Sondo Kim, Poongjin Cho, Dongkyu Kwak, Woojin Chang
Forecasting daily stock price is an important task in financial time series area. And it is known that the singular value decomposition Entropy has a predictive power for stock market. This study attempts to develop various models and compare their performances in predicting the daily KOSPI200 index. The models are based on a singular value decomposition process which has various correlation and entropy methods: Pearson correlation, Kendall correlation, Shannon entropy, Renyi entropy, Max-entropy, Min-entropy. Input variables include moving time window singular value decomposition entropy series which are the combination of two correlations and four entropies. Support Vector Regression is used to predict daily KOSPI200 index and the model performance is evaluated using accuracy measures such as MAE, MAPE, and RMSE of the forecasting values. As a result of its application, investors may have a guidance of their trading strategy.
 Caraiani, P. (2014). The predictive power of singular value decomposition entropy for stock market dynamics. Physica A: Statistical Mechanics and its Applications, 393, 571-578.
 Gu, R., Xiong, W., & Li, X. (2015). Does the singular value decomposition entropy have predictive power for stock market?—Evidence from the Shenzhen stock market. Physica A: Statistical Mechanics and its Applications, 439, 103-113.
 Gu, R., & Shao, Y. (2016). How long the singular value decomposed entropy predicts the stock market?—Evidence from the Dow Jones Industrial Average Index. Physica A: Statistical Mechanics and its Applications, 453, 150-161.
 Maasoumi, E., & Racine, J. (2002). Entropy and predictability of stock market returns. Journal of Econometrics, 107(1), 291-312.