Stock Market Prediction Using Recurrent Neural Network and LSTM

Abstract

Stock market prediction is a highly challenging task due to the inherent volatility and non-linear nature of financial markets, often rendering traditional forecasting methods ineffective. To overcome these limitations, this paper explores the application of advanced deep learning techniques, specifically Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) models, for predicting future stock prices. The study evaluates the predictive accuracy of these models and examines the effect of varying training epochs on their performance, using American Airlines stock data as a case study.