[Retracted] The Scoring Mechanism of Players after Game Based on Cluster Regression Analysis Model

Algorithm 1

For the set of multiple linear regression models , the accuracy of clustering is limited to T.

(1)	For i = 1, 2,...,N, repeat the following steps (2)–(8);
(2)	Select any model from the model set A and record it as Mi;
(3)	If i = 1, separate Mi into one category, and make A = A − M, and then perform step (2); otherwise, directly perform step (4);
(4)	Calculate the distance between Mi and the centroids of each clustering model set, select the model set with the minimum distance from Mi, and record the model set as Aj, and the distance between the two as Dij, and perform step (5);
(5)	If Dij < T, classify Mi as model set Aj and make A = A-Mi; perform step (6); otherwise, perform step (8);
(6)	If the mass center of Aj is not fixed, adjust the mass center and radius of Aj, record the new radius as R (Aj), and carry out step (7). Otherwise, perform step (2).
(7)	If R (Aj) > T, fix the Aj center of mass and carry out step (2). Otherwise, perform step (2) directly.
(8)	Separate Mi into one group and make A = A-M. Perform step (2);
(9)	Finally, the centroid of each model set is readjusted;
(10)	The algorithm ends.