Marketing segmentation using the particle swarm optimization algorithm: a case study

Traditionally, most companies use marketing campaigns to recruit new customers or retain old customers. Customer segmentation is an important technique for a marketing campaign to target the right customers. Most previous clustering algorithms have drawbacks, such as being stuck at local minima. To overcome such drawbacks this study attempts to develop a consumer segmentation model using a swarm intelligence based algorithm, called Particle Swarm Optimization (PSO). The swarm intelligent algorithm has the advantage of using fewer parameters to reach a global optimal solution. In general, the value of customer segmentation is judged by the customer’s lifetime value. Based on many previous researches, the RFM (Recency, Frequency, and Monetary) model is the most well-known model used to compute customer lifetime value. This study calculates the RFM model from a data set into value-based information. Based on this value-based information the PSO algorithm is able to cluster consumers to find customers likely to be the most profitable and valuable. To demonstrate the effectiveness of PSO, we present an empirical case study involving a retail automobile marketing campaign. We compare the performance of the PSO customer segmentation algorithm against that of other segmentation algorithms (K-mean and self-organizing map (SOM)) and hybrid algorithms. The study finds the hybrid S-KMeans -PSO (SOM, K-Means and PSO) algorithms can reach the best performance. Finally, this study proposes effective marketing strategies for two segmented profitable and valuable customers.