Analyzing browsing across websites by machine learning methods

The increasing importance of online distribution channels is paralleled by a rising interest in gaining insights into the customer journey and browsing behavior. We evaluate several machine learning methods (latent Dirichlet allocation, correlated topic model, structural topic model, replicated softmax model) with respect to their ability to reproduce the browsing behavior of households across websites. In addition, we compare these machine learning methods to a related classical technique, singular value decomposition. In our study, the replicated softmax model outperforms latent Dirichlet allocation, but the correlated topic model attains the overall best performance. Compared to singular value decomposition both the correlated topic model and the replicated softmax model lead to a more efficient compression of web browsing data. On the other hand, singular value decomposition surpasses latent Dirichlet allocation. We interpret results of the correlated topic model and the replicated softmax model by determining combinations of topics or hidden variables that are heterogeneous with respect to visited websites. We show that decision makers should not rely on bivariate measures of site visits, as these do not agree with measures of interdependences between sites that can be inferred from the correlated topic model or the replicated softmax model. We investigate how well topics or hidden variables measured by these methods predict yearly household expenditures. The correlated topic model leads to the best predictive performance, followed by the replicated softmax model. We also discuss how the replicated softmax model can be used to support online marketing decisions of websites.