T. M. Busu, Saadi Ahmad Kamarudin, N. Ahad, Norazlina Mamat
{"title":"Prediction of FTSE Bursa Malaysia KLCI Stock Market using LSTM Recurrent Neural Network","authors":"T. M. Busu, Saadi Ahmad Kamarudin, N. Ahad, Norazlina Mamat","doi":"10.1109/ICOCO56118.2022.10031901","DOIUrl":null,"url":null,"abstract":"Stock market prediction is vital in the financial world. Investors and people interested in investing would be interested in the future value of the stock market before they invest in it. By using the method of time series, this research gives a contribution to forecast and modelling the FTSE Bursa Malaysia KLCI (FBM KLCI) stock market. In this research, the stock market is forecasted to identify the stock market trend in the future. The FBM KLCI closing prices data was utilized to build Long Short-Term Memory (LSTM) models to predict the stock market. The performance of the model has been evaluated using the root mean squared error (RMSE) and the mean absolute error (MAE) in order to choose the best model. The researcher used the Bursa Malaysia data to forecast the stock market for five years, from October 20, 2016, to October 20, 2021, which has been scrapped from the Yahoo Finance website. The data is analyzed by running Python coding in Google Colab. The result proves that the accuration of the LSTM model by using Recurrent Neural Network (RNN) approach is accurate and the predicted value of the stock market at the date 2021-10-05 is increased by 1.87%. It can be used to predict the future closing stock prices in stock market prediction in FBM KLCI stock market. The results are expected to provide an accurate prediction for a better profit. Thus, prediction in stock market investment can support long-term economic growth, or in other words, it can help economic sustainability.","PeriodicalId":319652,"journal":{"name":"2022 IEEE International Conference on Computing (ICOCO)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE International Conference on Computing (ICOCO)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICOCO56118.2022.10031901","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Stock market prediction is vital in the financial world. Investors and people interested in investing would be interested in the future value of the stock market before they invest in it. By using the method of time series, this research gives a contribution to forecast and modelling the FTSE Bursa Malaysia KLCI (FBM KLCI) stock market. In this research, the stock market is forecasted to identify the stock market trend in the future. The FBM KLCI closing prices data was utilized to build Long Short-Term Memory (LSTM) models to predict the stock market. The performance of the model has been evaluated using the root mean squared error (RMSE) and the mean absolute error (MAE) in order to choose the best model. The researcher used the Bursa Malaysia data to forecast the stock market for five years, from October 20, 2016, to October 20, 2021, which has been scrapped from the Yahoo Finance website. The data is analyzed by running Python coding in Google Colab. The result proves that the accuration of the LSTM model by using Recurrent Neural Network (RNN) approach is accurate and the predicted value of the stock market at the date 2021-10-05 is increased by 1.87%. It can be used to predict the future closing stock prices in stock market prediction in FBM KLCI stock market. The results are expected to provide an accurate prediction for a better profit. Thus, prediction in stock market investment can support long-term economic growth, or in other words, it can help economic sustainability.