Analysis of Customer Journeys Using Prototype Detection and Counterfactual Explanations for Sequential Data

Recently, the proliferation of omnichannel platforms has attracted significant interest in the customer journey, particularly in terms of their role in developing marketing strategies. Although some attempts have been made to quantitatively analyze customer journeys, methods that facilitate the identification and visualization of prototype sequences—and their practical application in strategic use—remain scarce, primarily because of the complexity and inherently sequential nature of the data. In this study, we propose a novel approach comprising three steps for analyzing customer journeys. First, the distances between sequential data were defined and used to identify and visualize representative sequences. Second, the likelihood of purchasing was predicted based on this distance. Third, if a sequence suggests no purchase, counterfactual sequences can be recommended to increase the probability of purchase using the proposed method, which extracts counterfactual explanations for sequential data. We conducted a survey and analyzed the collected data; the results revealed that typical sequences could be extracted, and parts of those sequences important for purchase could be detected. We believe that the proposed approach can support improvements in marketing activities.