A case study of applying spectral clustering technique in the value analysis of an outfitter’s customer database

This case study applies the spectral clustering technique in the value analysis of the customer database of an outfitter in Taipei, Taiwan. By considering gender, birth date, zip code, shopping frequency, and the total spending, the spectral clustering analysis found six clusters among 551 member customers from the company’s database. In addition to the clustering analysis, different promotion strategies based on two recency-frequency-monetary based loyalty strategies matrices for the members of different clusters are provided. The analysis shows that Clusters 5 and 3 are the two most important groups and one group of customers may have to be abandoned to save the company’s marketing resources.