FinGenie: Design and Implementation of an AI-Assisted Financial Literacy Platform for Adolescents

Abstract: Financial illiteracy among teenagers continues to be a major challenge in education systems around the world. A large number of young people step into adult financial life with little to no understanding of how money actually works. This paper presents the design, development, and real-world evaluation of FinGenie — a locally hosted, AI-powered web application built specifically to help learners between the ages of 13 and 19 develop meaningful financial skills. Rather than relying on third-party cloud services, FinGenie uses on-device language models to power a Retrieval-Augmented Generation (RAG) chatbot, protecting user privacy while still delivering intelligent, personalized responses. The platform also includes structured learning modules, gamified elements like quests and badges, and hands-on tools such as a digital wallet and goal tracker. Built on a React–TypeScript frontend and an Express-based RESTful backend with the Ollama inference runtime, the system was tested with 150 adolescent users over an eight-week period. Results showed a 26- percentage-point increase in financial knowledge scores, an 84% retention rate at the 30-day mark, and an overall satisfaction rating of 87%. These outcomes suggest that well-designed educational technology — when combined with responsible AI use and strong pedagogical foundations — can produce real, lasting improvements in financial capability for teenage users.

Keywords: Financial literacy, adolescent education, Retrieval-Augmented Generation, local AI, gamification, React, Node.js, Ollama, educational technology, privacy-first design