Stock Price Prediction Using the ETSFormer Model Case Study: PTBA

Muhammad Azka Atqiya; Lala Septem Riza; Ani Anisyah

doi:10.47709/brilliance.v5i2.6729

Penulis

Muhammad Azka Atqiya Universitas Pendidikan Indonesia, Indonesia
Lala Septem Riza Universitas Pendidikan Indonesia, Indonesia
Ani Anisyah Universitas Pendidikan Indonesia, Indonesia

DOI:

https://doi.org/10.47709/brilliance.v5i2.6729

Kata Kunci:

ETSformer, Grid Search, Hyperparameter, Prediction, Stock

Abstrak

The capital market in Indonesia is currently experiencing very rapid development. This growth is significantly evidenced by the increasing number of investors, especially from the millennial and Gen Z demographics. However, this growing investor base also faces a major challenge: high stock price volatility. These fluctuations are triggered by various factors, ranging from domestic economic policies and global geopolitical conditions to rapidly changing market sentiment. This research aims to build a stock price prediction model for PT Bukit Asam Tbk (PTBA) using the ETSFormer architecture, a modern Transformer-based method designed for time-series data. The historical stock price data used in this study covers a five-year period from 2020 to 2025. To ensure optimal model performance, the best model was identified using the Grid Search technique to find the most effective combination of hyperparameters. The results of this study determined that the best model was achieved with the hyperparameters model dimension = 16, batch size = 16, and a learning rate = 0.01, which yielded a validation loss of 0.0074. In the evaluation phase, this model demonstrated solid performance with a MAPE score of 3.28%, an MAE of 86.76, and an RMSE of 117.2. Although the resulting model is quite good at reading long-term trend directions, observations indicate limitations in capturing short-term price volatility. This implies that the model is more suitable for strategic trend analysis than for predicting daily fluctuations.

Referensi

Anas, A. T., Aini, W., Ekonomi, F., Bisnis, D., & Ekonomi, P. (2020). Peran Bursa Efek Dalam Mendorong Pertumbuhan Ekonomi Sumatera Utara. AGHNIYA: Jurnal Ekonomi Islam, 2(2), 590–600. https://doi.org/10.30596/aghniya.v2i2.4825

Artiani, L. E., & Sari, C. U. P. (2019). Pengaruh Variabel Makro Dan Harga Komoditas Tambang Terhadap Harga Saham Sektor Pertambangan Di Indeks Saham Syariah Indonesia (Issi). Jurnal Ekonomika, 10(2), 1–10. https://doi.org/10.35334/jek.v10i2.763

Faisal, A. (2021). Prediksi Saham Telkom Dengan Metode Arima. Jurnal Bisnis, Logistik Dan Supply Chain (BLOGCHAIN), 1(2), 45–50. https://doi.org/10.55122/blogchain.v1i2.298

Hanafiah, A., Arta, Y., Nasution, H. O., & Lestari, Y. D. (2023). Penerapan Metode Recurrent Neural Network dengan Pendekatan Long Short-Term Memory (LSTM) Untuk Prediksi Harga Saham. Bulletin of Computer Science Research, 4(1), 27–33. https://doi.org/10.47065/bulletincsr.v4i1.321

Hidayati, R. N. (2024). Analisis Volatilitas IHSG: Pengaruh Suku Bunga dan Nilai Tukar dalam Dinamika Pasar Saham Indonesia. Jurnal Ekonomi, Bisnis Dan Pendidikan, 4(5). https://doi.org/10.17977/um066.v4.i5.2024.4

Istinganah, A., & Hartiyah, S. (2021). Pengaruh Inflasi, Suku Bunga, Nilai Tukar Rupiah, Produk Domestik Bruto Dan Jumlah Uang Beredar Terhadap Indeks Harga Saham Gabungan (Ihsg) Di Bursa Efek Indonesia (Bei) Periode 2010 Sampai 2019. Journal of Economic, Business and Engineering (JEBE), 2(2), 245–252. https://doi.org/10.32500/jebe.v2i2.1739

Jati, C. K., & Indriastuti, D. R. (2024). Analisis Dampak Volatilitas Pasar, Faktor Fundamental, dan Sentimen Investor terhadap Keputusan Investasi Saham pada Mahasiswa Program Studi Manajemen Fakultas Ekonomi Universitas Slamet Riyadi Surakarta Tahun 2024. Lokawati?: Jurnal Penelitian Manajemen Dan Inovasi Riset, 2(5), 74–82. https://doi.org/10.61132/lokawati.v2i5.1173

M, K. K., Dsouza, A. P., Vibha, V., & Kanse, V. P. (2024). Macroeconomic Factors and their Impact on Stock Market Volatility?: Trends , Drivers , and Policy Recommendations. International Journal of Scientific Research in Engineering and Management (IJSREM), 1–14. https://doi.org/10.55041/IJSREM39409

Minhaj, N., Ahmed, R., Khalique, I. A., & Imran, M. (2022). A Comparative Research of Stock Price Prediction of Selected Stock Indexes and the Stock Market by Using Arima Model. Global Economics Science, 4(1), 1–19. https://doi.org/10.37256/ges.4120231426

Nurjanah, A., Zamzam, I., & Zainuddin, Z. (2024). Mengungkap Gejolak Pasar: Analisis Volatilitas Saham dan Volume Perdagangan LQ45 Sebelum dan Selama Pandemi Covid-19. Jurnal Ekonomi Bisnis, Manajemen Dan Akuntansi (JEBMA), 4(1), 130–140. https://doi.org/10.47709/jebma.v4i1.3533

Shah, A., Doshi, M., Parekh, M., Deliwala, N., & Chawan, P. P. M. (2023). Identifying Trades Using Technical Analysis and ML / DL models. F Computer Engineering and IT, VJTI College, Mumbai, Maharashtra, India, April.

Triya, P., Suarna, N., & Dienwati Nuris, N. (2024). Penerapan Machine Learning Dalam Melakukan Prediksi Harga Saham Pt. Bank Mandiri (Persero) Tbk Dengan Algoritma Linear Regression. JATI (Jurnal Mahasiswa Teknik Informatika), 8(1), 1207–1214. https://doi.org/10.36040/jati.v8i1.8958

Wang, S., Li, G., & Bao, Y. (2017). A Novel Improved Fuzzy Support Vector Machine Based Stock Price Trend Forecast Model. https://doi.org/10.2991/iemss-17.2017.144

Wen, X., & Li, W. (2023). Time Series Prediction Based on LSTM-Attention-LSTM Model. IEEE Access, 11(May), 48322–48331. https://doi.org/10.1109/ACCESS.2023.3276628

Woo, G., Liu, C., Sahoo, D., Kumar, A., & Hoi, S. (2022). ETSformer?: Exponential Smoothing Transformers for Time-series Forecasting. 1–18.