Using data mining techniques for profiling profitable hotel customers: An application of RFM analysis

• Data mining techniques may enable managers to identify the most profitable customers in the hospitality sector.
• This study employs RFM analysis for the identification of profitable customers in the context of CRM.
• By data obtained from a five-star hotel chain's CRM system, RFM analysis results offered eight customer groups who have specific characteristics.
• Majority of the customers were identified as ‘Lost Customers’, who stay for shorter periods and spend less than other groups. The authors offered CRM strategies for these and other customer groups.

This study focuses on profiling profitable hotel customers by RFM analysis, which is a data mining technique. In RFM analysis, Recency, Frequency and Monetary indicators are employed for discovering the nature of the customers. In this study, the actual CRM data belong to three five-star hotels operating in Antalya, Turkey were used. Analysis results showed that 369 profitable hotel customers were divided into eight groups: ‘Loyal Customers’, ‘Loyal Summer Season Customers’, ‘Collective Buying Customers’, ‘Winter Season Customers’, ‘Lost Customers’, ‘High Potential Customers’, ‘New Customers’, and ‘Winter Season High Potential Customers’. Majority of the customers (36%) were positioned at ‘Lost Customers’ segment, who stay for shorter periods, spend less than other groups and tend to come to the hotels in the summer season. Results indicated that RFM effectively clusters the customers, which may lead hotel top managers to generate new strategies for increasing their abilities in CRM.