LendWise, a digital consumer lending platform processing ~250K loan applications per month, wants to improve its loan default model before expanding credit approval volume. You need to tune a deep learning model that predicts whether an applicant will default within 90 days of origination.
The training data contains applicant, bureau, and behavioral features collected at application time.
| Feature Group | Count | Examples |
|---|---|---|
| Applicant demographics | 8 | age, employment_length, housing_status |
| Financial attributes | 14 | annual_income, debt_to_income, revolving_utilization |
| Credit bureau signals | 11 | fico_band, delinquencies_2y, inquiries_6m |
| Application metadata | 6 | channel, state, loan_purpose, requested_amount |
| Engineered history features | 9 | prior_loans_count, prior_missed_payments, avg_days_late |
A strong solution should improve ranking quality over a logistic regression baseline and produce a stable model suitable for monthly retraining. Target business performance is AUC-ROC >= 0.84, PR-AUC >= 0.42, and recall >= 0.70 at precision >= 0.35.