Applying Data Mining and RFM Model to Analyze Customers' Values of a Veterinary Hospital

Due to fierce competition, veterinary hospitals have to maintain good relationship with their existing customers and attract new customers. In order to identify critical customers, data mining techniques particularly cluster analysis are viewed as a vital tool to facilitate customer relationship management. This study uses a veterinary hospital located in Taichung City, Taiwan as an example by analyzing its transactions data focusing solely on dogs in 2014 with 4,472 customers. Recency, frequency, and monetary are the three input variables for cluster analysis. A combination of self-organizing maps and K-means method is used for cluster analysis. The results show that seven out of twelve clusters are found to be the best or loyal customers, while three clusters are uncertain or lost customers. Two clusters with relatively higher recency values than average can be viewed as new customers. When customers are classified, this veterinary hospital can provide different marketing strategies to meet different customer needs.