A novel fuzzy-Markov forecasting model for stock fluctuation time series
- 4 Downloads
In order to reveal intrinsic fluctuation rules hidden in a stock market time series dataset with noise, a novel forecasting model combining Markov chain theory with fuzzy set theory is proposed in this study. A fuzzified one-step transition matrix of Markov Chain in the paper represents inherent rules of historical fluctuation. Comparing with existing models, the advantage of the proposed model is that transition matrix can express the relationship between history and current flexibly while the introduction of fuzzy theory can help to alleviate noises. Therefore, the proposed model could handle complex patterns during state transitions and the relatively simple forecasting algorithm could reduce the calculation cost. We apply the proposed method to forecast well-known stock indexes such as (Taiwan Stock Exchange Capitalization Weighted Stock Index) TAIEX, (Shanghai Stock Exchange Composite Index) SHSECI and so on. Experimental results demonstrate that our proposed method outperforms other traditional models.
KeywordsFluctuation time series Markov chain Fuzzy set Forecasting model
The authors are indebted to anonymous reviewers for their very insightful comments and constructive suggestions, which help ameliorate the quality of this paper. This work was supported by major projects of the National Social Science Foundation of China under Grants with No. 19VHQ011.
- 1.Kuo RJ, Lee LC, Lee CF (1996) Integration of artificial neural networks and fuzzy Delphi for stock market forecasting. In: IEEE international conference on system, man, and cybernetics, Beijing, China, vol 2, pp 1073–1078Google Scholar
- 3.Sharma N, Sharma P, Irwin D, Shenoy P (2012) Predicting solar generation from weather forecasts using machine learning. In: IEEE international conference on smart grid communications, Brussels, Belgium, pp 528–533Google Scholar
- 7.Tambi MK (2005) Forecasting exchange rate: a univariate out-of-sample approach (Box–Jenkins methodology). IUP J Bank Manag 1(6):60–74Google Scholar
- 18.Chen SM, Jian WS (2016) Fuzzy forecasting based on two-factors second-order fuzzy-trend logical relationship groups, similarity measures and PSO techniques. Inf Sci 391–392:65–79Google Scholar