PREDIKSI HARGA SAHAM BBCA MENGGUNAKAN METODE LONG SHORT-TERM MEMORY DAN GATED RECURRENT UNIT
DOI:
https://doi.org/10.51977/jti.v7i1.1901Keywords:
BBCA Stock, LSTM, GRUAbstract
Penelitian ini bertujuan untuk memprediksi harga saham PT Bank Central Asia Tbk (BBCA) menggunakan model Long Short-Term Memory (LSTM) dan Gated Recurrent Unit (GRU). Data harga saham diambil dari Yahoo Finance (2010–2023) sebanyak 3.464 data, mencakup atribut Tanggal, Open, High, Low, Close, Adj Close, dan Volume. Data diproses menggunakan MinMax Scaler sebelum pelatihan model. Model dievaluasi menggunakan MAE, RMSE, dan MAPE untuk mengukur performa prediksi. Hasil penelitian menunjukkan bahwa GRU lebih unggul dibandingkan LSTM dalam memprediksi harga saham BBCA, dengan akurasi prediksi yang lebih mendekati nilai aktual. Dari hasil eksperimen pelatihan model menggunakan dataset harga saham BBCA harian dengan berbagai kombinasi hyperparameter yang ditetapkan, ditemukan bahwa model dengan metrik evaluasi terendah adalah model LSTM dengan batch size 64 dan epoch 20. Model ini memberikan nilai MAE sebesar 158.508342, RMSE sebesar 208.687816, dan MAPE sebesar 2.248164%. Temuan ini diharapkan berkontribusi pada pengembangan analisis keuangan di Indonesia.
Downloads
Downloads
Published
Issue
Section
License
Copyright Notice
Proposed policy for journals offering open access. The requirements for authors are as follows:
- Authors retain copyright and grant the journal the right of first publication simultaneously under a Creative Commons Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) license. This license allows others to copy and redistribute the material in any medium or format, including remixing, transforming, and building upon the material for any purpose, even commercially
- .Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their websites), such as on Garuda, Academia, ResearchGate, or other repositories, prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (see: The Effect of Open Access).

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.