rckrdmrd 75c4d07690 feat: Initial commit - ML Engine codebase

Hierarchical ML Pipeline for trading predictions:
- Level 0: Attention Models (volatility/flow classification)
- Level 1: Base Models (XGBoost per symbol/timeframe)
- Level 2: Metamodels (XGBoost Stacking + Neural Gating)

Key components:
- src/pipelines/hierarchical_pipeline.py - Main prediction pipeline
- src/models/ - All ML model classes
- src/training/ - Training utilities
- src/api/ - FastAPI endpoints
- scripts/ - Training and evaluation scripts
- config/ - YAML configurations

Note: Trained models (*.joblib, *.pt) are gitignored.
      Regenerate with training scripts.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

2026-01-18 04:27:40 -06:00

2.2 KiB

Raw Permalink Blame History

Symbol-Timeframe Model Training Report

Generated: 2026-01-07 00:00:48

Configuration

Training Data Cutoff: 2024-12-31 (excluding 2025 for backtesting)
Dynamic Factor Weighting: Enabled
Sample Weight Method: Softplus with beta=4.0, w_max=3.0

Training Results Summary

Model	Symbol	Timeframe	Target	MAE	RMSE	R2	Dir Accuracy	Train	Val
XAUUSD_5m_high_h3	XAUUSD	5m	high	0.925573	1.299031	-0.0652	90.40%	288433	50901
XAUUSD_5m_low_h3	XAUUSD	5m	low	0.853913	1.248952	-0.0674	95.60%	288433	50901
XAUUSD_15m_high_h3	XAUUSD	15m	high	1.573459	2.169436	-0.0094	93.51%	96882	17097
XAUUSD_15m_low_h3	XAUUSD	15m	low	1.536228	2.175787	-0.0997	97.05%	96882	17097
EURUSD_5m_high_h3	EURUSD	5m	high	0.000367	0.000615	-0.0012	97.94%	312864	55212
EURUSD_5m_low_h3	EURUSD	5m	low	0.000352	0.000593	-0.0082	98.12%	312864	55212
EURUSD_15m_high_h3	EURUSD	15m	high	0.000650	0.001053	-0.0006	98.28%	104710	18479
EURUSD_15m_low_h3	EURUSD	15m	low	0.000624	0.000990	-0.0009	98.33%	104710	18479

Model Files

Models saved to: /home/isem/workspace-v1/projects/trading-platform/apps/ml-engine/models/symbol_timeframe_models

Model Naming Convention

{symbol}_{timeframe}_high_h{horizon}.joblib - High range predictor
{symbol}_{timeframe}_low_h{horizon}.joblib - Low range predictor

Usage Example

from training.symbol_timeframe_trainer import SymbolTimeframeTrainer

# Load trained models
trainer = SymbolTimeframeTrainer()
trainer.load('models/symbol_timeframe_models/')

# Predict for XAUUSD 15m
predictions = trainer.predict(features, 'XAUUSD', '15m')
print(f"Predicted High: {predictions['high']}")
print(f"Predicted Low: {predictions['low']}")

Notes

Models exclude 2025 data for out-of-sample backtesting
Dynamic factor weighting emphasizes high-movement samples
Separate models for HIGH and LOW predictions per symbol/timeframe

Report generated by Symbol-Timeframe Training Pipeline

2.2 KiB Raw Permalink Blame History