Data Analyst in Digital Lending: Tackling Default Spikes
Investigate a sudden rise in 30-day loan defaults among newly acquired borrowers and pinpoint the true operational driver to protect portfolio margins.
Context
You are a Data Analyst at a digital lending app. The platform provides microloans ranging from $100 to $1,000 with a 30-day repayment term. Over the past month, first-loan 30-day default rates escalated from an average of 3.2% to 7.8%, threatening lending margins and credit facility covenants. The Head of Credit Risk suspects that a newly launched affiliate acquisition campaign is attracting subprime borrowers and is considering shutting it down immediately. You have been tasked with investigating the borrower performance data and presenting your findings to the Credit Committee by end of day.
Your Task
Prepare an executive briefing for the Head of Credit Risk covering:
- Recommendation — one concrete decision regarding lending operations and marketing channel allocation.
- Impact — projected default rate recovery, financial exposure prevented, and portfolio volume implications.
- Implementation Plan — immediate mitigation steps, verification rollout, and monitoring milestones over the next 30 days (owner, sequence, timing).
Available Data
Recent Monthly Loan Cohort Performance
| Cohort Month | Total Loans Disbursed | Average Loan Size | 30-Day Default Rate | Primary Channel A Default Rate | Affiliate Channel B Default Rate |
|---|---|---|---|---|---|
| January | 24,000 | $350 | 3.1% | 3.0% | 3.3% |
| February | 26,500 | $360 | 3.3% | 3.2% | 3.5% |
| March | 38,000 | $355 | 7.8% | 3.4% | 11.6% |
Narrative Summary: In March, the growth team ramped up Affiliate Channel B, contributing 18,000 of the 38,000 total disbursements. Preliminary risk reporting shows Affiliate Channel B with an alarming 11.6% 30-day default rate, compared to 3.4% for organic and direct traffic (Primary Channel A). Initial management consensus is that Channel B attracts uncreditworthy applicants.