Customer category determination method and device and storage medium

Abstract

The embodiment of the invention provides a customer category determination method and device and a storage medium, and can be applied to the technical field of artificial intelligence. The method comprises: obtaining a preset number of customer samples, wherein the customer samples comprise positive samples and negative samples, the positive sample indicates that the customer category is a bad customer, and the negative sample indicates that the customer category is a common customer; dividing the negative samples into a plurality of groups of negative samples, and combining each group of negative samples with the positive samples to form a sample subset to obtain a plurality of sample subsets; for different sample subsets, extracting feature vectors of customer samples in each sample subset from different dimensions; based on a preset objective function, fitting the feature vector of the customer sample in each sample subset and the customer category represented by the customer sample to obtain a classification condition of the customer category under each dimension; and determining the category of the target customer according to the classification condition of the customer category under each dimension, so as to improve the accuracy of customer category determination.

Description

technical field [0001] The embodiments of this specification relate to the technical field of artificial intelligence, and in particular to a method, device and storage medium for determining a customer category. Background technique [0002] With the development of the financial industry, the balance of payments business accounts for an increasing proportion of financial institutions. Due to the complexity of the balance of payments business scenario, it is difficult to find bad customers in advance. If the bad customers become more serious, it will have an adverse impact on financial institutions, leading to a decline in the reputation of financial institutions and a decrease in profits. With the development of artificial intelligence technology, it is worth trying to apply machine learning technology to predict the classification of international balance of payments customers. [0003] Through machine learning technology, modeling and learning can be carried out from a l...

AI Technical Summary

Problems solved by technology

First, the characteristics of samples in the balance of payments scenario contain a lot of information, such as international trade information, enterprise information, and business owner information. The existing mainstream methods directly stitch these different types of information into sample characteristics. As a result, on the one hand, the feature dimension of the sample is particularly large, which is easy to cause the "dimension disaster problem"; on the other hand, the feature scale and meaning of different categories of features often vary greatly, and direct splicing together tends to make them lose their original physical meaning , so that the model does not achieve the expected effect

Second, the existing mainstream methods treat the BOP customer classification problem as a general category-balanced classification problem. In fact, in the BOP customer classification scenario, the proportion of bad customers is often very low, and the positive and negative categories The sample size is very unbalanced

If it is treated as a class balance problem, the effect is not good, and in this scenario, more attention should be paid to the minority class samples, that is, the model should predict the bad samples as accurately as possible while ensuring the accuracy rate, and the existing methods cannot meet this requirement.

Images