DESIGN AND IMPLEMENTATION OF AN AI-DRIVEN PERSONAL FINANCE TRACKING SYSTEM
Abstract
This study details the design and implementation of an AI-driven personal finance tracking
system developed to address limitations in traditional financial management. The project utilized
a modern web stack, including Next.js, TypeScript, Tailwind CSS, and a PostgreSQL database
managed by Supabase with Drizzle ORM. A core component involved integrating the OpenAI
API (GPT-4) for intelligent financial analysis of uploaded PDF bank statements. The
implementation results demonstrate the system's efficiency in processing financial data and high
accuracy in transaction categorization, providing users with clear financial summaries and
actionable recommendations. While challenges related to edge-case PDF formats, AI accuracy
with ambiguous data, and Next.js component distinctions were encountered, the project
successfully achieved its objectives, offering a user-friendly and intelligent solution for
enhancing personal financial literacy and management.
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.