Shopping mall commodity sales volume prediction method, device and apparatus based based on data mining

• Main Authors: YANG SENBIN, ZHANG XIAOBO
• Format: Patent
• Language: Chinese; English
• Published: 19.02.2019
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention discloses a shopping mall commodity sales volume prediction method based on data mining, which includes obtaining the sales related data to be predicted; taking the sales-related data tobe predicted as an input quantity to obtain a first prediction result through a stochastic forest algorithm; obtaining a second prediction result by k-nearest neighbor algorithm with the sales-related data to be predicted as an input quantity; performing weighted averaging on the first prediction result and the second prediction result according to the stochastic forest algorithm score weight andthe k-nearest neighbor algorithm score weight to obtain commodity sales forecast data; wherein the stochastic forest algorithm score weight and the k-nearest neighbor algorithm score weight are scoreweights obtained by training and learning the training data set. The invention can efficiently obtain a high-accuracy prediction result, meanwhile, the invention combines the prediction results of the existing two algorithms t