Prediksi Harga Pasar Modal Menggunakan Time Series Transformer

Renwarin, Abel Marcel Renwarin (2025) Prediksi Harga Pasar Modal Menggunakan Time Series Transformer. Other thesis, Institut Teknologi Sepuluh Nopember.

[thumbnail of 5024211020-Undergraduate_thesis.pdf] Text
5024211020-Undergraduate_thesis.pdf - Accepted Version
Restricted to Repository staff only

Download (9MB) | Request a copy

Abstract

Pergerakan harga pasar modal merupakan fenomena dinamis yang dipengaruhi oleh berbagai faktor ekonomi, politik, dan sosial. Prediksi yang akurat terhadap harga pasar modal menjadi penting dalam pengambilan keputusan investasi yang lebih baik. Penelitian ini bertujuan untuk mengembangkan model prediksi harga pasar modal menggunakan Time Series Transformer (TST). TST digunakan untuk meningkatkan kemampuan model dalam menangkap pola dinamis yang lebih kompleks dengan mempertimbangkan pergeseran temporal. Penelitian ini menggunakan data historis harga forex yang tersedia di sumber terbuka sebagai objek studi, dan akan mengevaluasi model TST dalam memprediksi harga di masa depan. Evaluasi model dilakukan menggunakan metrik akurasi prediksi dan Mean Absolute Error (MAE). Diharapkan hasil dari penelitian ini dapat memberikan kontribusi pada pengembangan metode prediksi pasar modal yang lebih akurat dan efisien.
==========================================================================================================================
The movement of capital market prices is a dynamic phenomenon influenced by various economic, political, and social factors. Accurate prediction of capital market prices is important in making better investment decisions. This study aims to develop a capital market price prediction model using Time Series Transformer (TST). TST is used to improve the model’s ability to capture more complex dynamic patterns by considering temporal shifts. This study uses historical forex price data available in open sources as the object of study, and will evaluate the TST model in predicting future prices. Model evaluation is carried out using prediction accuracy metrics and Mean Absolute Error (MAE). It is expected that the results of this study can contribute to the development of more accurate and efficient capital market prediction methods.

Item Type: Thesis (Other)
Uncontrolled Keywords: Stock Market Price Prediction, Forex, Time Series Transformer(TST), Prediksi Pasar Modal, Forex, TST(Time Series Transformer)
Subjects: T Technology > T Technology (General) > T174 Technological forecasting
Divisions: Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Computer Engineering > 90243-(S1) Undergraduate Thesis
Depositing User: Abel Marcel Renwarin
Date Deposited: 29 Jul 2025 01:16
Last Modified: 29 Jul 2025 01:16
URI: http://repository.its.ac.id/id/eprint/121557

Actions (login required)

View Item View Item