DEVELOPMENT OF A FINANCIAL ASSISTANCE AND BUDGETING CHATBOT
Abstract
This project presents the design, development, and evaluation of a web-based Financial
Assistance and Budgeting Chatbot powered by conversational artificial intelligence. The
system was developed to address the growing need for accessible, real-time financial
guidance among individuals, particularly those with limited financial literacy or access to
professional advisory services. Leveraging Natural Language Processing (NLP) and the
Gemini API, the chatbot provides personalized budgeting tips, spending analysis, and
financial literacy support in a conversational format. The frontend was implemented using
React, Next.js, and Tailwind CSS. The system architecture emphasizes modularity,
scalability, and user privacy.
A comprehensive literature review highlights the increasing adoption of chatbots by financial
institutions and identifies key challenges such as data security, regulatory compliance, and
explainability. Using a design-science methodology, the chatbot was iteratively developed,
tested, and refined. Functional and usability testing confirmed that the chatbot could
successfully interpret user inputs, deliver relevant responses, and provide an intuitive user
experience. The final system includes a landing page, a resources section, and a chat interface
that allows users to interact seamlessly with the AI assistant.
This work demonstrates the potential of conversational AI in promoting financial literacy and
self-service budgeting. It contributes to the growing body of research on AI applications in
finance and offers a blueprint for building secure, scalable, and user-centered financial
chatbot solutions.
Full-Text Access Notice
In accordance with the NERD Policy on promoting peer-reviewed publication, public access to the full text of a project, thesis or dissertation is restricted for three years, allowing the author and supervisors sufficient time to pursue peer-reviewed publication.
During this period, researchers with legitimate academic or research purposes may request authorisation directly from the author to enable NERD to release the indexed full texts of the work using the form below.