The Role of AI Chatbots in Enhancing Efficiency and Customer Experience in Banking Call Centers

Cai, Qingyun (2025) The Role of AI Chatbots in Enhancing Efficiency and Customer Experience in Banking Call Centers. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (913kB) | Preview
Preview	PDF (Configuration Manual) Download (856kB) | Preview

Abstract

The infusion of AI into the Banking sector has had a substantial influence on customer service, notably with the emergence of AI Chatbots. This research initiative focused on the creation, deployment, and evaluation of PrimeBank AI Assistant, a Rule-Based Banking Chatbot developed to enhance efficiency and optimize customer experience in Digital Banking Services. The chatbot has been developed using standard web technologies like HTML, CSS and JavaScript on a modular and Client-side architecture ensuring that the chatbot is secure, responsive and does not store sensitive information about the users.

The aim of overarching this project was to learn about and apply Rule Based Chatbot Systems that can mimic the real-world application and can support Banking and support users with relevant questions as well as usability on any device. We compiled a 1000 Q&A Pair Dataset to train and better enable our chatbot's logic. We used three real-world case studies to test its capabilities against 3 important and common challenges in chatbot design: conversation context, culturally/emotionally sensible responses and Regulatory Compliance with multi-chat session history. Iterative improvements to the design were made to effectively solve each challenge and demonstrate the chatbot's growing ability.

The result of the project shows that the basic rule-based AI assistants can be improved using the concepts of structured logic and user-oriented design approaches. In addition, the success of the chatbot in this project also opens the doors for more seamless integration with NLP (Natural Language Processing) framework in the future, to have more automated and smarter support and financial solutions. In this report, we have discussed methodology, design, implementation and case study-based evaluations to explore various ways to build secure, scalable and context aware chatbots for
the banking industry.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Del Rosal, Victor UNSPECIFIED
Subjects:	Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence H Social Sciences > HG Finance > Banking P Language and Literature > P Philology. Linguistics > Computational linguistics. Natural language processing H Social Sciences > HF Commerce > Customer Service H Social Sciences > HG Finance > Fintech T Technology > T Technology (General) > Information Technology > Fintech
Divisions:	School of Computing > Master of Science in FinTech
Depositing User:	Ciara O'Brien
Date Deposited:	20 Aug 2026 10:28
Last Modified:	20 Aug 2026 10:29
URI:	https://norma.ncirl.ie/id/eprint/9566

Actions (login required)

View Item