BrightLine Credit, a digital consumer lender processing ~250K applications per month, wants a model to predict 90-day loan default at origination. The goal is to improve approval quality without materially reducing funded volume.
You are given an offline training dataset built from the last 18 months of applications. Each row represents one funded or declined application with features available at decision time.
| Feature Group | Count | Examples |
|---|---|---|
| Applicant demographics | 8 | age_band, employment_status, region, housing_status |
| Credit bureau attributes | 14 | fico_band, delinquency_count_12m, credit_utilization, open_trades |
| Financial features | 11 | stated_income, debt_to_income, monthly_obligations, bank_balance_avg |
| Application behavior | 7 | device_type, session_length_sec, form_edits, application_hour |
| Loan terms | 5 | requested_amount, term_months, APR, channel, promo_flag |
A solution is considered good enough if it improves ranking quality over the current scorecard and supports a policy that reduces default rate by at least 15% at a fixed approval rate. The model should also provide clear feature-level explanations for risk review.