Explainable Machine Learning for Bank Marketing Campaign Success Prediction and Decision-Support Recommendations

Explainable Machine Learning for Bank Marketing Campaign Success Prediction and Decision-Support Recommendations

Parisa GhahremanShahraki1

1) Computer Engineer

IOI Code : AAHC-ABKKCZ
Publication : National Conference on Management, Commercialization, Knowledge-Based Economy and Investment for Production(impeb.ir)
Abstract :
    Objective: Inappropriately targeted direct bank-marketing campaigns may involve high contact costs and low conversion rates. This study aimed to develop an explainable machine-learning framework to predict the probability of a customer subscribing to a term deposit and to translate the predictions into practical recommendations for customer prioritization. Methods: The Bank Marketing dataset, comprising 41,188 records from direct marketing campaigns of a Portuguese bank, was used. After removing 12 duplicate records, 41,176 observations remained for analysis. To prevent information leakage, the call-duration variable (duration), which is only known after a call has been completed, was excluded from the primary pre-contact model. Following feature engineering and a stratified random split of the data into training and test sets, Logistic Regression, Random Forest, and CatBoost models were compared. The final model was calibrated using isotonic regression and interpreted using SHAP. Evaluation was conducted using accuracy, precision, sensitivity, specificity, F1-score, ROC-AUC, PR-AUC, and Brier score. Results: The campaign success rate was 11.27%. The calibrated Random Forest was selected as the final model and achieved an accuracy of 0.8774, sensitivity of 0.5991, specificity of 0.9127, F1-score of 0.5240, ROC-AUC of 0.8047, PR-AUC of 0.4600, and Brier score of 0.0758 on the test set. According to the SHAP analysis, the most influential predictors were employment variation rate, number of employees, three-month Euribor rate, contact type, contact month, age, job, and previous campaign outcome. Under the contact-capacity scenario, selecting the top 15% of customers by predicted probability captured 60.67% of all successful outcomes while maintaining an observed success rate of 45.55%. Conclusion: Combining leakage-aware modelling, probability calibration, and explainability enables machine-learning predictions to be used as a decision-support tool for customer prioritization. Nevertheless, the identified relationships are observational and should be assessed through continuous monitoring, recalibration, and prospective evaluation before operational deployment.

Keywords : bank marketing explainable machine learning random forest probability calibration shap decision support term deposit