We study the shopping patterns of online customers and how a series of store visits lead to purchase conversions. Toward this end, we develop a dynamic timing model that explicitly captures the lumpy patterns of online store visits. Our model is based on the notion that the arrival process of customer visits consists of multiple visit clusters with relatively short intervisit times within a cluster and a longer intervisit time between clusters. Because the start and the end of each visit cluster are unobserved, we employ a changepoint modeling framework and statistically infer the cluster formation on the basis of customer visit patterns through data augmentation in Bayesian approach. Our model provides a set of novel inferences about the patterns underlying online shopping behavior. In our empirical analysis, we find strong empirical evidence of lumpy shopping patterns by online customers with significant heterogeneity in the extent of the lumpiness. As part of our substantive contribution, we highlight how the clustered-based inferences of store visit patterns can be leveraged to examine conversion behavior of online customers.