Pooling method and device for retail risk exposure, computer equipment and medium

Abstract

The embodiment of the invention provides a pooling method and device for retail risk exposure, computer equipment and a medium, and relates to the field of automatic programming. The method comprises the steps of obtaining a sample used for constructing a model in a feature wide table corresponding to retail risk exposure; performing high-level subdivision on the sample in response to user configuration; and performing layer-by-layer subdivision on samples in the sample set obtained by high-level subdivision according to the pooling risk factors, and generating a retail risk exposure pooling model based on a high-level subdivision result and a layer-by-layer subdivision result. According to the embodiment of the invention, standardization and automation of construction of the retail risk exposure pooling model are realized, and the development time of the retail risk exposure pooling model is greatly shortened; in the aspect of model iteration, iteration can be performed in response to user configuration so as to quickly respond to business requirements, and the model iteration efficiency is improved; and the modeling process risk is controlled to a certain extent, and errors caused by manual operation are reduced.

Description

technical field [0001] The embodiment of the present invention relates to the field of automatic program design, in particular to information processing and bank risk management technology, and in particular to a method, device, computer equipment and media for pool segmentation of retail risk exposure. Background technique [0002] The sub-pool system of retail risk exposure is an important part of the credit risk internal assessment method, which is mainly used in the formulation of risk management related policies, credit approval process, economic capital allocation and risk governance. Risk pooling is to comprehensively consider the characteristics of retail risk exposures such as age, application score, and behavior score, and combine debts with consistent risk characteristics based on statistical test indicators, and then describe the risk parameters of corresponding exposures through statistical indicators of different pools measurement technology. [0003] The anal...

AI Technical Summary

Problems solved by technology

[0003] The analysis and construction of the current retail PD (Probability of Default) pooling model is mainly done by modelers manually. There are many analysis methods and steps, a large amount of analysis work is repeated, and the modeling efficiency is low. The construction and iteration cycle is long, and there are manual analysis errors, the quality of the model is difficult to control uniformly, and it is difficult to quickly respond to the risk management needs of supervision and business

Images