Customer Classification Method and System Based on Adaptive Particle Swarm

Abstract

Embodiments of the present invention provide a method and system for classifying clients based on an adaptive particle swarm. The method includes: dynamically adjusting the inertia weight of a standard particle swarm algorithm according to the change characteristics of the particles in the particle swarm to obtain an improved Particle swarm optimization algorithm; according to the improved particle swarm optimization algorithm, update the particle position, and perform out-of-bounds processing on the particle position to obtain multiple cluster centers; use the multiple cluster centers as the K-Means clustering algorithm to obtain the customer classification model of the adaptive particle swarm; according to the customer classification model of the adaptive particle swarm, perform clustering processing on the purchase behavior characteristic data set of the target customer group to obtain the customers of the target customer group Classification results. The embodiment of the present invention improves the convergence precision and efficiency of the particle swarm algorithm, avoids the problem of local minimum value, and can effectively and accurately divide consumer customers.

Description

technical field [0001] The invention relates to the technical field of customer classification management, in particular to a customer classification method and system based on an adaptive particle swarm. Background technique [0002] The classification of retail customers is the basis for the retail industry to determine products and services, it is a direct reflection of customer consumption behavior, and it is also the premise for the retail industry to establish one-to-one marketing with retail customers and provide personalized services to retail customers. In the fierce market competition, the classification of retail enterprise customers can enable retail enterprises to improve their competitiveness and expand market share, so as to allocate resources to a certain customer category. [0003] K-means clustering algorithm is a commonly used distance algorithm in customer classification. The algorithm is reliable in theory, simple in principle and fast in operation. It h...

AI Technical Summary

Problems solved by technology

However, the existing K-Means clustering is also sensitive to the initial value, easy to fall into a local optimal solution, needs to specify the number of clusters in advance, and is not suitable for processing mixed data.

Images