Project Abstract

With the rapid rise of young and first-time investors entering the stock market through accessible trading platforms, there’s an urgent need for tools that prioritize education over speculation. Many new traders rely on social media or unverified advice, often resulting in poor financial decisions. This project addresses that gap by proposing a web-based application that combines deep learning and data visualization to support responsible trading. Its unique focus lies in using LSTM (Long Short-Term Memory) models for stock price prediction while presenting insights through interactive, intuitive charts tailored to novice users. The main research question centers on whether combining time-series prediction with educational visualization can improve market literacy and decision-making in casual investors. The study follows a structured software development lifecycle (SDLC), beginning with user-driven requirement gathering and culminating in full-stack implementation. The backend, built with FastAPI and Python, handles data retrieval and LSTM-based predictions using historical stock data. The frontend, developed in Laravel with PHP, connects to the backend and presents users with prediction results alongside dynamic visualizations built with Chart.js. Key outcomes include a functional system capable of predicting next-day stock prices based on the previous 60 days and displaying these alongside actual trends for user comparison. Initial testing reveals that integrating predictions into a visual learning environment helps users better understand market behaviour, especially when simplified through chart overlays and real-time feedback. The system successfully demonstrates that deep learning models like LSTM can be made approachable for non-expert audiences through thoughtful UI design. This research contributes a blueprint for building AI-powered financial education tools that are accessible, interactive, and tailored to the needs of emerging investors, bridging a crucial gap between data science and public financial literacy.

Keywords: Data analytics, Machine learning, Data visualisation

 Conference Details

Session: A

Location: Sir Stanley Clarke Auditorium at 11:00 13:00

Markers: Benjamin Mora, Arnold Beckmann

Course: BSc Computer Science 3yr FT

Future Plans: I’m looking for work