Home

Personal Loan Campaign Intelligence

AllLife Bank — Supervised Learning Classification

What you'll see here

Predict which existing depositors are most likely to accept a personal loan offer, so AllLife Bank's marketing spend converts at a higher rate than last year's 9% pilot.

Business Context

AllLife Bank is a mid-sized US retail bank with a large base of liability customers(depositors) but a thin base of asset customers (borrowers). The retail marketing team wants to grow interest income by converting more depositors into personal-loan customers.

Last year's pilot campaign converted roughly 9% of contacted depositors. To do better, marketing needs to know who to target — and to back that targeting with evidence, not intuition.

Business objective

Increase personal loan conversion while reducing marketing spend wasted on low-probability customers.

Classification objective

Build a supervised classifier that flags depositors with high probability of accepting a loan offer.

Decision the model supports

Who should the marketing team contact — and through which channel — in the next campaign cycle?

Target variable
Personal_Loan
— binary target
Positive class · 1
Customer accepted the personal loan offer.
Negative class · 0
Customer did not accept the personal loan offer.
AI: Why this classification problem matters

Click Generate to produce an evidence-based observation, insight, recommendation, and business benefit for this section.