Melez Aşırı Öğrenme Makinesi ve Türevi ile Hisse Senedi Fiyatı Tahmini

Öz

Çok yüksek getiri elde etme potansiyeline sahip olması nedeniyle doğru ve etkili hisse senedi fiyatı tahmini yatırımcılar için caziptir. Bununla birlikte, borsanın karmaşık, evrimsel ve doğrusal olmayan yapısı nedeniyle, modern iş dünyasında hâlâ karmaşık bir iştir. Bu nedenle, iki melez model, HS-ELM olarak adlandırılan Harmoni Araması (HS) tabanlı aşırı öğrenme makinesi (ELM) ve HS-RELM olarak adlandırılan HS tabanlı tekrarlı aşırı öğrenme makinesi (RELM), günlük hisse senedi fiyatı tahminini doğru ve hızlı bir şekilde elde etmek için önerilmiştir. Bu çalışma, hisse senedi fiyatı tahmini alanına yeni bir yön vermekte ve BIST50 Endeksinde bulunan farklı hisse senetleri üzerinde uygulanması ile HS-ELM ve HS-RELM'nin hisse senedi fiyat tahmininde nasıl yapılandırılması gerektiği konusunda bazı öneriler sunmaktadır. Performans ölçümlerinin sonuçları, her iki önerilen modelin hisse senetleri fiyat tahminine pratik uygulanabilirliği açısından oldukça yararlı olduğunu göstermesine rağmen HS-RELM modelinin performansının HS-ELM modelinin performansından daha iyi olduğu gözlemlenmiştir.

Anahtar Kelimeler

• Aşırı öğrenme makinesi,Tekrarlı aşırı öğrenme makinesi,Harmoni araması,Hisse senedi fiyatı tahmini

A Hybrid Extreme Learning Machine and its Variant for Stock Price Prediction

Öz

Accurate and effective stock price prediction is appealing for investors due to the potential of obtaining a very high return. However, it is still a challenging task in the modern business world because of the complex, evolutionary, and nonlinear nature of stock market. Therefore, we proposed two hybrid models, which are Harmony Search (HS) based Extreme Learning Machine (ELM) that is denoted as HS-ELM and HS based Recurrent Extreme Learning Machine (RELM) that is represented as HS-RELM, to provide accurate and fast one-day ahead stock price prediction. This study provides a new direction in the field of stock price prediction and offers some suggestions on how to configure HS-ELM and HS-RELM for performing stock price prediction, with an application on stocks listed in BIST50 Index. The results of the performance measures show that although both proposed models are very helpful for the practical applicability of the stock market, HS-RELM model is more powerful than HS-ELM model.

Anahtar Kelimeler

• Extreme learning machine,Recurrent extreme learning machine,Harmony search,Stock price prediction

Kaynakça

1. 1. Zahedi, J., Rounaghi, M.M., 2015. Application of Artificial Neural Network Models and Principal Component Analysis Method in Predicting Stock Prices on Tehran Stock Exchange, Physica A: Statistical Mechanics and its Applications, 438: 178-187.
2. 2. Majumder, M., Hussian, M.D.A., 2007. Forecasting of Indian Stock Market Index Using Artificial Neural Network, Available at: https://nseindia.com/content/research/FinalPaper206.pdf.
3. 3. Wei, L.Y., Cheng, C.H., 2012. A Hybrid Recurrent Neural Networks Model Based on Synthesis Features to Forecast the Taiwan Stock Market, International Journal of Innovative Computing Information and Control, 8(8): 5559-5571.
4. 4. Zhu, Q.Y., Qin, A.K., Suganthan, P.N., Huang, G.B., 2005. Evolutionary Extreme Learning Machine, Pattern Recognition, 38: 1759-1763.
5. 5. Huang, G., Huang, G.B., Song, S., You, K., 2015. Trends in Extreme Learning Machines: a Review, Neural Networks, 61: 32-48.
6. 6. Bazi, Y., Alajlan, N., Melgani, F., AlHichri, H., Malek, S., Yager, R.R., 2014. Differential Evolution Extreme Learning Machine for the Classification of Hyperspectral Images, Geoscience and Remote Sensing Letters, 11: 1066-1070.
7. 7. Yang, H., Yi, J., Zhao, J., Dong, Z., 2013. Extreme Learning Machine Based Genetic Algorithm and its Application in Power System Economic Dispatch, Neurocomputing, 102: 154-162.
8. 8. Suresh, S., Saraswathi, S., Sundararajan, N., 2010. Performance Enhancement of Extreme Learning Machine for Multi-category Sparse Data Classification Problems, Engineering Applications of Artificial Intelligence, 23: 1149-1157.

9. 9. Hegazy, O., Soliman, O.S., Salam, M.A., 2015. FPA-ELM Model for Stock Market Prediction, International Journal of Advanced Research in Computer Science and Software Engineering, 5: 1050-1063.
10. 10. Wang, F., Zhang, Y., Xiao, H., Kuang, L., Lai, Y., 2015. Enhancing Stock Price Prediction With a Hybrid Approach Based Extreme Learning Machine, 2015 IEEE 15th International Conference on Data Mining Workshops, 1568-1575.
11. 11. Li, X., Xie, H., Wang, R., Cai, Y., Cao, J., Wang, F., Min, H., Deng, X., 2016. Empirical Analysis: Stock Market Prediction Via Extreme Learning Machine, Neural Computing and Applications, 27: 67-78.
12. 12. Ertugrul, Ö.F., 2016. Forecasting Electricity Load by a Novel Recurrent Extreme Learning Machines Approach, Electrical Power and Energy Systems, 78: 429-435.
13. 13. Ólafsson, S., 2006. Metaheuristics, Handbooks in Operations Research and Management Science, 13: 633-654.
14. 14. Saka, M.P., 2009. Optimum Design of Steel Skeleton Structures, In Music-Inspired Harmony Search Algorithm, Springer Berlin Heidelberg, 87-112.
15. 15. Geem, Z.W., 2009. Music-inspired Harmony Search Algorithm Theory and Applications, (Zong Woo Geem ed.). Springer-Verlag Berlin Heidelberg.
16. 16. Wang, Y., Cao, F., Yuan, Y., 2011. A Study on Effectiveness of Extreme Learning Machine, Neurocomputing, 74: 2483-2490.
17. 17. Huang, G.B, Zhu, Q.Y., Siew, C.K., 2006. Extreme Learning Machine: Theory and Applications, Neurocomputing, 70: 489-501.