Banking business performance contribution information prediction method and device

• Main Authors: ZHENG JIEFENG, SHUAI FEISHAO, WEN LIMING
• Format: Patent
• Language: Chinese; English
• Published: 13.11.2020
• 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; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention provides a method and a device for predicting banking business performance contribution information, which can be applied to the financial field or other fields. The method comprises thesteps of obtaining service data; asset business data, debt business data and corresponding feature information are obtained through data processing; taking the obtained data as a training sample, andtraining a pre-established first machine learning model to obtain an initial asset and debt configuration model and a corresponding training result; taking the training result as a training sample, and training the second machine learning model to obtain an initial internal fund transfer cost pricing model; and taking a training result of the initial internal fund transfer cost pricing model as acalculation parameter, and performing calculation by using a rolling difference algorithm to obtain business performance contribution information. According to the method, the characteristic value extraction, the machine learn