LendWise, a mid-size digital lending platform processing about 120K personal loan applications per quarter, wants a model to predict whether an approved borrower will default within 12 months. The risk team needs a simple, explainable model to support underwriting decisions and reduce charge-offs without materially lowering approval volume.
The training data contains historical funded loans from the last 3 years.
| Feature Group | Count | Examples |
|---|---|---|
| Applicant demographics | 6 | age, employment_length, home_ownership, state |
| Credit attributes | 9 | fico_score, revolving_utilization, delinquencies_2y, inquiries_6m |
| Loan attributes | 7 | loan_amount, interest_rate, term_months, purpose |
| Banking and income | 6 | annual_income, debt_to_income, monthly_obligations, verified_income |
| Behavioral / history | 5 | prior_loans, prior_defaults, days_since_last_loan, autopay_enrolled |
default_12m — whether the borrower becomes 90+ days delinquent within 12 monthsA good solution should achieve ROC-AUC >= 0.78, recall >= 0.60 at precision >= 0.35, and provide coefficients or feature effects that the credit policy team can explain to auditors.