A hybrid model based on rough sets theory and genetic algorithms for stock price forecasting

  • Authors:

  • Ching-Hsue Cheng;Tai-Liang Chen;Liang-Ying Wei

  • Affiliations:

  • Department of Information Management, National Yunlin University of Science and Technology, 123, Section 3, University Road, Touliu, Yunlin 640, Taiwan;Department of Information Management and Communication, Wenzao Ursuline College of Languages, 900 Mintsu, 1st Road, Kaohsiung 807, Taiwan;Department of Information Management, Yuanpei University, 306 Yuanpei Street, Hsin Chu 30015, Taiwan

  • Venue:
  • Information Sciences: an International Journal
  • Year:
  • 2010

Quantified Score

Hi-index 0.07

Visualization

Abstract

In the stock market, technical analysis is a useful method for predicting stock prices. Although, professional stock analysts and fund managers usually make subjective judgments, based on objective technical indicators, it is difficult for non-professionals to apply this forecasting technique because there are too many complex technical indicators to be considered. Moreover, two drawbacks have been found in many of the past forecasting models: (1) statistical assumptions about variables are required for time series models, such as the autoregressive moving average model (ARMA) and the autoregressive conditional heteroscedasticity (ARCH), to produce forecasting models of mathematical equations, and these are not easily understood by stock investors; and (2) the rules mined from some artificial intelligence (AI) algorithms, such as neural networks (NN), are not easily realized. In order to overcome these drawbacks, this paper proposes a hybrid forecasting model, using multi-technical indicators to predict stock price trends. Further, it includes four proposed procedures in the hybrid model to provide efficient rules for forecasting, which are evolved from the extracted rules with high support value, by using the toolset based on rough sets theory (RST): (1) select the essential technical indicators, which are highly related to the future stock price, from the popular indicators based on a correlation matrix; (2) use the cumulative probability distribution approach (CDPA) and minimize the entropy principle approach (MEPA) to partition technical indicator value and daily price fluctuation into linguistic values, based on the characteristics of the data distribution; (3) employ a RST algorithm to extract linguistic rules from the linguistic technical indicator dataset; and (4) utilize genetic algorithms (GAs) to refine the extracted rules to get better forecasting accuracy and stock return. The effectiveness of the proposed model is verified with two types of performance evaluations, accuracy and stock return, and by using a six-year period of the TAIEX (Taiwan Stock Exchange Capitalization Weighted Stock Index) as the experiment dataset. The experimental results show that the proposed model is superior to the two listed forecasting models (RST and GAs) in terms of accuracy, and the stock return evaluations have revealed that the profits produced by the proposed model are higher than the three listed models (Buy-and-Hold, RST and GAs).