Methodology

Technical details on models, calibration, evaluation, and fairness diagnostics.

1. Models

Model Type Details
XGBoost Gradient boosting 500 trees, lr=0.05, depth=6, Optuna-tuned (32 trials, TPE sampler, minimizing Brier)
Logistic Regression Linear Custom batch gradient descent, L2=1e-3
Lasso-Logistic L1-regularized L1=5e-4, proximal gradient descent
Base Rate Naive Predicts training-set positive rate for all

2. Calibration

3. Evaluation Metrics

Metric Role Notes
Brier score Primary Proper scoring rule (lower is better). Rewards calibration AND discrimination
AUROC Ranking How well model ranks individuals (higher is better)
AUPRC Positive-class ranking Important when base rate is moderate
ECE Calibration check Expected calibration error
FPR/FNR Threshold-dependent False positive/negative rates at chosen threshold

4. Horizon Conditioning

This prevents label leakage across horizons.

5. Fairness Diagnostics

6. SHAP

7. Libraries

Library Version
scikit-learn ≥1.4
xgboost ≥2.0
optuna ≥3.6
shap ≥0.44
Python 3.11+

8. Data