Leveraging fine-grained mobile data for churn detection through Essence Random Forest

The rise of unstructured data leads to unprecedented opportunities for marketing applications along with new methodological challenges to leverage such data. In particular, redundancy among the features extracted from this data deserves special attention as it might prevent current methods to benefit from it. In this study, we propose to investigate the value of multiple fine-grained data sources i.e. websurfing, use of applications and geospatial mobility for churn detection within telephone companies. This value is analysed both in substitution and in complement to the value of the well-known communication network. What is more, we also suggest an adaptation of the Random Forest algorithm called Essence Random Forest designed to better address redundancy among extracted features. Analysing fine-grained data of a telephone company, we first find that geo-spatial mobility data might be a good long term alternative to the classical communication network that might become obsolete due to the competition with digital communications. Then, we show that, on the short term, these alternative fine-grained data might complement the communication network for an improved churn detection. In addition, compared to Random Forest and Extremely Randomized Trees, Essence Random Forest better leverages the value of unstructured data by offering an enhanced churn detection regardless of the addressed perspective i.e. substitution or complement. Finally, Essence Random Forest converges faster to stable results which is a salient property in a resource constrained environment.