Agricultural operation subject credit evaluation model construction method, terminal and storage medium

Fecha de publicación: 27/05/2022
Fuente: Wipo "BigData"
The invention relates to the technical field of big data processing, in particular to an agricultural operation subject credit evaluation model construction method, a terminal and a storage medium, and the method comprises the steps: firstly obtaining a credit score, a credit investigation information set and a basic model of a sample, then grouping the sample into an adjustment group and an inspection group, the correlation weight of each relational expression in the basic model is adjusted through the adjusting group, and fitting of the samples is achieved; and then checking whether the samples of the non-approximate adjustment group can be accurately scored through the checking group, if not, changing the structure of the basic model, returning to the weight adjustment step, constructing the model again, and only if the basic model passes the checking of the checking group and the error is smaller than a threshold value, taking the basic model as a credit evaluation model. Therefore, the method provided by the embodiment of the invention can effectively avoid the problems that the scoring accuracy is high only for the samples and the use effect is poor after the method is put into use.