OPEN-SOURCE SCRIPT
AetherEdge - Adaptive Anchored VWAP

🖊️ Overview
Anchored VWAP marks the volume-weighted cost basis from an event. AE-VWAP picks the anchor for you and learns whether reclaiming the VWAP actually means something. It auto-anchors at significant swings, conformally calibrates its volume-weighted σ-bands to a target containment, and learns the follow-through probability after price crosses the anchored VWAP.
🔶 Key Features
Auto-anchored VWAP — anchors at significant swings (Session / Manual also available)
Volume-weighted σ-bands — standard-deviation bands weighted by volume
Conformally calibrated bands — no normality assumption; band width k is set to hit a target containment
Learned reclaim edge — follow-through probability after a VWAP reclaim/loss (signal only when the odds back it)
Realized containment — shows how well the bands are calibrated
Reclaim signals + anchor markers + alerts; bar-close training — no repaint
🧠 Technical Architecture
VWAP: the source (hlc3/close/ohlc4) is volume-weighted: vwap = Σ(price·vol)/Σvol, σ = √(Σ vol·price²/Σvol − vwap²). Anchor modes: Auto (pivot confirmation) / Session (daily) / Manual (date).
Bands (conformal calibration): k is set to the (1−α) quantile of the standardized deviation |src−vwap|/σ, matching the target containment empirically. A fixed normal-assumption k tends to under-contain on fat tails — conformal fixes that.
ML (online logistic): at a VWAP reclaim (close × VWAP cross), six side-oriented features (momentum, trend alignment, RSI, σ-band-width regime, volume, anchor age) predict the follow-through probability = P(price continues tpK·ATR in the cross direction before recrossing, within N bars) via a triple barrier. No lookahead.
Honest scope: a volume-weighted mean + conformal calibration + a linear classifier (no RL). Not deep learning, not a guarantee.
⚙️ Recommended Settings & Tuning Guide (crypto 15m–4H)
Key parameters: anchor mode, pivot strength, band width k / conformal calibration, target outside fraction, follow-through (ATR), horizon N, min follow-through probability.
Anchor: "Auto (pivots)" to catch trend origins, "Session" for a daily basis, "Manual" for a specific event
Higher pivot strength anchors only on bigger swings (fewer re-anchors)
Turn on conformal calibration so bands match the real containment (check the containment %)
Follow-through (ATR) defines what counts as success
Best on liquid symbols with reliable volume (major crypto, futures)
💡 How to Use in Practice
Use the anchored VWAP as the institutional cost basis / fair value (above = buyers in control, below = sellers)
Use the σ-bands for overextension/containment; outside the band is statistically unusual
Use reclaim signals (with probability) to filter genuine VWAP-reclaim breaks
If containment drifts from target, reconsider calibration or σ validity
Combine with AE-CVD (flow) or AE-RISK (sizing)
⚠️ Important Notes
Auto-anchoring lags by the pivot confirmation, and the basis shifts on re-anchor
The follow-through forecast is a probability and will miss (reclaims can fail)
Needs a learning period (warmup); learning resets on anchor/timeframe/parameter change
Probability, not a guarantee — always do your own due diligence and use risk management
🚨 Disclaimer
This indicator is for educational and informational purposes only and is not financial advice or a recommendation to buy or sell. No method guarantees future profits; past performance does not indicate future results, and trading carries the risk of loss. All decisions are your own — use proper validation and disciplined risk management.
Anchored VWAP marks the volume-weighted cost basis from an event. AE-VWAP picks the anchor for you and learns whether reclaiming the VWAP actually means something. It auto-anchors at significant swings, conformally calibrates its volume-weighted σ-bands to a target containment, and learns the follow-through probability after price crosses the anchored VWAP.
🔶 Key Features
Auto-anchored VWAP — anchors at significant swings (Session / Manual also available)
Volume-weighted σ-bands — standard-deviation bands weighted by volume
Conformally calibrated bands — no normality assumption; band width k is set to hit a target containment
Learned reclaim edge — follow-through probability after a VWAP reclaim/loss (signal only when the odds back it)
Realized containment — shows how well the bands are calibrated
Reclaim signals + anchor markers + alerts; bar-close training — no repaint
🧠 Technical Architecture
VWAP: the source (hlc3/close/ohlc4) is volume-weighted: vwap = Σ(price·vol)/Σvol, σ = √(Σ vol·price²/Σvol − vwap²). Anchor modes: Auto (pivot confirmation) / Session (daily) / Manual (date).
Bands (conformal calibration): k is set to the (1−α) quantile of the standardized deviation |src−vwap|/σ, matching the target containment empirically. A fixed normal-assumption k tends to under-contain on fat tails — conformal fixes that.
ML (online logistic): at a VWAP reclaim (close × VWAP cross), six side-oriented features (momentum, trend alignment, RSI, σ-band-width regime, volume, anchor age) predict the follow-through probability = P(price continues tpK·ATR in the cross direction before recrossing, within N bars) via a triple barrier. No lookahead.
Honest scope: a volume-weighted mean + conformal calibration + a linear classifier (no RL). Not deep learning, not a guarantee.
⚙️ Recommended Settings & Tuning Guide (crypto 15m–4H)
Key parameters: anchor mode, pivot strength, band width k / conformal calibration, target outside fraction, follow-through (ATR), horizon N, min follow-through probability.
Anchor: "Auto (pivots)" to catch trend origins, "Session" for a daily basis, "Manual" for a specific event
Higher pivot strength anchors only on bigger swings (fewer re-anchors)
Turn on conformal calibration so bands match the real containment (check the containment %)
Follow-through (ATR) defines what counts as success
Best on liquid symbols with reliable volume (major crypto, futures)
💡 How to Use in Practice
Use the anchored VWAP as the institutional cost basis / fair value (above = buyers in control, below = sellers)
Use the σ-bands for overextension/containment; outside the band is statistically unusual
Use reclaim signals (with probability) to filter genuine VWAP-reclaim breaks
If containment drifts from target, reconsider calibration or σ validity
Combine with AE-CVD (flow) or AE-RISK (sizing)
⚠️ Important Notes
Auto-anchoring lags by the pivot confirmation, and the basis shifts on re-anchor
The follow-through forecast is a probability and will miss (reclaims can fail)
Needs a learning period (warmup); learning resets on anchor/timeframe/parameter change
Probability, not a guarantee — always do your own due diligence and use risk management
🚨 Disclaimer
This indicator is for educational and informational purposes only and is not financial advice or a recommendation to buy or sell. No method guarantees future profits; past performance does not indicate future results, and trading carries the risk of loss. All decisions are your own — use proper validation and disciplined risk management.
Script open-source
Nello spirito di TradingView, l'autore di questo script lo ha reso open source, in modo che i trader possano esaminarne e verificarne la funzionalità. Complimenti all'autore! Sebbene sia possibile utilizzarlo gratuitamente, ricordiamo che la ripubblicazione del codice è soggetta al nostro Regolamento.
Declinazione di responsabilità
Le informazioni e le pubblicazioni non sono intese come, e non costituiscono, consulenza o raccomandazioni finanziarie, di investimento, di trading o di altro tipo fornite o approvate da TradingView. Per ulteriori informazioni, consultare i Termini di utilizzo.
Script open-source
Nello spirito di TradingView, l'autore di questo script lo ha reso open source, in modo che i trader possano esaminarne e verificarne la funzionalità. Complimenti all'autore! Sebbene sia possibile utilizzarlo gratuitamente, ricordiamo che la ripubblicazione del codice è soggetta al nostro Regolamento.
Declinazione di responsabilità
Le informazioni e le pubblicazioni non sono intese come, e non costituiscono, consulenza o raccomandazioni finanziarie, di investimento, di trading o di altro tipo fornite o approvate da TradingView. Per ulteriori informazioni, consultare i Termini di utilizzo.