Uncovering Characteristic Paths to Purchase of Consumers
51 Pages Posted: 18 Jun 2015 Last revised: 6 Jan 2017
Date Written: January 20, 2016
Managers have long been interested in understanding the consumers’ purchase decision process, commonly referred to as the path to purchase, so that they can develop effective marketing strategies. Despite a strong interest in this concept, there are few published approaches to empirically identify consumers’ path to purchase in terms of a sequence of different types of activities that begin with a marketing stimulus and lead to a purchase. We offer one of the first empirical definitions of path to purchase and a methodology to identify such paths from commonly available CRM touch point data. We propose the Clustered Generalized Multivariate Autoregressive model (CGMAR), an extension of the VAR model, to capture the interactions among distinct but potentially simultaneous activities of a consumer over time. Using the proposed model, we obtain the characteristic path to purchase behavior, defined as a relatively small number of activity sequences leading to purchases that represent a consumer’s most common responses to a marketing stimulus. We embed the CGMAR model in a mixture model that endogenously identifies segments of consumers who follow similar paths to purchase. We apply our methodology to a dataset from a multi-channel North American Specialty Retailer to uncover the distinct paths of six consumer segments: fully engaged shoppers, digitally driven shoppers, research online-purchase offline (ROPO) shoppers, highly targeted loyal shoppers, holiday shoppers, and disengaged offline shoppers. Using out-of-sample forecasts, we demonstrate improved predictions of future purchases compared to extant methods. Finally, we perform policy simulations to show that managers can use the uncovered path to purchase information to dynamically optimize marketing campaigns for each segment.
Keywords: Path to purchase, Generalized multivariate autoregressive (GMAR) model, Customer segmentation, dynamic programming model, optimal marketing policy
Suggested Citation: Suggested Citation