OPEN-SOURCE SCRIPT
AetherEdge - STRUCTURA Adaptive Price-Action Intelligence
🖊️ Overview
STRUCTURA fuses the three pillars of price action — market structure, order blocks, and fair value gaps — with a self-learning AI layer. Built on a non-repainting foundation that reads structure only from confirmed swings, its online learning discovers from the market which zones actually work and attaches a probabilistic confidence to every reversal. Unlike conventional tools that merely draw price structure, STRUCTURA continuously updates its weights from experience — emphasizing what works, fading what doesn't — adapting to the market itself.
🔶 Key Features
Automatic market structure: real-time BOS (continuation) and CHoCH (reversal) detection from confirmed swings
Swing-point classification (HH/HL/LH/LL) for wave-structure visualization
Volumetric order blocks: the last opposite-color candle before a structure break, zoned with recorded volume
Mitigation tracking: detects when price returns into a zone and visually distinguishes consumed zones (Wick/Close methods)
Fair Value Gaps: detects 3-candle imbalances and tracks fills at the midpoint
[AI Layer 1] Adaptive zone reliability: online-learns each zone type's reaction success rate and emphasizes reliable types visually
[AI Layer 2] CHoCH confidence: an online logistic regression predicts each CHoCH's "hold probability," auto-dimming low-confidence signals
Refined red/green jewel-tone palettes (three options) with a gold-framed integrated HUD
Built-in BOS/CHoCH alert conditions
🧠 Technical Architecture
STRUCTURA's foundation is confirmed-swing detection. Swing highs and lows confirm with a few bars of lag, and in exchange gain non-repainting permanence — their positions never change once printed. From these confirmed swings, a market-structure state machine is driven. When price closes above the last swing high, it is judged a CHoCH (character change) if the prevailing trend was bearish, or a BOS (continuation) if bullish, with symmetric handling on the low side.
Order blocks are identified by scanning back to the last opposite-color candle before a structure break, capturing its high, low, and volume as a zone. Each zone tracks its own mitigation state, transitioning to a dotted style once price returns and consumes it. Fair value gaps are detected as 3-candle imbalances where the current low exceeds the high two bars prior (or the symmetric decline), extended rightward until price reaches the midpoint.
Two AI layers sit atop this. The first, adaptive zone reliability, observes whether price reacts off or breaks through a zone upon entry, updating each zone type's reaction success rate via an exponentially-weighted moving average. This learns which zone types actually function in the current market and quantifies it as reliability. The second, CHoCH confidence, is an online logistic regression taking standardized momentum, body strength, and volume as features. When a CHoCH fires it predicts whether the change will continue in the new direction, then labels the outcome after a set horizon and updates its weights via stochastic gradient descent. The learned probability is shown on each CHoCH label, and low-confidence reversals are automatically dimmed, visually separating fakeouts from genuine turns.
⚙️ Recommended Settings & Tuning Guide
STRUCTURA is tuned with crypto in mind. On majors like BTC and ETH, Swing Length near 10 balances structural granularity against lag. On higher-volatility names such as SOL and XRP, widening Swing Length to 12–15 suppresses noise structure and clarifies major BOS/CHoCH events.
Swing Length is the master sensitivity parameter — larger captures only major structure, smaller picks up short-term structure. For swing trading, 15–20 is a guide; for intraday, 8–12. In the AI layer, raising the Zone Learning Rate makes reliability track the current regime faster; lowering it stabilizes over the long run. The CHoCH Model Learning Rate and Outcome Horizon control the reversal probability's responsiveness and evaluation window. If order blocks or FVGs become too dense, adjust the Max display counts and Min Gap Size.
💡 How to Use in Practice
The highest-conviction setups are confluences where multiple elements align. For example, a bullish CHoCH flipping structure, with a high-reliability bullish order block beneath it and an unfilled FVG nearby, forms a strong long-consideration point. Checking the HUD's zone reliability and prioritizing the zone types actually working in the current market helps avoid overtrusting zones that don't function.
The CHoCH confidence % is a unique gauge of reversal reliability. High-confidence CHoCHs are strong evidence of a trend turn, while low-confidence ones (auto-dimmed) suggest patience. For multi-timeframe trading, pair a higher-timeframe STRUCTURA to read the macro structure and order blocks with a lower timeframe for precise entry timing. Overlaying order blocks and FVGs with volume profile and key horizontal levels further deepens the interpretation of where liquidity concentrates.
⚠️ Important Notes
Because this tool is based on confirmed swings, structure signals confirm with a few bars of lag in real time — a necessary property of an honest, non-repainting design. The AI layer requires accumulated data to learn, so near the chart's left edge or when CHoCH occurrences are few, reliability remains at its initial values (zones 50%, CHoCH accuracy 50%). Static HUD values are a sign that learning data is still insufficient. Whether CHoCH model accuracy stably exceeds 50% depends on the instrument, timeframe, and period, and cannot overcome the fundamental constraint of market predictability.
🚨 Disclaimer
This indicator is provided for educational and informational purposes only and does not constitute financial or investment advice. No signal guarantees future profit, and past performance does not indicate future results. All trading decisions are made at your own risk; please use this tool with sound risk management and your own independent verification.
STRUCTURA fuses the three pillars of price action — market structure, order blocks, and fair value gaps — with a self-learning AI layer. Built on a non-repainting foundation that reads structure only from confirmed swings, its online learning discovers from the market which zones actually work and attaches a probabilistic confidence to every reversal. Unlike conventional tools that merely draw price structure, STRUCTURA continuously updates its weights from experience — emphasizing what works, fading what doesn't — adapting to the market itself.
🔶 Key Features
Automatic market structure: real-time BOS (continuation) and CHoCH (reversal) detection from confirmed swings
Swing-point classification (HH/HL/LH/LL) for wave-structure visualization
Volumetric order blocks: the last opposite-color candle before a structure break, zoned with recorded volume
Mitigation tracking: detects when price returns into a zone and visually distinguishes consumed zones (Wick/Close methods)
Fair Value Gaps: detects 3-candle imbalances and tracks fills at the midpoint
[AI Layer 1] Adaptive zone reliability: online-learns each zone type's reaction success rate and emphasizes reliable types visually
[AI Layer 2] CHoCH confidence: an online logistic regression predicts each CHoCH's "hold probability," auto-dimming low-confidence signals
Refined red/green jewel-tone palettes (three options) with a gold-framed integrated HUD
Built-in BOS/CHoCH alert conditions
🧠 Technical Architecture
STRUCTURA's foundation is confirmed-swing detection. Swing highs and lows confirm with a few bars of lag, and in exchange gain non-repainting permanence — their positions never change once printed. From these confirmed swings, a market-structure state machine is driven. When price closes above the last swing high, it is judged a CHoCH (character change) if the prevailing trend was bearish, or a BOS (continuation) if bullish, with symmetric handling on the low side.
Order blocks are identified by scanning back to the last opposite-color candle before a structure break, capturing its high, low, and volume as a zone. Each zone tracks its own mitigation state, transitioning to a dotted style once price returns and consumes it. Fair value gaps are detected as 3-candle imbalances where the current low exceeds the high two bars prior (or the symmetric decline), extended rightward until price reaches the midpoint.
Two AI layers sit atop this. The first, adaptive zone reliability, observes whether price reacts off or breaks through a zone upon entry, updating each zone type's reaction success rate via an exponentially-weighted moving average. This learns which zone types actually function in the current market and quantifies it as reliability. The second, CHoCH confidence, is an online logistic regression taking standardized momentum, body strength, and volume as features. When a CHoCH fires it predicts whether the change will continue in the new direction, then labels the outcome after a set horizon and updates its weights via stochastic gradient descent. The learned probability is shown on each CHoCH label, and low-confidence reversals are automatically dimmed, visually separating fakeouts from genuine turns.
⚙️ Recommended Settings & Tuning Guide
STRUCTURA is tuned with crypto in mind. On majors like BTC and ETH, Swing Length near 10 balances structural granularity against lag. On higher-volatility names such as SOL and XRP, widening Swing Length to 12–15 suppresses noise structure and clarifies major BOS/CHoCH events.
Swing Length is the master sensitivity parameter — larger captures only major structure, smaller picks up short-term structure. For swing trading, 15–20 is a guide; for intraday, 8–12. In the AI layer, raising the Zone Learning Rate makes reliability track the current regime faster; lowering it stabilizes over the long run. The CHoCH Model Learning Rate and Outcome Horizon control the reversal probability's responsiveness and evaluation window. If order blocks or FVGs become too dense, adjust the Max display counts and Min Gap Size.
💡 How to Use in Practice
The highest-conviction setups are confluences where multiple elements align. For example, a bullish CHoCH flipping structure, with a high-reliability bullish order block beneath it and an unfilled FVG nearby, forms a strong long-consideration point. Checking the HUD's zone reliability and prioritizing the zone types actually working in the current market helps avoid overtrusting zones that don't function.
The CHoCH confidence % is a unique gauge of reversal reliability. High-confidence CHoCHs are strong evidence of a trend turn, while low-confidence ones (auto-dimmed) suggest patience. For multi-timeframe trading, pair a higher-timeframe STRUCTURA to read the macro structure and order blocks with a lower timeframe for precise entry timing. Overlaying order blocks and FVGs with volume profile and key horizontal levels further deepens the interpretation of where liquidity concentrates.
⚠️ Important Notes
Because this tool is based on confirmed swings, structure signals confirm with a few bars of lag in real time — a necessary property of an honest, non-repainting design. The AI layer requires accumulated data to learn, so near the chart's left edge or when CHoCH occurrences are few, reliability remains at its initial values (zones 50%, CHoCH accuracy 50%). Static HUD values are a sign that learning data is still insufficient. Whether CHoCH model accuracy stably exceeds 50% depends on the instrument, timeframe, and period, and cannot overcome the fundamental constraint of market predictability.
🚨 Disclaimer
This indicator is provided for educational and informational purposes only and does not constitute financial or investment advice. No signal guarantees future profit, and past performance does not indicate future results. All trading decisions are made at your own risk; please use this tool with sound risk management and your own independent verification.
Script de código abierto
Fiel al espíritu de TradingView, el creador de este script lo ha convertido en código abierto, para que los traders puedan revisar y verificar su funcionalidad. ¡Enhorabuena al autor! Aunque puede utilizarlo de forma gratuita, recuerde que cualquier republicación del código está sujeta a nuestras Normas internas.
Exención de responsabilidad
La información y las publicaciones no constituyen, ni deben considerarse como, asesoramiento o recomendaciones financieras, de inversión, de trading u otro tipo, proporcionadas o respaldadas por TradingView. Obtenga más información en Condiciones de uso.
Script de código abierto
Fiel al espíritu de TradingView, el creador de este script lo ha convertido en código abierto, para que los traders puedan revisar y verificar su funcionalidad. ¡Enhorabuena al autor! Aunque puede utilizarlo de forma gratuita, recuerde que cualquier republicación del código está sujeta a nuestras Normas internas.
Exención de responsabilidad
La información y las publicaciones no constituyen, ni deben considerarse como, asesoramiento o recomendaciones financieras, de inversión, de trading u otro tipo, proporcionadas o respaldadas por TradingView. Obtenga más información en Condiciones de uso.