Abstract :

The Increasing Demand For Instant And Reliable Customer Support Has Encouraged Financial Institutions To Adopt Intelligent Conversational Systems That Can Provide Continuous Assistance With Minimal Human Intervention. This Paper Presents A Machine Learning-based Banking Chatbot Designed To Answer Customer Queries Related To Banking Services Through An Interactive Web Application. The Proposed System Employs Natural Language Processing Techniques To Interpret User Questions And Predicts The Most Relevant Response Using Supervised Learning Algorithms Trained On A Banking Question– Answer Dataset. To Identify The Most Effective Classification Model, The Performance Of Random Forest, Support Vector Machine (SVM), And KNearest Neighbors (KNN) Algorithms Is Evaluated Using Standard Performance Metrics. Experimental Results Indicate That The Random Forest Classifier Achieves The Highest Prediction Accuracy Among The Evaluated Models, Making It Suitable For Real-time Banking Assistance. The Application Includes Separate Interfaces For Administrators And Users, Allowing Administrators To Manage User Accounts, Train Machine Learning Models, And Monitor Chatbot Interactions, While Registered Users Can Securely Access The Chatbot To Obtain Banking-related Information. The System Also Records User Interactions For Future Analysis And Continuous Improvement Of Response Quality. The Developed Solution Demonstrates That Integrating Machine Learning With Conversational Interfaces Can Significantly Enhance Customer Support By Providing Accurate, Responsive, And Accessible Banking Assistance. The Proposed Framework Offers A Practical, Scalable, And Cost-effective Approach For Improving Digital Customer Service In Modern Banking Environments.

Published:

30-7-2026

Issue:

Vol. 26 No. 7 (2026)

Page Nos:

1386-1393

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite