PREDIKSI TREND PERUBAHAN HARGA PADA SAHAM-SAHAM SYARIAH BURSA EFEK INDONESIA MENGGUNAKAN METODE SUPPORT VECTOR MACHINE

ALKAUTSAR, MUHAMMAD ZUFAR and Primartha, Rifkie (2023) PREDIKSI TREND PERUBAHAN HARGA PADA SAHAM-SAHAM SYARIAH BURSA EFEK INDONESIA MENGGUNAKAN METODE SUPPORT VECTOR MACHINE. Undergraduate thesis, Sriwijaya University.

	Text RAMA_55201_09021281823073.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_55201_09021281823073_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (11MB) | Request a copy
	Text RAMA_55201_09021281823073_0001067709_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB)
	Text RAMA_55201_09021281823073_0001067709_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (261kB) | Request a copy
	Text RAMA_55201_09021281823073_0001067709_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (240kB) | Request a copy
	Text RAMA_55201_09021281823073_0001067709_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021281823073_0001067709_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021281823073_0001067709_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (10kB) | Request a copy
	Text RAMA_55201_09021281823073_0001067709_07_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (87kB) | Request a copy
	Text RAMA_55201_09021281823073_0001067709_08_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (314kB) | Request a copy

Abstract

Stocks have high risks. Due to the high risks of stocks, investors can perform technical analysis before making decisions in buying and selling stocks. Technical analysis is done by using technical indicators, such as Moving Average Convergence Divergence (MACD), Exponential Moving Average (EMA), and Relative Strength Index (RSI). Machine learning methods can be used to perform technical analysis automatically, one of which is the Support Vector Machine (SVM) method. Company stocks data that were listed in the Jakarta Islamic Index (JII) for the period December 2022 to May 2023 were collected in advance. The range of data used is from January 2, 2020 to December 30, 2022. Then, the stock data will be transformed with pre-processing, and then a feature selection process using the Principal Component Analysis (PCA) method will be applied to reduce the dimension of the stock data. The data will be separated into training data and test data. After that, the training process will be performed with SVM and followed with the evaluation process to find the best model from the study. The results from this study indicate that SVM can be used to predict the price change trends in Islamic stocks, with the best performance achieved is accuracy of 93.19%, recall of 98.82%, precision of 90.32%, and f1-score of 94.38%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Prediksi Trend, Saham Syariah, Principal Component Analysis, Support Vector Machine
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Muhammad Zufar Alkautsar
Date Deposited:	09 Aug 2023 06:56
Last Modified:	09 Aug 2023 06:56
URI:	http://repository.unsri.ac.id/id/eprint/126485

Actions (login required)

View Item