Comparative Analysis of ARIMA and LSTM Models for Stock Price Prediction

Stock price prediction is crucial for informed investment decisions, enabling investors to maximize returns and manage risks effectively in the dynamic and complex world of financial markets. It also aids in portfolio management and financial planning by providing insights into future market movements and asset valuations. This study delves into the intriguing realm of stock price prediction using two models, Auto-Regressive Integrated Moving Average (ARIMA) and Long Short-Term Memory (LSTM) networks, leveraging the efficient market hypothesis framework. Analyzing historical market data for Apple, Google, and Tesla, ARIMA and LSTM models are independently developed to forecast closing stock values. The research compares the forecasting accuracy of each model through Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE) assessment, aiming to provide insights into their distinct strengths. The findings offer nuanced perspectives on the predictive performance of ARIMA and LSTM models in stock price behavior.