Method and device for recognizing person working outside based on bank data, and medium

Abstract

The invention discloses a method and device for recognizing a person working outside based on bank data, and a medium, and the method comprises the steps: obtaining a large amount of client data of abank, extracting client features associated with go-out tags from the client data, taking the client features as feature vectors of samples, taking the go-out tags registered by opening accounts as sample tags, and constructing a weak supervision sample set; selecting a part of samples from the weak supervision sample set, and constructing a strong supervision sample set by taking a result of manual verification as a sample label; constructing a classification model, and training the classification model by using the weak supervision sample set and the strong supervision sample set to obtain an outgoing operator identification model; and for the to-be-identified client, extracting client features from the client data, inputting the client features into the identification model for personsworking outside, and outputting to obtain whether the to-be-identified client is a person working outside. According to the method, the strong and weak supervision sets are divided, the acquisition difficulty of training samples is reduced, the diversity of the samples is ensured, the generalization performance of the recognition model is improved, and the recognition accuracy is high.

Description

technical field [0001] The present invention relates to the technical field of bank specific customer group identification, in particular to a method, device and medium for identifying migrant workers based on bank data. Background technique [0002] With the development of technology related to the financial industry, the financial industry is undergoing tremendous changes. With the rise of emerging financial companies such as consumer finance and Internet finance, commercial banks are facing severe challenges. At the same time, due to the gradual improvement of the business model of each commercial bank, the difference in business level between banks has gradually decreased, and each bank has gradually become homogeneous. It is increasingly necessary to customize relevant marketing strategies according to the characteristics of the bank's own customers. An important part of winning in fierce competition. [0003] Guizhou is a province with a large export of labor service...

AI Technical Summary

Problems solved by technology

At the same time, it is the management model of most banks to divide bank customers according to attributes such as assets, preferences, and liabilities. However, commercial bank customer data usually has high-dimensional complexity, which makes it difficult to select features.

At the same time, the accuracy of the labels recorded when opening an account cannot be guaranteed. Obtaining a large number of accurate sample labels through manual investigation will incur a large cost. If the sample size is too small, the learned model will have a large variance. , Low generalization, how to obtain samples that meet the needs of learning algorithms with as little cost as possible is full of challenges

Images