EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Explainable Artificial Intelligence and Machine Learning for Intelligent Business Decision-Making: A Predictive Analytics Framework

Kanimozhi. M, Faseeha Begum, Aravind Sivaraj, P.Balaji, Dr Priyanka Bhatt, Dr. MAHESH TUBAKI

Computer and Decision Making: An International Journal · 04.11.2026 · 3 (6S) · 3835-3843

DOI: 10.1922/comdem.v3i6s.19059 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer and Decision Making: An International Journal, online erschienen am 04.11.2026. Verfasst von Kanimozhi. M und 5 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The study proposes and tests an explainable artificial intelligence (XAI) powered machine learning solution for intelligent business decision-making with a dataset from a bank marketing system with 16 predictors, a binary term-deposit subscription label and 45,211 customer observations. The study utilizes a quantitative predictive analytics design that combines logistic regression, decision tree, random forest, XGBoost and support vector machine models, with model explainability provided by SHAP. To enhance operational validity, the main decision support model does not include contact duration as a variable since that information is not available prior to the end of the customer interaction. The results indicate that XGBoost had the best overall discrimination with an ROC AUC of 0.803 and PR AUC of 0.465, while Random Forest had the highest accuracy and F1-score. The contact type, prior campaign success, cellular communication, account balance, contact day, age, housing-loan status, and campaign intensity were found to be important factors influencing subscription propensity, as per SHAP analysis. The results show that predictive accuracy along with interpretable explanations can help prioritize customers, target campaigns more efficiently, as well as provide clear managerial decision support. The proposed framework thus connects the business data, predictive ML, explainable AI, actionable intelligence and managerial decision-making actions within a single path towards intelligent business decision-making.

Zitieren

APA

M, K., Begum, F., Sivaraj, A., P.Balaji, Bhatt, D. P., & TUBAKI, D. M. (2026). Explainable Artificial Intelligence and Machine Learning for Intelligent Business Decision-Making: A Predictive Analytics Framework. Computer and Decision Making: An International Journal, 3(6S), 3835-3843. https://doi.org/10.1922/comdem.v3i6s.19059

Vancouver

M K, Begum F, Sivaraj A, P.Balaji, Bhatt DP, TUBAKI DM. Explainable Artificial Intelligence and Machine Learning for Intelligent Business Decision-Making: A Predictive Analytics Framework. Computer and Decision Making: An International Journal. 2026;3(6S):3835-3843. doi:10.1922/comdem.v3i6s.19059

BibTeX
@article{M2026,
  author = {M, Kanimozhi. and Begum, Faseeha and Sivaraj, Aravind and P.Balaji and Bhatt, Dr Priyanka and TUBAKI, Dr. MAHESH},
  title = {Explainable Artificial Intelligence and Machine Learning for Intelligent Business Decision-Making: A Predictive Analytics Framework},
  journal = {Computer and Decision Making: An International Journal},
  year = {2026},
  volume = {3},
  number = {6S},
  pages = {3835--3843},
  doi = {10.1922/comdem.v3i6s.19059}
}
Kostenlos starten →