Predictive Churn Analytics using H2O and IBM Data Science Experience
Determining whether or a not a customer will become a churner (i.e., no longer remain a customer) is fairly straightforward in subscription models, but a bit more challenging in non-subscription models. In subscription models, a customer churns when they request cancellation of their subscription. In non-subscription models, however, you need to analyze your customer’s behavioral tendencies in order to identify potential churn (e.g., the amount of time since he last used the company’s services/products). The goal is to then determine the specific point when your customer will no longer use your services or products.
Key Point of Presentation:
· IBM DSX Overview
· Predictive churn modeling with Spark Scala
· Build predict models with H2O Sparkling Water using R
· Modeling with H2O Flow
· Deploy a predictive model with Play Scala
Ndjido Ardo BAR, is a Senior Data Science consultant at Davidson UAE working in a project related to Dubai Smart City.
He started his career as a researcher at Pasteur Institute in BioStatistics. In 2011 he co-founded a startup specialised in realtime agriculture market (MLouma). In late 2012, Ndjido joined Bearing Point a french consulting company as a Data Scientist in its Machine Learning team named Hypercube. In late 2015, Ndjido joined AXA France as a Senior Data Scientist and delivered a Credit Scoring model.
He earned a Master Degree in Applied Mathematics at Gaston Berger University in Senegal and loves functional programming like Scala to deliver most of Data Science project