Live Model Diagnostics

Signal Model Performance

Directional accuracy across Bitcoin, Ethereum, Gold, Silver, Oil, Brent, Dow Jones, S&P 500 and NVIDIA — validated on market data the system never encountered during training. No look-ahead. No data leakage. No survivorship bias. Numbers reflect real forward-looking labels only.
36,000–210,000 signals per asset  ·  M5 timeframe  ·  5-fold time-series cross-validation  ·  up to 2 years of market history
Per-Asset Performance
Crypto
Bitcoin
Directional Accuracy
58.6%
BUY / SELL correct direction

Overall 3-Class Accuracy
44.8%
BUY / SELL / WAIT · random = 33.3%

vs direction
+8.6pp
Crypto
Ethereum
Directional Accuracy
58.9%
BUY / SELL correct direction

Overall 3-Class Accuracy
44.8%
BUY / SELL / WAIT · random = 33.3%

vs direction
+8.9pp
Commodity
Gold
Directional Accuracy
62.4%
BUY / SELL correct direction

Overall 3-Class Accuracy
50.2%
BUY / SELL / WAIT · random = 33.3%

vs direction
+12.4pp
Commodity
Silver
Directional Accuracy
62.0%
BUY / SELL correct direction

Overall 3-Class Accuracy
43.8%
BUY / SELL / WAIT · random = 33.3%

vs direction
+12.0pp
Energy
Oil (WTI)
Directional Accuracy
60.2%
BUY / SELL correct direction

Overall 3-Class Accuracy
51.0%
BUY / SELL / WAIT · random = 33.3%

vs direction
+10.2pp
Energy
Brent Oil
Directional Accuracy
60.5%
BUY / SELL correct direction

Overall 3-Class Accuracy
50.9%
BUY / SELL / WAIT · random = 33.3%

vs direction
+10.5pp
Index
S&P 500
Directional Accuracy
62.1%
BUY / SELL correct direction

Overall 3-Class Accuracy
50.4%
BUY / SELL / WAIT · random = 33.3%

vs direction
+12.1pp
Equity
NVIDIA
Directional Accuracy
62.5%
BUY / SELL correct direction

Overall 3-Class Accuracy
51.1%
BUY / SELL / WAIT · random = 33.3%

vs direction
+12.5pp
Index
Dow Jones
Directional Accuracy
61.3%
BUY / SELL correct direction

Overall 3-Class Accuracy
50.2%
BUY / SELL / WAIT · random = 33.3%

vs direction
+11.3pp
Why two accuracy numbers? The model outputs three classes: BUY, SELL, or WAIT. Overall accuracy measures all three — including WAIT signals, which are deliberately issued when conviction is low. Directional accuracy only measures the BUY/SELL calls against a 50% coin-flip baseline. That is the number that matters for trading: when the model commits to a direction, how often is it right?
Conviction Calibration — The Higher the Confidence, the More Accurate
Historical Accuracy by Confidence Bucket
Overall accuracy  ·  directional accuracy in parentheses
Confidence Bitcoin Ethereum Gold Silver Oil (WTI) Brent Dow Jones S&P 500 NVIDIA Rating
45 – 55% 46.4% (59.9% dir) 45.8% (59.8% dir) 46.9% (60.6% dir) 48.3% (60.7% dir) 48.2% (58.1% dir) 48.8% (59.3% dir) 47.6% (60.0% dir) 47.9% (59.7% dir) 47.4% (59.4% dir) Moderate
55 – 65% 54.5% (66.8% dir) 57.5% (69.7% dir) 62.5% (70.1% dir) 61.5% (68.8% dir) 60.8% (67.9% dir) 63.3% (69.7% dir) 64.2% (70.5% dir) 63.6% (70.7% dir) 61.6% (69.7% dir) High
65 – 75% 63.6% (72.2% dir) 71.1% (79.0% dir) 81.2% (81.7% dir) 78.8% (78.0% dir) 75.1% (78.2% dir) 81.7% (83.2% dir) 80.9% (82.3% dir) 78.8% (79.6% dir) 76.5% (77.9% dir) High
75%+ 84.0% (81.2% dir) 85.1% (87.8% dir) 91.3% (88.0% dir) 87.1% (78.0% dir) 90.1% (86.2% dir) 93.5% (90.7% dir) 91.3% (89.5% dir) 86.8% (86.0% dir) 89.5% (85.3% dir) Peak
What this means: Conviction is monotonically calibrated — accuracy rises consistently as the model's confidence increases. At 75%+ conviction, BTC signals have been correct 84.0% of the time across 430 historical instances, and ETH signals 85.1% correct across 322 instances. These high-conviction signals are rare by design: the model holds back unless the evidence is strong. Users can see the current conviction level on every signal in the app.
Signal Quality — Correct Calls Move More
Average Price Move: Correct vs Incorrect Signals
Measured over the 6-bar lookahead window after signal issuance
Bitcoin
Correct calls
+0.244%
Incorrect calls
+0.183%
Quality gap
+33%
Ethereum
Correct calls
+0.366%
Incorrect calls
+0.264%
Quality gap
+39%
Gold
Correct calls
+0.18%
Incorrect calls
+0.131%
Quality gap
+37%
Silver
Correct calls
+0.408%
Incorrect calls
+0.319%
Quality gap
+28%
Oil (WTI)
Correct calls
+0.306%
Incorrect calls
+0.248%
Quality gap
+23%
Brent Oil
Correct calls
+0.291%
Incorrect calls
+0.230%
Quality gap
+26%
Dow Jones
Correct calls
+0.091%
Incorrect calls
+0.066%
Quality gap
+38%
S&P 500
Correct calls
+0.083%
Incorrect calls
+0.062%
Quality gap
+34%
NVIDIA
Correct calls
+0.629%
Incorrect calls
+0.436%
Quality gap
+44%
Why the quality gap matters: Even when the model is wrong about direction, the magnitude of the move tends to be smaller. When it is right, the move is larger. This asymmetry — correct calls catching bigger moves, incorrect calls occurring on smaller noise — is the structural trading edge beyond raw accuracy alone.
How the Model Works
Architecture Overview
Signal pipeline · from raw price data to BUY / SELL / WAIT
Signal Type
3-class classification — BUY, SELL, or WAIT. The WAIT class is a deliberate output, not a fallback. The model withholds a directional call when evidence is insufficient, reducing noise and false positives.
Label Generation
Maximum Favorable Excursion (MFE) scaled by Average True Range. Labels reflect whether a real, volatility-adjusted move occurred in the next 6 bars — not just whether the next candle closed up or down.
Feature Engineering
100+ technical features per bar — momentum indicators, volatility measures, volume signals, trend structure, candlestick patterns, Ichimoku components, and multi-timeframe lags. All features are strictly backward-looking.
Dimensionality Reduction
Return-weighted PCA — a variation of standard PCA where principal components are selected based on their correlation with forward price returns, not just variance explained. This biases the feature space toward market-relevant structure.
Model Architecture
Soft-voting ensemble of gradient-boosted trees and a random forest. Each model produces class probabilities; the ensemble averages them. The final confidence score is the probability of the winning class — a real calibrated number, not a heuristic.
Validation Protocol
Strict chronological split — training on earliest data, testing on most recent. No shuffling. 5-fold time-series cross-validation with each fold advancing forward in time. No data leakage between folds.
Comparative Summary
Asset Directional Accuracy Overall Accuracy Uplift vs Coin Flip Uplift vs Random (3-class) Rating
Gold
62.4% 50.2% +12.4pp +16.8pp High
Bitcoin
58.6% 44.8% +8.6pp +11.5pp High
Ethereum
58.9% 44.8% +8.9pp +11.5pp High
Silver
62.0% 43.8% +12.0pp +10.5pp High
Oil (WTI)
60.2% 51.0% +10.2pp +17.6pp High
Brent Oil
60.5% 50.9% +10.5pp +17.6pp High
Dow Jones
61.3% 50.2% +11.3pp +16.8pp High
S&P 500
62.1% 50.4% +12.1pp +17.1pp High
NVIDIA
62.5% 51.1% +12.5pp +17.8pp High
Past model performance does not guarantee future results. Markets are non-stationary — model accuracy may vary across different market regimes. Enodara provides market intelligence for informational purposes only and does not constitute financial advice. All figures will be updated following each model retrain.