Published Paper Details:

Predicting stock prices accurately remains a challenging task, driving continuous research efforts in leveraging various machine learning, deep learning, and statistical analysis techniques. This paper presents a comparative study of four different models BiLSTM, GRU, CNN-LSTM, and ARIMA for stock price forecasting, using data from the S&P 500 index and five prominent technology companies: Meta, Apple, Google, Netflix, and Amazon. The study aims to identify the most effective model for maximising returns on investment in stock trading by forecasting future trends. Leveraging a dataset sourced from Yahoo Finance, comprising historical stock market data, we evaluate the performance of each model based on error metrics such as , Mean Squared Error (MSE), Root Mean Square Error (RMSE) and Mean Absolute Error (MAE). The research findings highlight the strengths and weaknesses of each model in accurately predicting stock prices. Lower RMSE values indicate higher accuracy in predicting stock prices, guiding investors towards more informed decision-making. Through this comparative analysis, investors can identify the optimal model for stock price forecasting, thus enhancing their investment strategies and maximising returns.