COMPARATIVE ANALYSIS ON MACHINE LEARNING MODELS FOR PREDICTING KOSPI200 INDEX RETURNS
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
In this paper, machine learning models employed in various ¯elds are discussed and applied to KOSPI200 stock index return forecasting. The results of hyperparameter analysis of the machine learning models are also reported and practical methods for each model are presented. As a result of the analysis, Support Vector Machine and Arti¯cial Neural Network showed a better performance than k-Nearest Neighbor and Random Forest.
Abstract
In this paper, machine learning models employed in various ¯elds are discussed and applied to KOSPI200 stock index return forecasting. The results of hyperparameter analysis of the machine learning models are also reported and practical methods for each model are presented. As a result of the analysis, Support Vector Machine and Arti¯cial Neural Network showed a better performance than k-Nearest Neighbor and Random Forest.
참고문헌 (14)
- L. Breiman, "Random Forests", Machine Learning, 45, pp.5~32 (2001)
- B.E. Boser, "A training algorithm for optimal margin classi-fiers", Proceeding COLT '92 Proceedings of the fifth annual workshop on Computational learning theory, pp.144~152 (1992)
- C.L. Dunis, "Higher order and recurrent neural architectures for trading the EUR", USD exchange rate, 2011, pp.11, 615~629
- T.K. Ho, "The Random Subspace Method for Constructing Decision Forests", IEEE Transactions on Pattern Analysis and Machine Intelligence, 20, pp.832~844 (1998)
- W. Huang, "Forecasting stock market movement direction with support vector machine", Computers & Operations Research, 32, pp.2513~2522 (2005)
- 김명현, "K-Nearest Neighbors(K-NN) 알고리즘을 통한 KOSPI200 선물지수 예측효과 연구", 대한경영학회지, 28(10), pp.2613~2633 (2015), 대한경영학회
- K. Kim, "Financial time series forecasting using support vector machines", Neurocom-puting, 55, pp.307~319 (2003)
- H.Y. Lee, "A Combination Model of Multiple Artificial Intelligence Techniques Based on Genetic Algorithms for the Prediction of Korean Stock Price Index(KOSPI)", The Review of Financial Studies, 1, pp.41~66 (1988)
- W.S. McCulloch, "A logical calculus of the ideas immanent in nervous activity", The bulletin of mathematical biophysics, 5, pp.115~133 (1943)
- J.Y. Park, "Predicting KOSPI Stock Index using Machine Learn-ing Algorithms with Technical Indicators", Omega, 29, pp.309~317 (2001)
- F. Rosenblatt, "The perceptron: A probabilistic model for information storage and organization in the brain", Psychological Review, 65, pp.386~408 (1958)
- D.E. Rumelhart, "Parallel Distributed Processing: Explorations in the Microstructure of Cognition 1", pp.318~362 (1985)
- L.A. Teixeira, "A method for automatic stock trading combining tech-nical analysis and nearest neighbor classification", Journal of Korean Future Research, 22, pp.45~70 (2014)
- Z. Yudong, "Stock market prediction of S&P 500 via combination of improved BCO approach and BP neural network", Indian Institute of Capital Markets 9th Capital Markets Conference Paper, 9, pp.1~16 (2005)