Mixed weight kernel entropy component analysis-based enterprise supplier evaluation method

• Main Authors: TAO SIRUI, WANG RUOTONG, GAO SHAN, SHEN WEI, LI CHENXI, TAO XINMIN, CHANG RUI
• Format: Patent
• Language: Chinese; English
• Published: 15.09.2017
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention discloses a mixed weight kernel entropy component analysis-based enterprise supplier evaluation method. The method is characterized by comprising the following steps of (1) determining supplier evaluation criteria, and performing output and input index classification; (2) taking a reciprocal of an input index obtained in the step (1) and performing normalization processing on all indexes by utilizing a maximum and minimum method to enable a range to be [0,1]; (3) performing kernel entropy component analysis on data obtained in the step (2) to calculate out a kernel matrix K corresponding to a sample matrix X; (4) decomposing the kernel matrix obtained in the step (3), working out eigenvalues and eigenvectors, and selecting out maximal first d eigenvalues corresponding to values defined in the specification and corresponding eigenvectors to perform projection; and (5) calculating weight vectors of corresponding new base coordinates, and performing weighted summation with projection values obtaine