Comparison of Extreme Learning Machine Methods and Support Vector Regression for Predicting Bank Share Prices in Indonesia

Setiadi, Williem Kevin and Prasetyo, Vincentius Riandaru and Kartikasari, Fitri Dwi (2024) Comparison of Extreme Learning Machine Methods and Support Vector Regression for Predicting Bank Share Prices in Indonesia. Jurnal Teknika, 13 (2). pp. 219-225. ISSN 2549-8037, E-ISSN 2549-8045

PDF Vincent_Teknika_Juli 2024 [Full].pdf - Published Version Download (21MB)

Abstract

Investing is the practice of postponing current consumption to obtain more significant value in the future. One profitable form of investment is stock investment, where investors buy company shares to benefit from appreciation in share value or dividend payments. Before investing in shares, investors need to pay attention to movements in the Composite Stock Price Index (IHSG), which reflects the performance of the Indonesian stock market. The Indonesian Stock Exchange (BEI) recorded around 740 companies listed in 2021. The BEI also compiled the LQ45 list of 45 stocks with the largest market capitalization, including the four largest banks in Indonesia. However, investing in bank shares only sometimes produces profits due to share price fluctuations. Stock price analysis and price movement predictions are important steps before investing. Extreme Learning Machine (ELM) and Support Vector Regression (SVR) methods are techniques used to predict time series data. This research compares the performance of the two methods in predicting stock prices of the big 4 Indonesian banks. The dataset used in this research comes from the Yahoo Finance site, which was taken since the market crash recovery period due to the Covid-19 pandemic. Based on the evaluation conducted, both the ELM and SVR methods are effective for predicting the share prices of the big four Indonesian banks. The average MAPE for the ELM method is 8.5% and SVR is 2.64%. However, when considering computing time, the ELM method is more efficient with an average computing time of 0.006 seconds, than the SVR method with an average computing time of 0.694 seconds.

Item Type:	Article
Uncontrolled Keywords:	Extreme Learning Machine, Support Vector Regression, Stocks Prediction, Banking Indonesia, MAPE
Subjects:	H Social Sciences > HJ Public Finance Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software
Divisions:	Faculty of Engineering > Department of Informatic
Depositing User:	VINCENTIUS RIANDARU PRASETYO
Date Deposited:	12 Jul 2024 02:00
Last Modified:	12 Jul 2024 02:00
URI:	http://repository.ubaya.ac.id/id/eprint/46706

Actions (login required)

View Item