **L7 — Dispersion:** Rolling correlation of index returns with its top 5 constituent stocks' returns. High dispersion (low correlation) penalizes signals; high cohesion boosts them.
- **L7b — Residual Dispersion:** Idiosyncratic residual z-scores (β-adjusted) per constituent. If 3 of 5 stocks show same-sign extreme residuals, the index is detached from constituents — strong mean-reversion candidate.
- **L9 — Cross-Asset Stress:** Sigma-normalized stress across USD/INR, DXY, and crude oil. Penalizes signals during cross-asset hedging cascades.
Each layer outputs a {direction, strength} pair. The Layer 8 fusion engine combines these via a weighted composite score (default weights: L1=0.28, L5=0.22, L3=0.18, L4=0.12, L6/L7b=0.10), then applies a regime multiplier (L2 × L7 × VRP × cross-asset × expiry), clamped to to prevent extreme compounding.
If the absolute composite score crosses one of three thresholds (0.25 / 0.40 / 0.45 by default), a signal is fired at Scalp / Swing / Session horizon respectively. A TCA cost filter then validates that the expected move (distance to μ) exceeds estimated round-trip transaction cost; otherwise the signal is suppressed.
### Originality
The author is not aware of any other public Pine script that implements the full OU-fit chain (mean, mean-reversion speed, half-life, stationary variance) together with all three stationarity tests (Hurst, ADF, Variance Ratio) directly in Pine v6 — every step is computed natively, no external library calls. Additionally, the session-anchored VWAP with running volume-weighted sigma bands, the rolling-beta residual dispersion across multiple constituents, and the Kalman-filtered futures-basis residual are original Pine implementations. The signal telemetry module (a 200-signal FIFO ring buffer with horizon × composite-magnitude bucket attribution) is also an original diagnostic tool.
### How to use
1. **Apply to an index futures chart.** Defaults are pre-configured for NSE NIFTY1! futures, but inputs allow any index — change the VIX symbol, spot/futures symbols, constituent symbols, and currency pairs.
2. **Read the compact dashboard.** It's a single 9-row table (default position: middle-right) showing only what you need to evaluate a setup:
| Row | What it shows | What it means |
|---|---|---|
| Title | Profile + OU window in use | Confirms which calibration is active |
| OU Z-Score | Z-score with half-life (HL) | How extended price is + how long mean-reversion typically takes |
| Stat Validity | H / ADF / VR pass-fail | Whether the recent series is actually stationary (all 3 must pass) |
| Regime | Volatility state + VIX value | Whether market conditions favor mean-reversion |
| Composite | Fused score × regime multiplier | The unified signal strength |
| Confluence | Layers agreeing (out of 6) | How many orthogonal signals support the direction |
| TCA Edge | Expected move in bps + PASS/FAIL | Whether the trade clears transaction costs |
| E / SL / TP | Entry, Stop, Target + Risk:Reward | The trade levels if a signal fires |
| **DECISION** | Direction · Horizon · Side | The actionable output (green=long, red=short, gray=neutral) |
3. **Trade levels and markers.** When a signal fires, entry/stop/target lines auto-plot on the chart. Stop is ATR-based (default 1.2× ATR); target is min(OU mean μ, entry + 2× ATR). Triangle markers plot below (long) or above (short) the bar — small for Scalp, medium for Swing, large for Session.
4. **Optional diagnostic.** A separate Signal Telemetry table (disabled by default; enable via the "Show Telemetry Dashboard" input) tracks the last 200 signals' outcomes (win = price touched μ, loss = stop hit, expired = timeout) and reports hit rate by horizon × composite-magnitude bucket. This is a backward-looking diagnostic, not a backtest.
### Recommended chart and timeframe
This indicator was developed and parameter-tested primarily on NIFTY1! futures. The OU window auto-mapping (1m→32, 2m→20, 5m→12, 15m→32, 30m→20, 1h→24) was selected empirically through parameter sweeps. Users on other instruments should expect to tune the OU window manually or accept the auto-mapped default as a starting point.
The indicator works on any timeframe between 1 minute and daily, though intraday timeframes (1m through 1h) are where the multi-layer confluence adds the most value.
### Important notes
- This is an **indicator**, not a strategy — no backtest equity curve is produced. The telemetry table is a descriptive measure of recent signal outcomes only.
- Many layers are **optional**. If you don't have symbols for options OI, just leave those inputs blank; the script will redistribute composite weight naturally across the active layers.
- Signals can fluctuate intra-bar before bar close, especially in real-time mode. For consistent behavior, evaluate signals on closed bars only.
- The default constituents (top-5 NIFTY weights) need to be changed in the L7 inputs to use this on a different index.
### Disclaimer
This indicator is published for educational and research purposes only. It is not financial advice, not an investment recommendation, and not a solicitation to trade. Past behavior of signals does not guarantee future results. Trading futures, options, and equities carries substantial risk of loss. You are solely responsible for your trading decisions. The author makes no representations about the accuracy, completeness, or suitability of this indicator for any particular purpose. Use at your own risk, and always consult a qualified financial professional before trading.
指标
Hurst Exponent Market Phases [DW]This study is an experiment designed to identify market phases using changes in an approximate Hurst Exponent.
The exponent in this script is approximated using a simplified Rescaled Range method.
First, deviations are calculated for the specified period, then the specified period divided by 2, 4, 8, and 16.
Next, sums are taken of the deviations of each period, and the difference between the maximum and minimum sum gives the widest spread.
The rescaled range is calculated by dividing the widest spread by the standard deviation of price over the specified period.
The Hurst Exponent is then approximated by dividing log(rescaled range) by log(n).
The theory is that a system is persistent when the Hurst Exponent value is above 0.5, and antipersistent when the value is below 0.5.
The color scheme indicates 4 different phases I found to be significant in this formula:
- Stabilization Phase
- Destabilization Phase
- Chaos Increase Phase
- Chaos Decrease Phase
This script includes two visualization types to choose from:
- Bar Counter Mode, which displays the number of bars the exponent is consecutively in each phase.
- Hurst Approximation Mode, which displays the approximated exponent value.
Custom bar colors are included.
Please note: This is a rough estimate of the Hurst Exponent. It is not the actual exponent. Numerous approximations exist, and their results all differ slightly.
指标
