NorthBridge Bank issues unsecured personal loans to roughly 1.2M applicants per year across the U.S. The credit risk team wants a model that predicts whether an applicant will become 90+ days delinquent within 12 months of origination so underwriting can reduce losses without materially hurting approval volume.
| Feature Group | Count | Examples |
|---|---|---|
| Applicant profile | 12 | age, employment_length, annual_income, housing_status |
| Credit bureau | 18 | fico_score, revolving_utilization, inquiries_6m, delinquencies_2y |
| Loan application | 9 | loan_amount, term_months, interest_rate, purpose |
| Account behavior snapshots | 6 | prior_relationship_months, avg_balance_90d, overdraft_count_12m |
| Derived temporal features | 7 | income_to_loan_ratio, dti_bucket, recent_inquiry_trend |
A solution is considered good enough if it improves ranking quality over the current scorecard and achieves ROC-AUC >= 0.80, PR-AUC >= 0.32, and recall >= 70% at precision >= 25% on an out-of-time test set. The model should also provide stable, regulator-friendly explanations.