Evaluate credit-limit increase profitability

Business/Analytics Case: Strategy for Credit Limit Increases

You work as a data scientist on a consumer credit team.

Scenario

A credit-limit increase initiative is under consideration for one defined customer segment (for instance, cardholders with 6 to 12 months of tenure and a mid-range FICO). Your job is to say whether it should launch, and how large it should be and whom it should target.

What to do

1. Pin down the objective: is success revenue growth, profit, a lower default rate, a higher approval rate, retention, or some mix of these?
2. Build a straightforward P&L / unit economics model:
   • Start from a profit identity such as: $\text{Profit} = \text{Revenue} - \text{Loss} - \text{Operational Cost}$
   • Spell out what falls under revenue (interest, interchange, fees, for example) and what counts as loss (charge-offs, fraud, cost of funds).
3. Name the main levers and the trade-offs among them (limit size, eligibility rules, APR and pricing, risk policy, model thresholding).
4. Lay out an evaluation plan covering the data required, segmentation, and experiment design, and describe how you would gut-check the figures with rough mental math.

Output

Deliver a structured recommendation: what to launch (or whether to launch at all), which customers to aim at, which metrics to optimize, and how to measure incremental profit and risk. Overview: This prompt tests a data engineer's grasp of business analytics, unit-economics P&L modeling, the trade-off between risk and revenue, and experiment-driven assessment of credit product changes. See the complete Capital One Data Engineer interview account this question came from