Trustworthy and Explainable Artificial Intelligence for Reliable Bank Term Deposit Subscription Prediction
Computational Discovery and Intelligent Systems (CDIS) · 2026
DOI: 10.66279/016z8w59 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computational Discovery and Intelligent Systems (CDIS), 2026. Verfasst von Gehad Ashraf Abd Elmoneam und 3 weiteren Autor:innen. Die Arbeit nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Predicting subscription to a bank term deposit is a highly imbalanced binary classification problem in which apparently strong performance can result from information that is unavailable at the time of targeting. This study develops and audits a leakage aware prediction pipeline using the UCI Bank Marketing dataset. The analysis compares logistic regression with XGBoost, LightGBM, and CatBoost, evaluates class imbalance treatments, performs hyperparameter optimization, examines probability calibration, and adds model agnostic and model specific explanations. The post call duration variable is excluded from the deployable feature set and retained only for a controlled leakage experiment. Five fold cross validation on the training partition gives realistic ROC AUC values from 0.7519 to 0.7959, whereas inclusion of duration increases the corresponding values to 0.8966 to 0.9375. On the untouched random test partition, the calibrated LightGBM model obtains ROC AUC 0.8101, average precision 0.4698, and Brier score 0.0795. An inferred chronological stress test produces ROC AUC 0.7089, demonstrating that random partition estimates can overstate temporal portability. Under illustrative unit economics, a threshold selected from training set out of fold predictions increases test set expected profit from 16,595 to 41,825 units. These findings support a practical principle: leakage control, temporal validation, calibration, and decision analysis are more consequential than small differences among strong tree boosting algorithms.
Zitieren
APA
Elmoneam, G. A. A., Khalid, H., Taha, M., & Salah, H. (2026). Trustworthy and Explainable Artificial Intelligence for Reliable Bank Term Deposit Subscription Prediction. Computational Discovery and Intelligent Systems (CDIS). https://doi.org/10.66279/016z8w59
Vancouver
Elmoneam GAA, Khalid H, Taha M, Salah H. Trustworthy and Explainable Artificial Intelligence for Reliable Bank Term Deposit Subscription Prediction. Computational Discovery and Intelligent Systems (CDIS). 2026. doi:10.66279/016z8w59
BibTeX
@article{Elmoneam2026,
author = {Elmoneam, Gehad Ashraf Abd and Khalid, Heba-t-allah and Taha, Manar and Salah, Habiba},
title = {Trustworthy and Explainable Artificial Intelligence for Reliable Bank Term Deposit Subscription Prediction},
journal = {Computational Discovery and Intelligent Systems (CDIS)},
year = {2026},
doi = {10.66279/016z8w59}
}
EUVIMED