Abnormal consumption detection method based on multi-dimensional data analysis

• Main Author: ZHANG CHANGZHENG
• Format: Patent
• Language: Chinese; English
• Published: 14.11.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; 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 provides an abnormal consumption detection method based on multi-dimensional data analysis. Automatically acquiring reimbursement fee information in the associated reimbursement system to form a database, wherein the database at least comprises payment time, payment modes and suppliers in the reimbursement fee information; taking time as a longitudinal axis, and respectively constructing change trends of the same supplier, the same payment time and different payment modes in a set time period to form a feature project; inputting the feature engineering into a Gaussian kernel function, and mapping the features of the feature engineering into a high-order space by the Gaussian kernel function to obtain a nonlinear relationship so as to form a preliminary detection model; dividing the abnormal consumption detection model into a training set and a test set, verifying the abnormal consumption detection model through k-fold cross validation, and obtaining the abnormal consumption detection model after