Pahlawan, Muhammad Reza (2022) Prediksi Indeks Harga Saham Berdasarkan Indikator Teknikal Dan Berita Sentimen Menggunakan Model Pembelajaran Ensemble Berbasis Jaringan Saraf Recurrent Dan Algoritma Genetika. Masters thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 6026201019-Master_Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
6026201019-Master_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2024. Download (2MB) | Request a copy |
Abstract
Indeks harga saham merupakan salah satu faktor penting dalam merepresentasikan kinerja kondisi ekonomi suatu negara. Kinerja tersebut seringkali menjadi landasan bagi investor untuk berinvestasi saham. Oleh karena itu, model prediksi diperlukan untuk membantu dalam melakukan analisis pergerakan nilai ke depannya. Analisis strategi diperlukan karena harga saham seringkali dipengaruhi oleh berbagai faktor sehingga membuatnya fluktuatif. Penelitian ini bertujuan mengembangkan model prediksi saham berdasarkan berbagai faktor seperti data historis harga saham, indikator teknikal, dan analisis berita sentimen menggunakan model ensemble learning berdasarkan metode Recurrent Neural Network (RNN) yang dioptimasi menggunakan metode Genetic Algorithm (GA). Hasil penggunaan model tersebut menghasilkan kinerja yang lebih baik hingga 75% dari model dasar. Penambahan variabel indikator teknikal dan sentiment juga mampu meningkatkan kinerja model sebesar 4% daripada penggunaan harga saham saja dimana hal tersebut mengindikasikan bahwa kedua variabel tersebut berpengaruh terhadap harga saham.
=============================================================================================================================
The stock price index is one of the important factors in representing the performance of a country's economic conditions. This performance is often the basis for investors to invest in stocks. Therefore, predictive models are needed to assist in analyzing future value movements. Strategy analysis is needed because stock prices are often influenced by various factors that make them fluctuate. This study aims to develop a stock prediction model based on various factors such as historical stock price data, technical indicators, and news sentiment analysis using an ensemble learning model based on the Recurrent Neural Network (RNN) method which is optimized using the Genetic Algorithm (GA) method. The results of using this model produce up to 75% better performance than the basic model. The addition of technical indicators and sentiment variables is also able to increase the performance of the model by 4% more than the use of stock prices alone, which indicates that these two variables have an effect on stock prices.
| Item Type: | Thesis (Masters) |
|---|---|
| Uncontrolled Keywords: | analisis sentimen, ensemble learning, investasi, peramalan saham, RNN, sentiment analysis, ensemble learning, invest, stock forecasting |
| Subjects: | Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines. Q Science > QA Mathematics > QA276 Mathematical statistics. Time-series analysis. Failure time data analysis. Survival analysis (Biometry) Q Science > QA Mathematics > QA76.9.D343 Data mining. Querying (Computer science) |
| Divisions: | Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Information System > 59101-(S2) Master Thesis |
| Depositing User: | Muhammad Reza Pahlawan |
| Date Deposited: | 16 Nov 2022 08:59 |
| Last Modified: | 29 Nov 2022 01:35 |
| URI: | http://repository.its.ac.id/id/eprint/95097 |
Actions (login required)
 |
View Item |