Combination of individual and group patterns for time-sensitive purchase recommendation

Due to the availability of large amounts of data, recommender systems have quickly gained popularity in the banking sphere. However, time-sensitive recommender systems, which take into account the temporal behavior and the recurrent activities of users to predict the expected time and category of next purchase, are still an active field of research. Many researchers tend to use population-level features or their low-rank approximations because the client's purchase history is very sparse with few observations for some time intervals and product categories. But such approaches inevitably lead to a loss of accuracy. In this paper, we present a generative model of client spending based on the temporal point processes framework. The model is built in the way, to bring more individuality for the clients' purchase behavior which takes into account individual purchase histories of clients. We also tackle the problem of poor statistics for people with a low transactional activity using effective intensity function parameterizations, and several other techniques such as smoothing daily intensity levels and taking into account population-level purchase rates for clients with a small number of transactions. The model is highly interpretable, and its training time scales linearly to millions of transactions and cubically to hundreds of thousands of users. Different temporal-process models were tested, and our model with all the incorporated modifications has shown the best results in terms of both error of time prediction and the accuracy of category prediction.