IRMA-International.org: Creator of Knowledge
Information Resources Management Association
Advancing the Concepts & Practices of Information Resources Management in Modern Organizations

Empowering Sustainable Recommendations in Retail Banking Using Explainable AI

Empowering Sustainable Recommendations in Retail Banking Using Explainable AI
View Sample PDF
Author(s): Shrey Arora (Symbiosis Centre for Information Technology, Symbiosis International University, Pune, India), Souvik Purakayastha (Symbiosis Centre for Information Technology, Symbiosis International University, Pune, India)and Ajey Kumar (Symbiosis Centre for Information Technology, Symbiosis International University, Pune, India)
Copyright: 2025
Pages: 20
Source title: Organizational Risks, Challenges, and Barriers in Developing Sustainability Start-Ups
Source Author(s)/Editor(s): Kyla Latrice Tennin (College of Doctoral Studies, University of Phoenix, USA)and A. B. Mishra (International Institute of Management Studies, Pune, India)
DOI: 10.4018/978-1-6684-9872-9.ch008

Purchase

View Empowering Sustainable Recommendations in Retail Banking Using Explainable AI on the publisher's website for pricing and purchasing information.

Abstract

This research explores the pivotal role of Explainable AI (XAI) in enhancing transparency, trust, and decision-making processes within personalized retail banking recommendation systems. Leveraging methodologies from popular XAI library packages, including LIME, SHAP, Yellowbrick, ELI5, and Alibi, a profound examination of machine learning models was conducted to comprehend and validate recommendations. The collaborative insights of these XAI techniques led to the identification and removal of a detrimental feature, significantly improving model accuracy and precision. Graphical representations and analyses provided by these methods guided model refinement strategies, exemplifying the power of XAI in promoting both accuracy and interpretability in the decision-making process. Despite challenges related to data complexity and reliance on synthetic data, this research contributes valuable insights to the potential of XAI in retail banking recommendation systems, emphasizing future avenues for exploration and refinement.

Related Content

Aditi Nag. © 2026. 48 pages.
Mayur Thakur, Shikha Sharma, Trilochan Kumar. © 2026. 44 pages.
Partha Mukhopadhyay, Prachee Parwanee. © 2026. 36 pages.
Kamaraj Kalaimathy, Chathana Thagavel, Sofiya M. Karunanithi. © 2026. 30 pages.
İlhami Ay, Murat Dal. © 2026. 34 pages.
Vinupandyan Lakshmanan. © 2026. 32 pages.
Muhammad Usman Tariq. © 2026. 28 pages.
Body Bottom