ML / Classification Project
Bank Term Deposit Prediction
A two-stage machine learning pipeline predicting whether a bank client will subscribe to a term deposit after a phone marketing campaign.
Seven reproducible stages from raw data to model insights.
Problem & Goal
Predict term deposit subscription. Optimise for recall using F2 as the tuning guardrail.
Only ~12% of clients subscribe, so the model is tuned to catch positives (recall), with F2 keeping precision in check.
Project objective
Maximise recall, controlled by F2.
The positive class is small, so accuracy alone is misleading. The model is designed to catch as many likely subscribers as possible, while F2 keeps precision from becoming completely uncontrolled.
Recall = TP / (TP + FN)
Share of real subscribers the model actually catches — the metric we maximise.
Target distribution
Only 11.7% of clients subscribed. A naive model can predict “no” for everyone and still achieve high accuracy.
Because missing a real subscriber is worse than making an extra call, the pipeline prioritises recall and uses F2 as the model-selection metric.