Sufyaan, Muhammad Khairii (2024) Prediksi Harga Saham Berdasarkan Judul Berita dan Informasi Emiten Menggunakan Support Vector Machine, Long-Short Term Memory, dan Gated Recurrent Unit. Other thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 5003201077-Undergraduate_Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
5003201077-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2026. Download (2MB) | Request a copy |
Abstract
Pasar saham yang dinamis dan kompleks dipengaruhi oleh informasi terkini mengenai internal emiten dan faktor eksternal. Fluktuasi harga yang tajam bisa menyebabkan kerugian bagi investor. Peningkatan pesat data berita pasar mendorong penelitian tentang hubungan antara suatu berita yang berkaitan dengan emiten dan pergerakan harga sahamnya. Dengan perkembangan natural language processing dan deep learning, penelitian semakin tertuju pada prediksi pergerakan saham berdasarkan data teks seperti berita, yang sebelumnya dianggap sulit. Informasi emiten seperti pemahaman terhadap sektor, listing board, volume dan harga saham dapat membantu investor membuat keputusan yang lebih cerdas. Oleh karena itu, penelitian ini akan membahas mengenai prediksi pergerakan harga saham berdasarkan integrasi judul berita dan informasi terkait emiten dengan tujuan mendapatkan model terbaik di antara metode Support Vector Machine (SVM), Long-Short Term Memory (LSTM), dan Gated Recurrent Unit (GRU) dan mengevaluasi kelayakannya untuk digunakan oleh investor. Analisis menemukan bahwa model SVM dapat mencapai akurasi 74,75% dan weighted f1-score 73,49%. Sementara itu, model LSTM dan GRU menunjukkan performa kurang memadai dengan akurasi masing-masing 53,77% dan 52,63% serta weighted f1-score 52,89% dan 52,57%. Hasil penelitian ini menyoroti kemampuan integrasi data berita dan informasi emiten dalam memprediksi pergerakan harga saham, dengan SVM sebagai model terbaik yang masih memerlukan penyempurnaan untuk meningkatkan kinerjanya.
========================================================================================================================
The dynamic and complex stock market is influenced by the latest information about the issuer's internal and external factors. The rapid increase in market news data encourages research on the relationship between news related to an issuer and its stock price movements. With the development of natural language processing and deep learning, research is increasingly focused on predicting stock movements based on news, which was previously considered difficult. Issuer information such as sector, listing board, volume and share price can help investors make smarter decisions. Therefore, this study will discuss the prediction of stock price movements based on the integration of news headlines and issuer-related information with the aim of obtaining the best model among Support Vector Machine (SVM), Long-Short Term Memory (LSTM), and Gated Recurrent Unit (GRU) methods and assessing its suitability for investors. The analysis found that the SVM model can achieve 74.75% accuracy and 73.49% weighted f1-score. Meanwhile, the LSTM and GRU models performed less well with accuracies of 53.77% and 52.63% and weighted f1-score of 52.89% and 52.57%, respectively. The study underscores integrating news and issuer information for predicting stock prices, with SVM emerging as the top model needing refinement for better performance.
| Item Type: | Thesis (Other) |
|---|---|
| Uncontrolled Keywords: | deep learning, issuer information, news headlines, stock price prediction, svm, deep learning, informasi emiten, judul berita, prediksi harga saham, svm. |
| Subjects: | Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines. Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science) Q Science > QA Mathematics > QA76.9.D343 Data mining. Querying (Computer science) T Technology > T Technology (General) > T57.5 Data Processing |
| Divisions: | Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis |
| Depositing User: | Muhammad Khairii Sufyaan |
| Date Deposited: | 08 Aug 2024 12:09 |
| Last Modified: | 28 Aug 2024 08:29 |
| URI: | http://repository.its.ac.id/id/eprint/115039 |
Actions (login required)
 |
View Item |