Stock market prediction of Bangladesh using multivariate long short-term memory with sentiment identification

Q2 Computer Science

International Journal of Electrical and Computer Engineering Pub Date : 2023-10-01 DOI:10.11591/ijece.v13i5.pp5696-5706

Md. Ashraful Islam, Md. Rana Sikder, Sayed Mohammed Ishtiaq, A. Sattar

{"title":"Stock market prediction of Bangladesh using multivariate long short-term memory with sentiment identification","authors":"Md. Ashraful Islam, Md. Rana Sikder, Sayed Mohammed Ishtiaq, A. Sattar","doi":"10.11591/ijece.v13i5.pp5696-5706","DOIUrl":null,"url":null,"abstract":"The prediction of stock market trends is a challenging task due to its dynamic and volatile nature. Research has shown that predicting the stock market, especially in developing nations like Bangladesh, is challenging due to the presence of multiple external factors in addition to technical ones. To address this, this study proposed a novel dataset that includes not only technical stock market data from 2014 to 2021, but also external factors such as news sentiment and other economic indicators like inflation, gross domestic product (GDP), exchange rate, interest rate, and current balance. The goal is to provide a comprehensive view of the Dhaka Stock Exchange (DSE), the largest stock market in Bangladesh. The main objective of this study is to predict the trend of DSE by taking into account both technical stock market data and relevant external factors, and to compare the predictions made with and without using external factors. The study utilized a multivariate long short-term memory (LSTM) neural network for the stock market trend prediction. The experimental results showed that the use of external factors improved the accuracy of the LSTM-based stock market trend predictions by approximately 24%.","PeriodicalId":38060,"journal":{"name":"International Journal of Electrical and Computer Engineering","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Electrical and Computer Engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.11591/ijece.v13i5.pp5696-5706","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"Computer Science","Score":null,"Total":0}

引用次数: 0

Abstract

The prediction of stock market trends is a challenging task due to its dynamic and volatile nature. Research has shown that predicting the stock market, especially in developing nations like Bangladesh, is challenging due to the presence of multiple external factors in addition to technical ones. To address this, this study proposed a novel dataset that includes not only technical stock market data from 2014 to 2021, but also external factors such as news sentiment and other economic indicators like inflation, gross domestic product (GDP), exchange rate, interest rate, and current balance. The goal is to provide a comprehensive view of the Dhaka Stock Exchange (DSE), the largest stock market in Bangladesh. The main objective of this study is to predict the trend of DSE by taking into account both technical stock market data and relevant external factors, and to compare the predictions made with and without using external factors. The study utilized a multivariate long short-term memory (LSTM) neural network for the stock market trend prediction. The experimental results showed that the use of external factors improved the accuracy of the LSTM-based stock market trend predictions by approximately 24%.

查看原文本刊更多论文

基于多变量长短期记忆和情绪识别的孟加拉股市预测

由于股票市场的动态性和波动性，预测股票市场趋势是一项具有挑战性的任务。研究表明，预测股市，特别是在孟加拉国等发展中国家，具有挑战性，因为除了技术因素外，还存在多种外部因素。为了解决这一问题，本研究提出了一个新的数据集，该数据集不仅包括2014年至2021年的技术性股市数据，还包括外部因素，如新闻情绪和其他经济指标，如通货膨胀、国内生产总值、汇率、利率和当前余额。目标是全面了解孟加拉国最大的股票市场达卡证券交易所（DSE）。本研究的主要目的是通过考虑股票市场技术数据和相关外部因素来预测DSE的趋势，并比较使用和不使用外部因素的预测。该研究利用多元长短期记忆（LSTM）神经网络进行股市趋势预测。实验结果表明，外部因素的使用将基于LSTM的股市趋势预测的准确性提高了约24%。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

International Journal of Electrical and Computer Engineering Computer Science-Computer Science (all)

CiteScore

4.10

自引率

0.00%

发文量

177

期刊介绍： International Journal of Electrical and Computer Engineering (IJECE) is the official publication of the Institute of Advanced Engineering and Science (IAES). The journal is open to submission from scholars and experts in the wide areas of electrical, electronics, instrumentation, control, telecommunication and computer engineering from the global world. The journal publishes original papers in the field of electrical, computer and informatics engineering which covers, but not limited to, the following scope: -Electronics: Electronic Materials, Microelectronic System, Design and Implementation of Application Specific Integrated Circuits (ASIC), VLSI Design, System-on-a-Chip (SoC) and Electronic Instrumentation Using CAD Tools, digital signal & data Processing, , Biomedical Transducers and instrumentation, Medical Imaging Equipment and Techniques, Biomedical Imaging and Image Processing, Biomechanics and Rehabilitation Engineering, Biomaterials and Drug Delivery Systems; -Electrical: Electrical Engineering Materials, Electric Power Generation, Transmission and Distribution, Power Electronics, Power Quality, Power Economic, FACTS, Renewable Energy, Electric Traction, Electromagnetic Compatibility, High Voltage Insulation Technologies, High Voltage Apparatuses, Lightning Detection and Protection, Power System Analysis, SCADA, Electrical Measurements; -Telecommunication: Modulation and Signal Processing for Telecommunication, Information Theory and Coding, Antenna and Wave Propagation, Wireless and Mobile Communications, Radio Communication, Communication Electronics and Microwave, Radar Imaging, Distributed Platform, Communication Network and Systems, Telematics Services and Security Network; -Control[...] -Computer and Informatics[...]