This paper studies the dynamics of online purchase patterns, focusing on the impact of the channel used on conversion probability, as well as the transition of channel use over time. A novel data set from a major Chinese online travel agency is used for analysis, consisting of four months of data with 24,337 store visits through three types of channels: direct visit, search advertising and referral. Results of a Bayesian multinomial logit model show that the search channel significantly affects consumers’ conversion probability, and show a high degree of inertia in channel use. This finding contrasts sharply with suggestions of previous research that most future purchases will converge to the direct-visit channel.