Prediction of Stock Market Movement Using Long Short-Term Memory (LSTM) Artificial Neural Network: Analysis of KSE 100 Index
Atif Khan Jadoon
Tariq Mahmood
Ambreen Sarwar
Maria Faiq Javaid
Munawar Iqbal
Predicting the movement of the stock price index has remained a challenging task for financial analysts. They are complex, given how the nation's economic, social, and political conditions affect stock market predictions. The present study is designed to build an efficient model using machine learning and taking monthly data from February 2004 to December 2020. Long- and short-term memory and backpropagation methods of an artificial neural network are utilized to predict the Karachi Stock Exchange (KSE) movement by using twenty-six economic, social, political, and administrative indicators. The model developed in this study to predict the movement of the KSE 100 index gained 99 percent accuracy. The predictions' results showed that the KSE 100 index would remain stagnant at around 40,000 points till September 2023. We compared actual and predicted values from January 2021 to July 2022 to validate our developed model. The results showed that the model developed in this study could be used to forecast stock market trends. The research predicted the KSE 100 index with 99% accuracy using LSTM and backpropagation in a neural network. The KSE 100 should stay around 40,000 points until September 2023. Despite their promise, machine learning forecasts in financial markets require continuing research, market dynamics evaluation, and liability disclosure. A thorough validation procedure and the most recent KSE 100 index prediction using LSTM and backpropagation algorithms demonstrate how machine learning may improve stock market forecasting. The study's accurate projections and consistent data through September 2023 are crucial for investors and inancial experts in the Karachi Stock Exchange's changing environment.
Keywords:Artificial Neural Network (ANN), Backpropagation algorithm, KSE 100 index, Karachi stock exchange, Long Short-Term Memory (LSTM), Pakistan
