Direction edge experiment

Experiment Summary

Random Forest · 60s direction target

completed

Train rows: 4756
Test rows: 2039
Default confidence: 0.8
Accuracy: 0.4012
Progress stage: -
Started: 2026-06-27 20:15:14.899929+02:00
Heartbeat: -
Completed: 2026-06-27 20:15:37.954544+02:00

Training Dataset Diagnostics

Eligibility funnel captured when this experiment trained.

Training diagnostics unavailable

This experiment artifact does not include training diagnostics.

Class Metrics

Class	Precision	Recall	F1
long	0.4023	0.524	0.4551
short	0.3968	0.4216	0.4088
flat	0.4248	0.1171	0.1836

Confusion Matrix

Actual \ Predicted	Long	Short	Flat
Long	426	352	35
Short	442	344	30
Flat	191	171	48

Feature Importance

Top 20 features reported by the trained model.

price_change_percent_24h

0.024914

ask_wall_score

0.024818

candle_momentum_5

0.02454

candle_return_3

0.023806

cross_exchange_price_deviation_percent

0.023368

cross_exchange_spread_percent

0.023256

wall_shift_score

0.023189

imbalance_5_delta

0.023021

volume_24h

0.022833

imbalance_10_delta

0.022828

mid_price_delta

0.022815

bid_wall_score

0.022771

order_book_imbalance_20

0.022598

quote_volume_24h

0.022559

order_book_imbalance_10

0.022373

spread_percent

0.021941

order_book_imbalance_5

0.02116

capture_latency_ms

0.02108

cross_exchange_mid_median

0.02076

cross_exchange_mid_avg

0.020668

Probability Diagnostics

Maximum class probabilities on the held-out rows used by shadow backtesting.

Probability diagnostics unavailable

No labeled held-out rows remain for diagnostics.

Run Shadow Backtest

Historical simulation on held-out test rows only. No orders or live predictions.

Shadow Backtest Results

Expectancy values are percentages per accepted historical signal.

Edge	Confidence	Signals	Long / Short	Win rate %	Avg win %	Avg loss %	Raw expectancy %	Net expectancy %	Max drawdown %	Profit factor	Fees + slip %	Created
Weak / Insufficient	0.8	0	0 / 0	-	-	-	-	-	-	-	0.15	2026-06-27 20:17