Stock Price Prediction Using LSTM And GRU

Stock price prediction has been challenging and essential task in the part of financial forecasting.As the rise of learning models, researchers have explored various architecture, like Long ShortTerm Memory (LSTM) and Gated Recurrent Unit (GRU) for predict stock market trends.This paper presents a comparative study between LSTM and GRU models applied to IBM stock price data.The dataset used spans from 2006 to 2018, and various preprocessing techniques have been employed to enhance model performance.Evaluation metrics such as Root Mean Squared Error (RMSE) is used for prediction accuracy.The results highlight the effectiveness of deep learning models in financial time series forecasting, providing insights into their strengths and weaknesses.