ChiFeng TanXinYing ChewKhaiWah KhawWeiLin TeohZhiLin Chong2026-11-062026-11-062026-04-0210.32802/asmscj.2026.0077https://dspace-cris.utar.edu.my/handle/123456789/11863Rapid advances in big data analytics, machine learning (ML), and deep learning (DL) have transformed algorithmic trading (AT), enabling more accurate prediction of market trends and price movements. Once limited by technological constraints, AT is now widely adopted, with a large share of daily trading volume executed by hedge funds, insurance companies, and investment banks using proprietary algorithms. This institutional dominance has concentrated resources and innovation within large corporations, creating barriers that limit access to advanced trading tools for individual investors. This paper addresses this imbalance by proposing a user-centric, open-source algorithmic trading platform designed to democratise access to sophisticated trading technologies. The system integrates a custom-built deep learning model that analyses historical stock data alongside news sentiment to improve trading predictions. The trading infrastructure is implemented using the open-source QuantConnect framework, while decision-making is driven by DL and sentiment analysis techniques. The application was designed, deployed, and rigorously evaluated using standard software performance metrics. Results demonstrate that the proposed system enhances accessibility to state-of-the-art trading strategies, empowering individual investors and promoting a more inclusive, competitive, and innovative stock trading ecosystem. © 2026 Akademi Sains Malaysia. All rights reserved.en-USdeep learninginvestorsopen-sourceQuantConnectstock analysisDesigning a Cutting-Edge User-Centric Algorithmic Trading Platform with QuantConnect and Deep Learningjournal-article