Case Study of Cluster Analysis in Intercity Passenger Rail Planning and Marketing

Recent policy and regulatory initiatives have established new momentum for intercity passenger rail among planners, policymakers, and the general public. As a result, there is a great interest in developing new passenger rail lines and expanding existing routes in intercity corridors across the country. Moving forward, there exists a need to understand how current passenger rail services are being utilized, who is riding them, and what changes could be implemented to existing routes to attract ridership — as well as to document lessons learned from existing lines that can aid service development planning for newly proposed routes. In this paper, cluster analysis is applied to passenger survey data obtained in 2007 from riders of three Amtrak routes in the state of Michigan, USA. Cluster analysis is a multivariate data analysis method used extensively in marketing and customer profile research which seeks to identify similarities among potential customers that are not immediately evident using traditional grouping techniques. Data used in the formation of the passenger clusters include traveler alternatives to the passenger rail service and the importance of service attributes, on-board activities, and station amenities. These variables and other data from the passenger survey are then used to characterize the identified clusters in terms of what kinds of passengers are in each cluster and how these passengers benefit from the rail service. The passenger clusters are also analyzed for their potential response to service improvements such as reduced travel time, increased service frequencies, or improved intermodal connections. The findings of this case study can be applied in a number of activities related to intercity passenger rail service planning for existing as well as proposed routes. The findings provide valuable insight into the needs and preferences of current passengers and can be used to formulate strategies for equipment investments or the development of new on-board amenities. From a policy perspective, passengers’ preferences for alternative travel modes in the absence of the rail service reveal how the rail service supports intercity mobility for each of the clusters. Finally, from the cluster profile, potential strategies to attract new riders can be identified. The results show that clustering analysis methodology applied in this case study is a valuable tool for intercity passenger rail planning.