Implementation of Churn Prediction and its Efficiency Estimation
Churn Prediction is one of the most popular Big Data use cases in business. This case is decided by everyone from internet-shops, telecom operators to game developers and ticket services. It is widely thought, that churn prediction is traditionally well solved by methods of machine learning. In that report, we would discuss how to compare metrics of machine learning (AUC ROC, F1, Logloss) with business metrics. How to make an experiment in order to estimate the effect of introducing machine learning. Which characteristics should a business have so that investments into introducing the machine learning would recover?
Alexei Chernobrovov, Ph.D. in maths. Consultant on Data Science. Worked with some well-known companies in Russia and CIS: Mail.ru Group / Ok.ru, Mazda (Russia), National Settlement Depository (Russia), Pult.ru, SkyEng. Member of the Expert Council of the Runet Prize. Speaker of all top conferences on marketing, analytics and data science in Russia: Oborot.ru, Datafest, Locomotiv, GoAnalytics, etc.
