Customer segmentation using K-means clustering and the adaptive particle swarm optimization algorithm

The improvement of enterprise competitiveness depends on the ability to match segmented customers in a competitive market. In this study, we propose a customer segmentation method based on the improved K-means algorithm and the adaptive particle swarm optimization (PSO) algorithm. The current PSO algorithm can easily fall into a local extremum; thus, adaptive learning PSO (ALPSO) is proposed to improve the optimization accuracy. On the basis of the analysis of population-based optimization, the inertia weight, learning factors, and the position update method are redesigned. To prevent the K-means clustering algorithm from depending on initial cluster centres, the ALPSO algorithm is used to optimize the K-means cluster centres (KM-ALPSO). Aimed at the issue of clustering the actual grape-customer consumption mixed dataset, factor analysis is used to extract numerical variables. We then propose a dissimilarity measurement method to cluster the mixed data. We compare ALPSO with several parameter update methods. We also conduct comparative experiments to compare KM-ALPSO on five UCI datasets. Finally, the improved KM-ALPSO (IKM-ALPSO) clustering algorithm is applied in customer segmentation. All results show that the three proposed methods outperform existing models. The experimental results also demonstrate the effectiveness and practicability of IKM-ALPSO for customer segmentation.