RICON: A ML framework for real-time and proactive intervention to prevent customer churn

We consider the problem of churn prediction in real-time. Because of the batch mode of inference generation, the traditional methods can only support retention campaigns with offline interventions, e.g., test messages, emails or static in-product nudges. Other recent works in real-time churn predictions do not assess the cost to accuracy trade-off to deploy such models in production. In this paper we present RICON, a flexible, cost-effective and robust machine learning system to predict customer churn propensities in real-time using clickstream data. In addition to churn propensity prediction, RICON provides insights based on product usage intelligence. Through application on a real big data of QBO Advanced customers we showcase how RICON has achieved a top decile lift of 2.68 in the presence of strong class imbalance. Moreover, we execute an extensive comparative study to justify our modeling choices for RICON. Finally, we mention how RICON can be integrated with intervention platforms within Intuit to run large-scale retention campaigns with real-time in-product contextual helps.

Compressive Sampling Using EM Algorithm

Conventional approaches of sampling signals follow the celebrated theorem of Nyquist and Shannon. Compressive sampling, introduced by Donoho, Romberg and Tao, is a new paradigm that goes against the conventional methods in data acquisition and provides a way of recovering signals using fewer samples than the traditional methods use. Here we suggest an alternative way of reconstructing the original signals in compressive sampling using EM algorithm. We first propose a naive approach which has certain computational difficulties and subsequently modify it to a new approach which performs better than the conventional methods of compressive sampling. The comparison of the different approaches and the performance of the new approach has been studied using simulated data.