Technical Analysis of the Indonesian Stock Market with Gated Recurrent Unit and Temporal Convolutional Network

Siti Aisyah; Yenni Angraini; Kusman Sadik; Bagus Sartono; Gerry Alfa Dito

doi:10.30595/juita.v12i2.23464

Authors

Siti Aisyah IPB University
Yenni Angraini IPB University
Kusman Sadik Department of Statistics, IPB University
Bagus Sartono IPB University
Gerry Alfa Dito IPB University

DOI:

https://doi.org/10.30595/juita.v12i2.23464

Keywords:

GRU, JKSE, stock market crisis, TCN

Abstract

BigÂ data is essential in the age of 4.0 industry as it becomes the basis of decision making. Deep learning research in the last few years has been proven effective in understanding complex big data patterns, especially in the finance sector. The rapid growth of the Indonesian stock market in the last 20 years, which was driven by globalization, prompted fluctuation in the Bursa Efek Jakarta (JKSE) which was influenced by stock prices, commodity prices, and exchange rate. This study identifies the main indicators of Indonesian stock market crisis, applies and compares deep learning models, particularly Gated Recurrent Unit (GRU) and Temporal Convolutional Network (TCN), in predicting stock prices. This study identified 20 JKSE crisis points between the 2002-2023 period with average return value at around -6%. All variables correlated positively with JKSE, with SET.BK as the highest correlated variable in lag 0. The American and European stock market, commodity price, and exchange rate tend to show a pattern opposite to the JKSE crisis. Predictor variables such as STI, HIS, KLSE, KS11, SET.BK, PSEI.PS, RUT, and USDIDR are chosen based on significant cross correlation and average return plot. Hyperparameter tuning and cross validation within a 3 years window concluded that the GRU model is accurate and efficient, with RMSE value at 43.35568 and MAE value at 33.66909 in the validation data.

Author Biographies

Siti Aisyah, IPB University

Department of Statistics

Yenni Angraini, IPB University

Department of Statistics

Kusman Sadik, Department of Statistics, IPB University

Department of Statistics

Bagus Sartono, IPB University

Department of Statistics

Gerry Alfa Dito, IPB University

Department of Statistics

References

[1] I. M. P. D. Putra and I. D. N. Badera, “Identifikasi hubungan linier dan non-linier antara rasio-rasio keuangan dan return saham,” Jurnal Ilmu Akuntansi, vol. 12, no. 1, pp. 83–92, 2019, [Online]. Available: https://journal.uinjkt.ac.id/index.php/akuntabilitas/article/view/10093

[2] H. A. Al Al Hakim, “Prediksi tren pergerakan harga saham menggunakan algoritma Temporal Convolutional Network (TCN),” Universitas Islam Indonesia, Yogyakarta, 2021. [Online]. Available: https://dspace.uii.ac.id/handle/123456789/35941

[3] S. P. Chatzis, V. Siakoulis, A. Petropoulos, E. Stavroulakis, and N. Vlachogiannakis, “Forecasting stock market crisis events using deep and statistical machine learning techniques,” Expert Syst Appl., vol. 112, pp. 353–371, Dec. 2018, doi: 10.1016/j.eswa.2018.06.032.

[4] W. Widodo, “Analisis pengaruh Indeks Harga Saham Gabungan regional Asia terhadap Indeks Harga Saham Gabungan Indonesia,” EkBis: Jurnal Ekonomi dan Bisnis, vol. 1, no. 2, pp. 148–164, 2017, [Online]. Available: https://ejournal.uin-suka.ac.id/febi/ekbis/article/view/12-02

[5] “Melalui berbagai pencapaian tahun 2023, Pasar Modal Indonesia tunjukkan optimisme hadapi tahun 2024,” PT Bursa Efek Indonesia, Dec. 29, 2023. Accessed: Jan. 20, 2024. [Online]. Available: https://www.idx.co.id/en/news/press-release/2080

[6] P. H. Setianingrum and D. Prastuti, “Analisis kointegrasi dan korelasi indeks pasar saham utama dunia dan IDX tahun 2013 – 2019,” Jurnal Akuntansi dan Manajemen, vol. 19, no. 01, pp. 01–10, Jun. 2022, doi: 10.36406/jam.v19i01.539.

[7] A. Nilsen, “Perbandingan model RNN, model LSTM, dan model GRU dalam memprediksi harga saham-saham LQ45,” Jurnal Statistika dan Aplikasinya, vol. 6, no. 1, pp. 137–147, 2022, [Online]. Available: https://journal.unj.ac.id/unj/index.php/statistika/article/view/26939

[8] S. Bai, J. Z. Kolter, and V. Koltun, “An empirical evaluation of Generic Convolutional and Recurrent Networks for sequence modeling,” arXiv:1803.01271v2, Mar. 2018, [Online]. Available: http://arxiv.org/abs/1803.01271

[9] L. K. Sari, “Pemodelan dan transmisi volatilitas return saham utama dunia terhadap Indonesia,” IPB University, Bogor, 2017. [Online]. Available: http://repository.ipb.ac.id/handle/123456789/87780

[10] I. R. Kurniyanto, “Pengaruh variabel kinerja keuangan dan variabel makroekonomi terhadap harga saham perusahaan pertanian di Bursa Efek Indonesia,” IPB University, Bogor, 2019. [Online]. Available: http://repository.ipb.ac.id/handle/123456789/100055

[11] J. A. Ripto and H. Heryanto, “Penerapan Gated Recurrent Unit untuk prediksi pergerakan harga saham pada Bursa Efek Indonesia,” Institut Teknologi Harapan Bangsa, Bandung, 2022. [Online]. Available: https://repository.ithb.ac.id/id/eprint/38/

[12] C. Choi, “Time series forecasting with Recurrent Neural Networks in presence of missing data,” UiT The Arctic University of Norway, Tromsø, 2018. [Online]. Available: https://hdl.handle.net/10037/14887

[13] Caroline, “Prediksi harga saham menggunakan Long-Short Term Memory dan Temporal Convolutional Network,” Universitas Mikroskil, Medan, 2023.

[14] S. Ben Taieb, A. Sorjamaa, and G. Bontempi, “Multiple-output modeling for multi-step-ahead time series forecasting,” Neurocomputing, vol. 73, no. 10–12, pp. 1950–1957, Jun. 2010, doi: 10.1016/j.neucom.2009.11.030.

[15] B. S. Vien, L. Wong, T. Kuen, L. R. Francis Rose, and W. K. Chiu, “A machine learning approach for anaerobic reactor performance prediction using Long Short-Term Memory Recurrent Neural Network,” in Materials Research Proceedings, Association of American Publishers, 2021, pp. 61–70. doi: 10.21741/9781644901311-8.

[16] R. Wan, S. Mei, J. Wang, M. Liu, and F. Yang, “Multivariate temporal convolutional network: A deep neural networks approach for multivariate time series forecasting,” Electronics (Basel), vol. 8, no. 8, p. 876, Aug. 2019, doi: 10.3390/electronics8080876.

[17] E. Rohaeti, “Pengembangan analisis gerombol berbasis model Vector Autoregressive pada data deret waktu peubah ganda dengan data hilang,” IPB University, Bogor, 2023. [Online]. Available: http://repository.ipb.ac.id/handle/123456789/119578

[18] D. N. Utami, “Ini langkah BEI kalau pasar turun tajam lagi,” Bisnis.com, Feb. 2020. Accessed: Feb. 05, 2024. [Online]. Available: https://market.bisnis.com/read/20200227/7/1206793/ini-langkah-bei-kalau-pasar-turun-tajam-lagi

[19] Khairunnida, “Pengaruh suku bunga dan nilai tukar terhadap harga saham perusahaan consumer goods di Bursa Efek Indonesia,” Majalah Ilmiah Politeknik Mandiri Bina Prestasi, vol. 6, no. 2, pp. 208–216, 2017.

[20] D. A. de Vaus, Surveys In Social Research, Fifth Edition. New South Wales: Allen & Unwin, 2002.

[21] A. Julianto, A. Sunyoto, D. Ferry, and W. Wibowo, “Optimasi hyperparameter Convolutional Neural Network untuk klasifikasi penyakit tanaman padi (Optimization of Convolutional Neural Network hyperparameters for classification of rice plant diseases),” TEKNIMEDIA: Teknologi Informasi dan Multimedia, vol. 3, no. 2, pp. 98–105, 2022, [Online]. Available: https://jurnal.stmiksznw.ac.id/index.php/teknimedia/article/view/77

[22] R. Soekarta, S. Aras, and Ahmad Nur Aswad, “Hyperparameter optimization of CNN classifier for music genre classification,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 7, no. 5, pp. 1205–1210, Oct. 2023, doi: 10.29207/resti.v7i5.5319.

[23] C. Cai, Y. Li, Z. Su, T. Zhu, and Y. He, “Short-term electrical load forecasting based on VMD and GRU-TCN hybrid network,” Applied Sciences (Switzerland), vol. 12, no. 13, p. 6647, Jul. 2022, doi: 10.3390/app12136647.