Artificial Intelligence–Driven Decision Intelligence in Banking and FinTech: Predictive Analytics for Financial Risk, Customer Behaviour, and Strategic Management
Computer and Decision Making An International Journal · 03.11.2026
DOI: 10.1922/comdem.v3i6s.19006 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer and Decision Making An International Journal, online erschienen am 03.11.2026. Verfasst von Vishweswar sastry V N und 5 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The use of artificial intelligence (AI) in banking and FinTech is growing, and while many focus on predictive accuracy when deploying AI, more is needed to make it work. This study proposes an AI-powered decision-intelligence platform with the combined features of credit-default prediction, repayment-behaviour analytics, model explanation, and risk stratification. The UCI Default of Credit Card Clients data set was analyzed which consists of 30,000 customers and 23 predictors. Four classifiers – Logistic Regression, Random Forest, Extra Trees and HistGradientBoosting – were tested on leakage-safe stratified training and cross validation with a hold out test set, following the category cleaning and behaviour-oriented feature engineering process. Since the defaults accounted for 22.12% of the observations, average precision was chosen as the main model selection criterion. HistGradientBoosting was the best model in terms of cross-validated average precision (0.558) and PR-AUC (0.559) and ROC-AUC (0.782) on the held-out data. On the training-derived threshold, 0.225, sensitivity, specificity and F1-score were 63.83%, 78.47% and 0.533, respectively. Permutation importance found that the top risk signals were recent repayment status, the number of delinquent months, and the maximum number of missed months. Monotonic default rates from 6.11% to 51.28% were achieved using risk bands derived from training for interpretable strategic segmentation for credit-risk management.
Zitieren
APA
N, V. S. V., Reddy, D. R. R., K, D. R. H., K, D. S., Govindan, D. V., & Sathyakala, D. S. (2026). Artificial Intelligence–Driven Decision Intelligence in Banking and FinTech: Predictive Analytics for Financial Risk, Customer Behaviour, and Strategic Management. Computer and Decision Making An International Journal. https://doi.org/10.1922/comdem.v3i6s.19006
Vancouver
N VSV, Reddy DRR, K DRH, K DS, Govindan DV, Sathyakala DS. Artificial Intelligence–Driven Decision Intelligence in Banking and FinTech: Predictive Analytics for Financial Risk, Customer Behaviour, and Strategic Management. Computer and Decision Making An International Journal. 2026. doi:10.1922/comdem.v3i6s.19006
BibTeX
@article{N2026,
author = {N, Vishweswar sastry V and Reddy, Dr. Rajidi Rammohan and K, Dr Renushree H and K, Dr Shailashree and Govindan, Dr. Vishnu and Sathyakala, Dr S},
title = {Artificial Intelligence–Driven Decision Intelligence in Banking and FinTech: Predictive Analytics for Financial Risk, Customer Behaviour, and Strategic Management},
journal = {Computer and Decision Making An International Journal},
year = {2026},
doi = {10.1922/comdem.v3i6s.19006}
}
EUVIMED