LendWise, a digital consumer lending platform processing ~250K applications per quarter, wants a model to predict whether an approved borrower will default within 90 days of origination. The goal is to improve underwriting decisions while keeping the model explainable for risk and compliance teams.
| Feature Group | Count | Examples |
|---|---|---|
| Applicant demographics | 6 | age, employment_status, region, housing_status |
| Credit bureau variables | 11 | credit_score, delinquencies_12m, total_open_accounts, utilization_rate |
| Application attributes | 8 | loan_amount, term_months, interest_rate, purpose |
| Bank transaction aggregates | 9 | avg_monthly_income, income_volatility, nsf_count_90d, avg_balance |
| Behavioral / derived | 6 | application_hour, device_risk_score, prior_applications_30d, fraud_flag_history |
default_90d — 1 if borrower misses payments and is charged off within 90 days, else 0A solution is considered good enough if it achieves ROC-AUC >= 0.82, PR-AUC >= 0.42, and recall >= 0.70 at precision >= 0.35 on a held-out test set. The candidate should also show a clear, repeatable model-building process from raw data to threshold selection.