Label classification and quantitative analysis method based on credit big data

• Main Authors: SHA LINGFENG, GUO JIAJIE, DONG JUN, WANG LIUXIA, LIU JING, YE LIN, RAN ZUOZHOU
• Format: Patent
• Language: Chinese; English
• Published: 28.04.2020
• 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 label classification and quantitative analysis method based on credit big data, and relates to the technical field of enterprise credit evaluation. The label classification and quantitative analysis method based on credit big data comprises the following steps: S1, obtaining and integrating credit record data; s2, cleaning the data; s3, screening and distinguishing identity credit information, capability credit information and willingness credit information; and S4, determining a feature type according to the credit data type. According to the method, traditional machine learning models such as a decision tree are used; natural language processing methods such as Jieba word segmentation and word2vec models and deep learning models such as an LSTM neural network areadopted; and a classification method of credit research results, identity credit information, capability credit information and willingness credit information is added to form a set of complete method for establishing social