USG Analytics (Gold ETF Forecasting)
Forecasts daily gold ETF closes by pairing lean feature engineering with cross-validated ensemble models.
- Problem: Predict next-day Gold ETF adjusted close from market signals while avoiding leakage and overfitting on a small 2011–2019 dataset.
- Approach: Time series → supervised ML with 1-day lags + 7/30-day rolling means; models = RF, best-subset OLS, Lasso, Ridge; 10-fold CV; simple 4-model average ensemble.
- Result: Ensemble achieved the best error (MSE ≈ 1.44); RF the best single model (MSE ≈ 1.49); all beat the naive “yesterday = today” baseline (≈ 1.55).
- Repro: Python + scikit-learn; deterministic folds (`random_state=42`); save `requirements.txt`; add Binder/Colab badge.
Overview
Short narrative about data, features, and modeling choices.
Methods
- Feature engineering (lags/rolls), model grid, cross-validation, ensembling.
Results
- Errors vs. baseline, plots (residuals, feature importances), notes on stability.
Links: GitHub Repo · Report (PDF)