Abstract: Customer churn (cancellation) is the bane of all businesses with recurring revenue,. and data can help understand the causes of churn and take action to reduce it. But there are many misconceptions about churn and pitfalls in actually using data driven insights to reduce churn. The foundation to fight churn with data requires creating a library of customer metrics. Customer metrics are used as features for machine learning algorithms and by themselves can be used to define segments for data driven churn reducing interventions. Churn reducing interventions include targeted messaging that may be informational and intended to drive product usage, or contain offers intended to drive up-sell (more expensive plans) and cross-sell (related products and add ons). A recent development in the field is the use of reinforcement learning to replace composite systems built from supervised models combined with A/B tested intervention parameters.
This workshop will teach hands-on coding techniques covering all the foundations of a complete churn fighting data pipeline including churn measurement, feature engineering from raw data, data set creation, and machine learning. The workshop is taught using Python and SQL from the open source fightchurn package (pypi pypi.org/project/fightchurn/, github github.com/carl24k/fight-churn.) Participants should come with their own laptop prepared with Python and an IDE such as PyCharm or VSCode that will allow them to put breakpoints in code that will be demonstrated and discussed. During the workshop participants will generate a simulated database of customers, product usage and churn and then use it to practice various churn analysis, feature engineering and machine learning techniques. These techniques are based on the dozens of predictive churn analyses Dr. Gold has done for customers of Zuora (www.zuora.com) as Chief Data Scientist, and features material from his book: Fighting Churn With Data. For more information see www.fightchurnwithdata.com.
Bio: Carl Gold is currently the Data Science Director at OfferFit.ai, an AI-as-a-Service reinforcement learning engine that maximizes customer upsell and retention. Before coming to OfferFit, Carl was Chief Data Scientist of Zuora, the Subscription Economy leading billing platform. Based on his experiences fighting churn for SaaS companies during his time at Zuora, Carl wrote the first book dedicated to customer churn analytics and data science: "Fighting Churn With Data". Carl has a PhD from the California Institute of Technology and first author publications in leading Machine Learning and Neuroscience journals.