Enterprise supplier classification method based on local preserving projection analysis

• Main Authors: MA CHENGLIN, TAO SIRUI, WANG RUOTONG, SHEN WEI, WANG LIHAI, TAO XINMIN, CHANG RUI
• Format: Patent
• Language: Chinese; English
• Published: 18.08.2017
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

Provided is an enterprise supplier classification method based on local preserving projection analysis. The enterprise supplier classification method is characterized in that the method includes the following steps of (1) determining the supplier evaluation criterion and classifying the output and input indexes; (2) taking the reciprocal of the input index obtained in step (1) and performing the normalization processing on all the indexes by means of a maximum and minimum method, and making the range within [0, 1]; (3) calculating the weighted adjacency matrix W and the metric matrix D by means of the normalized data matrix X obtained in step (2) and obtaining the corresponding Laplace matrix L; (4) obtaining the generalized eigenvalues and eigenvectors of matrix A relative to matrix B by means of the matrix structure A=XLXT, B=XDXT obtained in step (3), performing the ascending sort on the eigenvalues, and taking the eigenvector corresponding to the minimum eigenvalue; and (5) calculating the projection of t