Churn modeling with probabilistic meta paths-based representation learning

Abstract

Finding structural and efficient ways of leveraging available data is not an easy task, especially when dealing with network data, as is the case in telco churn prediction. Several previous works have made advancements in this direction both from the perspective of churn prediction, by proposing augmented call graph architectures, and from the perspective of graph featurization, by proposing different graph representation learning methods, frequently exploiting random walks. However, both graph augmentation as well as representation learning-based featurization face drawbacks. In this work, we first shift the focus from a homogeneous to a heterogeneous perspective, by defining different probabilistic meta paths on augmented call graphs. Secondly, we focus on solutions for the usually significant number of random walks that graph representation learning methods require. To this end, we propose a sampling method for random walks based on a combination of most suitable random walk generation strategies, which we determine with the help of corresponding Markov models. In our experimental evaluation, we demonstrate the benefits of probabilistic meta path-based walk generation in terms of predictive power. In addition, this paper provides promising insights regarding the interplay of the type of meta path and the predictive outcome, as well as the potential of sampling random walks based on the meta path structure in order to alleviate the computational requirements of representation learning by reducing typically sizable required data input.