Prediction of Central Asia Bank's Stock Price using Support Vector Regression Method

Authors

  • Dide Guna Jayaswara Statistics Department, Faculty of Mathematics and Natural Sciences, Sebelas Maret University,
  • Isnandar Slamet Statistics Department, Faculty of Mathematics and Natural Sciences, Sebelas Maret University,
  • Yuliana Susanti Statistics Department, Faculty of Mathematics and Natural Sciences, Sebelas Maret University,

Keywords:

Prediction, Stock, Support Vector Regression, Time Series

Abstract

The capital market in Indonesia is a developing market that is very vulnerable to global economic conditions and world capital markets. There is a term mostly found in the capital market, namely investment. Investment is a form of delaying consumption from the present to the future where there is a risk of uncertainty. In capital market investment, it is necessary to analyse stock price predictions to find out stock prices in the future by using historical stock prices because stock prices change quickly from time to time, making the shareholder immediately decide when the shares should be sold or retained. This study aims to obtain stock price predictions and model implementation and determine the model's accuracy in predicting a stock's movement to benefit from each stock price that changes from time to time or can be referred to as time series data. Therefore, we need a method that can predict stock prices. In this study, the predicted stocks are BCA stock data using the SVR algorithm with linear and RBF kernels. SVR has advantages in making accurate stock price predictions and can overcome overfitting problems. From several studies conducted, SVR provides optimal results for stock price prediction analysis. Based on the results of the research for BCA shares, it can be concluded that the SVR algorithm has an excellent predictive accuracy value with a linear kernel function with the help of a grid search using a k-fold Cross-validation of 3, which has an R-square value of training data of 93.79% and an R- square data testing is 92.98%, Mean Absolute Percentage Error (MAPE) training data is 0.2340, and MAPE data testing is 0.1021, Root Mean Square Error (RMSE) training data is 0.0597, and RMSE data testing is 0.0499. This algorithm shows that the SVR method is suitable for predicting stock prices.

References

Ahmad, A. 2017. Mengenal Artificial Intelligence, Machine Learning, Neural Network, dan Deep Learning. Yayasan Cahaya Islam Jurnal Teknologi Indonesia.

Anoraga, P., & Pakarti, P. 2008. Pengantar Pasar Modal. Jakarta: Rineka Cipta.

Astudillo, G., Carrasco, R., Fernández-Campusano, C., & Chacón, M. 2020. Copper price prediction using support vector regression technique. Applied Sciences (Switzerland), 10(19). https://doi.org/10.3390/APP10196648

Cortez, P. dan Donate, J.P. 2012. Evolutionary Support Vector Machines for Time Series Forecasting. ICANN Part II, LNCS 7553: 523-530

Darmaji, T., & Fakhrudin, H. 2012. Pasar Modal di Indonesia. Jakarta: Salemba Empat.

Dwi, N., & Pengembangan, S. B. (n.d.). 2015. Penerapan Algoritma Support Vector Machine untuk Prediksi Harga Emas.

Enri, U. 2018. Optimasi Parameter Support Vector Machine untuk Prediksi Nilai Tukar Rupiah Terhadap Dollar Amerika Serikat. Jurnal Gerbang, Vol. 8(1): 65-72.

Fadilah, W. R. U., Agfiannisa, D., & Azhar, Y. 2020. Analisis Prediksi Harga Saham PT. Telekomunikasi Indonesia Menggunakan Metode Support Vector Machine. Fountain of Informatics Journal, 5(2), 45. https://doi.org/10.21111/fij.v5i2.4449

Feta, N. R., & Asep, R. G. 2019. Komparasi Fungsi Kernel Metode Support Vector Machine Untuk Pemodelan Klasifikasi Terhadap Penyakit Tanaman Kedelai. BRITech (Jurnal Ilmiah Ilmu Komputer, Sains dan Teknologi Terapan), Vol. 1(1): 33-39.

Furi, R.P., Jondri, dan Saepudin, D. 2015. Prediksi Financial Time Series Menggunakan Independent Component Analysis dan Support Vector Regression Studi Kasus: IHSG dan JII. E-proceeding of Engineering, Vol. 2(2): 3608-3618.

Gujarati, D. 1999. Ekonometrika Dasar. Jakarta: Erlangga.

Hedianti, E.S. 2019. Peramalan Harga Saham Dengan Menggunakan Metode Support Vector Regression (SVR). Tugas Akhir. Departemen Sistem Informasi ITS, Surabaya.

Heizer, J., & Barry, R. 2009. Manajemen Operasi Buku 1 Edisi 9. Jakarta: Salemba Empat.

Henrique, B., Sobreiro, V. and Kimura, H., 2018. Stock price prediction using support vector regression on daily and up to the minute prices. The Journal of Finance and Data Science, 4(3), pp.183-201.

Lahmiri, S., 2018. Minute-ahead stock price forecasting based on singular spectrum analysis and support vector regression. Applied Mathematics and Computation, 320, pp.444-451.

Lin, K., Lin, Q., Zhou, C., dan Yao, J. 2007. Time Series Prediction Based on Linear Regression and SVR. Third International Conference on Natural Computation (ICNC) 0-7695-2875-9/07.

Maulana, N. D., Setiawan, B. D., & Dewi, C. 2019. Implementasi Metode Support Vector Regression (SVR) Dalam Peramalan Penjualan Roti. Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer.

Maulida, K. H., Gede Susrama Mas Diyasa, I., Aji, P. R., & Maulana, T. F. (n.d.). Seminar Nasional Informatika Bela Negara (SANTIKA) Studi Literatur Mengenai Prediksi Harga Saham Menggunakan Machine Learning.

Mutmainnah, A. dan Widodo, E. 2018. Application of Support Vector Machine (SVM) Methods on Stock Price Forecasting of PT Telekomunikasi Indonesia Tbk. Seminar Nasional Edusainstek FMIPA UNIMUS: 50

Naufal, M.F. 2017. Peramalan Jumlah Wisatawan Mancanegara yang Datang ke Indonesia Berdasarkan Pintu Masuk Menggunakan Metode Support Vector Machine (SVM). Tugas Akhir. Departemen Sistem Informasi ITS, Surabaya.

Purnama, D.I. 2020. Peramalan Jumlah Penumpang Datang Melalui Transportasi Udara di Sulawesi Tengah Menggunakan Support Vector Regression (SVR). Jurnal Ilmiah Matematika dan Terapan (JIMT), Vol. 17(1): 109- 117.

Rahmadayanti, C., Rabbani, H., & Rohmawati, A. A. 2018. Model GARCH dengan Pendekatan Conditional Maximum Likelihood untuk Prediksi Harga Saham. Indonesian Journal on Computing (Indo-JC), 3(2), 21. https://doi.org/10.21108/indojc.2018.3.2.223

Ramdhani, Y., & Mubarok, A. 2019. Analisis Time Series Prediksi Penutupan Harga Saham Antm.Jk Dengan Algoritma SVM Model Regresi. JURNAL RESPONSIF, 1(1). http://ejurnal.univbsi.id/index.php/jti

Rijin, J.N.V. dan Hutter, F. 2018. Hyperparameter Importance A cross Datasets. Proceedings of ACM Conference on Knowledge Discovery and Data Mining: 2367-2376

Septiningrum, L., Yasin, H., Jurusan Statistika FSM UNDIP, M., & Pengajar Jurusan Statistika, S. 2015. Prediksi Indeks Harga Saham Gabungan Menggunakan Support Vector Regression (Svr) Dengan Algoritma Grid Search. 4(2), 315–321. http://ejournal-s1.undip.ac.id/index.php/gaussian

Smola, A.J. dan Scholkopf, B. 2004. A tutorial on Support Vector Regression. Statistics and Computing , Vol. 14: 199-222

Thissen, U., van Brakel, R., de Weijer, A.P., Melssen, W.J., dan Buydens L.M.C. 2003. Using support vector machines for time series prediction. Chemometrics and Intelligent Laboratory Systems, Vol. 69: 35-4

Yasin, H., Prahutama, A., & Utami, T. W. 2014. Prediksi Harga Saham Menggunakan Support Vector Regression Dengan Algoritma Grid Search. Media Statistik.

Yudhawan, D. H. 2020. Implementasi Support Vector Regression Untuk Peramalan Harga Saham Perusahaan Pertambangan di Indonesia. SKRIPSI. Yogyakarta. Universitas Islam Indonesia.

Downloads

Published

2023-04-08

How to Cite

Dide Guna Jayaswara, Isnandar Slamet, & Yuliana Susanti. (2023). Prediction of Central Asia Bank’s Stock Price using Support Vector Regression Method . Proceeding International Conference on Religion, Science and Education, 2, 7–12. Retrieved from http://sunankalijaga.org/prosiding/index.php/icrse/article/view/883

Issue

Section

Articles