Financial market subject credit assessment method and system based on neural network

• Main Authors: XIAO RUI, WANG JIANQIANG, LIU JING, LIU HAIBIN
• Format: Patent
• Language: Chinese; English
• Published: 12.07.2024
• 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 relates to a financial market subject credit assessment method and system based on a neural network, and belongs to the technical field. The method comprises the steps that market credit information is acquired, and after the market credit information is cleaned, credit data based on market subject cognition are obtained; taking credit data as an input variable, performing fuzzification processing on the input variable, converting an actual value of the input variable into a membership value in a fuzzy set, and setting a membership function for learning the fuzzy set; establishing a credit evaluation model based on a fuzzy neural network; performing iterative training on the credit evaluation model by acquiring historical data, calculating an output error of each layer in the iterative process, reversely propagating the output error along the network through an error function, and updating the weight of each node layer by layer; and performing credit risk assessment on the credit data acquired i