|
1 year
experience
|
1
products
|
2
demo versions
|
|
0
jobs
|
0
signals
|
0
subscribers
|
Quantitative researcher building production-grade ML pipelines for MetaTrader 5.
Author of the "MetaTrader 5 Machine Learning Blueprint" (20+ parts) and
"Feature Engineering for ML" series on MQL5 Community — the most comprehensive
free resource for applying Advances in Financial Machine Learning (López de Prado)
to live trading.
What I build:
• End-to-end Python→MQL5 pipelines: tick data → features → triple-barrier labels
→ PurgedKFold CV → Optuna HPO → ONNX → live EA
• MQL5 indicators & EAs with embedded microstructure, fractal, and structural-break features
• Custom ML solutions for prop-firm evaluation criteria and risk constraints
Available for hire:
→ Custom strategy development (Python research + MQL5 deployment)
→ Feature engineering & model diagnostics for your alpha idea
→ Audit of existing ML pipelines for data leakage, look-ahead bias, and overfitting
Publications: https://www.mql5.com/en/users/patricknjoroge743/publications
Contact: patricknjoroge743@proton.me
Author of the "MetaTrader 5 Machine Learning Blueprint" (20+ parts) and
"Feature Engineering for ML" series on MQL5 Community — the most comprehensive
free resource for applying Advances in Financial Machine Learning (López de Prado)
to live trading.
What I build:
• End-to-end Python→MQL5 pipelines: tick data → features → triple-barrier labels
→ PurgedKFold CV → Optuna HPO → ONNX → live EA
• MQL5 indicators & EAs with embedded microstructure, fractal, and structural-break features
• Custom ML solutions for prop-firm evaluation criteria and risk constraints
Available for hire:
→ Custom strategy development (Python research + MQL5 deployment)
→ Feature engineering & model diagnostics for your alpha idea
→ Audit of existing ML pipelines for data leakage, look-ahead bias, and overfitting
Publications: https://www.mql5.com/en/users/patricknjoroge743/publications
Contact: patricknjoroge743@proton.me