An uncertain possibility-probability information fusion method under interval type-2 fuzzy environment and its application in stock selection

Abstract

Stock selection is one of the most significant topic in investment decision problems, which can be solved through aggregating financial variables of the enterprizes. Because of the complexity and ambiguity of the stock exchange market, crisp financial ratios and their corresponding probabilities could not represent the fluctuation and ambiguity over a period. Interval type-2 fuzzy numbers have advantages in modeling uncertainty over type-1 fuzzy sets(T1 FSs), and have gained popularity in investment decisions. In this paper, we propose an uncertain possibility-probability information fusion method for stock selection under interval type-2 fuzzy environment. Firstly, based on the expected value and variance of the evaluations, both the interval type-2 fuzzy evaluations and probabilities are constructed. Secondly, considering the idea of probability for a fuzzy event, the fused probability with possibility-probability information is suggested to handle the uncertainty under interval type-2 fuzzy environment, and the entropy weight is used to reflect the importance degree for each criteria. Thirdly, the aggregation model based on the concept of the relative closeness to the ideal alternatives is used to compare the alternatives. Finally, an application have been performed in stock selection of real estate industry in China.