Modelling Enterprise’s Coordinated Development Strategy with a Soft Fuzzy Rough Set

Algorithm 1

	Input: training sample set and test sample set .
	Output: effect class i for each test sample .
	Step 1: calculate the effect number.
	Step 2: for each test sample , the following treatment shall be conducted:
(1)	For each kind class j ∈ Y (Y = {y1, y2, …, yk}), calculate the distance between and per sample in different kinds, and obtain the candidate distance.
(2)	For the obtained candidate distance sequence, calculate the corresponding soft distance for kind class j according to equation (3).
(3)	It can be known from equations (6) and (7) that the value of obtained in equation (1) to soft distance for the sample in different kinds is equal to that for its corresponding lower approximation membership degree. Thus, the lower approximation membership degree of sample to each kind was obtained.
(4)	Corresponding kind strategy class t at the time of the maximum of membership degree shall be selected and returned, and the effect for sample can be obtained.
	Step 3: repeat Step 2 until a kind strategy is obtained for each test sample.