Performance Comparison of LSTM and SVR Models in Predicting Stock Prices

Abstract

There were many models developed for predicting random and complicated stock price. Over past years, many researches were taking interest in stock price prediction. Deep learning techniques were used for better predicting of stock prices. In this paper, Long Short-Term Memory (LSTM) and Support Vector Regressor (SVR) model is used to predict Meta, Amazon, Apple, Netflix &Google (MAANG) companies stock prices, we used 6 years data from Dec 2017 to Dec 2022 from which we found that LSTM model provides better accuracy by comparing both results of Root Mean Squared Error (RMSE) & Mean Absolute Error (MAE) values.