Abstract
This study investigates index prediction performance of Relevance Vector Machines (RVM) and frequently applied Ridge Regression and Support Vector Machines (SVM). Daily prices of BIST Banks and BIST Financials indices of Borsa Istanbul are used to obtain one-day-ahead predictions of the algorithms. According to estimated performance measures, RVM yielded mostly the best metrics in both periods of BIST Banks. While SVM obtained the best performance metrics on BIST Financials index, metrics of RVM were not far from the best. Overall, the results indicate the applicability of RVM in predicting index directions and has a potential to be a good rival of SVM.
Publisher
Eskisehir Osmangazi University Journal of Economics and Administrative Sciences
Reference40 articles.
1. Akcan, A., & Kartal, C. (2011), “İMKB Sigorta Endeksini Olusturan Sirketlerin Hisse Senedi Fiyatlarının Yapay Sinir Ağları İle Tahmini”, Muhasebe Ve Finansman Dergisi, 51: 27-40.
2. Aksoy, B. (2021), “Pay senedi fiyat yönünün makine öğrenmesi yöntemleri ile tahmini: Borsa İstanbul örneği”, Business and Economics Research Journal, 12(1): 89-110. http://dx.doi.org/10.20409/berj.2021.312
3. Avcı, E. (2007), “FORECASTING DAILY AND SESSIONAL RETURNS OF THE ISE-100 INDEX WITH NEURAL NETWORK MODELS”, Doğuş Üniversitesi Dergisi, 8(2): 128-142.
4. Ballings, M., Poel, D.V., Hespeels, N., & Gryp, R. (2015), “Evaluating multiple classifiers for stock price direction prediction”, Expert Systems with Applications, 42(20): 7046–7056. https://doi.org/10.1016/j.eswa.2015.05.013
5. Bollerslev, T. (1986), “Generalized Autoregressive Conditional Heteroskedasticity”, J. Econ., 31: 307-327.