Random Mix strategy on USD/CHF 5min: API-default style: randomly composed indicator set, model learns the rule. Features: RSI 7, Candle structure, Keltner (20,2.0). Model: Gradient Boosting. Label horizon 3 bars, confidence threshold 0.58, direction both. Risk: 15 pip stop / 30 pip target (1:2 R/R), 1.0 lot on $10k, $6 round-trip commission.

Random Mix strategy on USD/CAD 1h: API-default style: randomly composed indicator set, model learns the rule. Features: Candle structure, SMA 100, Return lags 1-5, BB (20,2.0), ATR 10. Model: Gradient Boosting. Label horizon 4 bars, confidence threshold 0.58, direction both. Risk: 25 pip stop / 50 pip target (1:2 R/R), 1.0 lot on $10k, $6 round-trip commission.

Random Mix strategy on USD/CAD 5min: API-default style: randomly composed indicator set, model learns the rule. Features: ADX 14, Return lags 1-8, BB (10,2.0), ATR 14, Volatility 50. Model: LightGBM. Label horizon 6 bars, confidence threshold 0.58, direction both. Risk: 15 pip stop / 30 pip target (1:2 R/R), 1.0 lot on $10k, $6 round-trip commission.

Signal Mix strategy on NZD/USD 1h. A compact, machine-selected indicator set; the classifier learns the entry rule directly from the features. Features: SMA 200, MACD (12,26,9), Volatility 50. Model: Gradient Boosting; label horizon 2 bars, confidence threshold 0.55, direction both. Risk: 25 pip stop / 50 pip target (1:2 R/R), 1.0 lot on $10k, $6 round-trip commission. Trained on the last 40 days with a 70/30 holdout; the published numbers are the out-of-sample 30%.

Signal Mix strategy on NZD/USD 15min. A compact, machine-selected indicator set; the classifier learns the entry rule directly from the features. Features: CCI 14, Williams %R 21, Keltner (20,2.0), Return lags 1-8. Model: XGBoost; label horizon 3 bars, confidence threshold 0.55, direction both. Risk: 25 pip stop / 50 pip target (1:2 R/R), 1.0 lot on $10k, $6 round-trip commission. Trained on the last 40 days with a 70/30 holdout; the published numbers are the out-of-sample 30%.