Value evaluation method, device and equipment based on XGBoost model

Abstract

The invention discloses a value evaluation method, device and equipment based on an XGBoost model, relates to the technical field of computers, and can solve the problem of low accuracy of value evaluation for clients. Comprising the following steps: training an XGBoost model by using first feature data of a target subject, and determining a first feature importance value of a first feature item corresponding to the first feature data by using the trained XGBoost model; extracting a second feature item of which the first feature importance value is greater than a preset feature importance threshold value and the feature evaluation index is greater than a preset feature evaluation index threshold value from the first feature item; inputting second feature data corresponding to the second feature item into the trained XGBoost model to obtain a second feature importance value of the second feature item; and normalizing the second feature importance value into a feature weight value, and calculating a value evaluation score of the target subject according to the feature weight value.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to a value evaluation method, device and equipment based on an XGBoost model. Background technique [0002] Customer value evaluation starts from the perspective of the enterprise, and calculates the value that the customer can create for the enterprise based on the basic characteristics, consumption characteristics, and behavioral characteristics of the customer. It is an important basis for the enterprise to segment customers and refine marketing. [0003] The traditional customer value evaluation method is mainly the RFM value model, which describes the customer's value status through three indicators: the latest purchase time R (Recency), the purchase frequency F (Frequency) and the purchase amount M (Monetary) of a customer. , but the RFM value model only uses 3 dimensions, which contains limited information, does not explain enough business problems, and has low ev...

AI Technical Summary

Problems solved by technology

[0004] In view of this, this application provides a value evaluation method, device and equipment based on the XGBoost model, which relates to the field of computer technology and can solve the problem of low accuracy of value evaluation for customers

Images