Adapted TSK type fuzzy rule based system for Stock Market Analysis

In this paper, Nero-fuzzy Inference System adoped on a Takagi-Sugeno-Kang (TSK) type Fuzzy Rule Based System is developed for stock price prediction. The TSK fuzzy model applies the tachnical indexas the input variables and the consequent part is a linear combination of the input variables. Fuzzy Mean clustering implemented for identifying number of rules. TSK parameters tuned by Adaptive Nero-Fuzzy Inference system (ANFIS). Proposed model is tested on the Taiwan Stock Exchange (TSE) and with high accuracy near by 98.7% has successfully forecasted the price variation in TSF index through the intensive experimental test from different sectors. Nowadays because of the complicated nature of making decision in stock market and making real-time strategy for buying and selling stock via porfolio selection and maintenance, many research papers has involoved stock price prediction issue; therfore we have considered comparison between the proposed model and some predefine models in the literature.

کلیدواژه ها:

FCM clustering ، Fuzzy rule based systems ، Forecasting ، stock market ، forecasting accuracy ، ANFIS