Case 05 — ML signal system for crypto futures
Production-grade LSTM signal system: 77,179 training samples, 79 features, 50 selected. Confidence-threshold inference — not every signal is traded, only the top 35 %.
The challenge
A quant trader wanted an ML system calibrated for precision, not quantity: many signals, only the most confident ones executed. Requirements: clean feature engineering, LSTM training with validation-gap control, confidence scoring, reproducible backtests.
Architecture
A feature-engineering pipeline produces 79 candidate features from OHLCV data; feature selection narrows them to the 50 strongest. An LSTM model with 24,962 parameters classifies. The smart-inference layer drops signals below the confidence threshold. Backtesting and live engines share the same inference logic.
Pipeline
Training and inference lifecycle
- 01Feature engineering across 5 markets and several timeframes
- 02Balanced training with validation-gap monitoring (≤ 15 %)
- 03Feature-selection pass delivers a +0.5–1 % uplift
- 04Confidence threshold 0.65 → top-35 % signals are traded
- 05Backtesting replay before every live rollout
Technology stack
Outcome
Validation accuracy 53 %, win-rate after confidence filter 56–58 %. Train/val gap under 14 % — the model generalises. Production inference pipeline is deterministic: same features → same decision. No black-box overselling, every signal explained via feature importances.