Stage 1
Direction edge experiment 72k+
Experiment Summary
Random Forest ยท 60s direction target
- Train rows
- 4756
- Test rows
- 2039
- Default confidence
- 0.8
- Accuracy
- 0.4012
- Progress stage
- -
- Started
- 2026-06-30 12:07:47.951771+02:00
- Heartbeat
- -
- Completed
- 2026-06-30 12:08:04.641012+02:00
Training Dataset Diagnostics
Eligibility funnel captured when this experiment trained.
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.
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 | 2026-06-30 12:09 |