This guide illustrates how to combine churn and offer taker modeling for strategic customer retention.
Build a churn model for predicting if an active customer will disconnect a service within the next 30 days.
Include data that describes the customers' line-of-service, including usage, billing and omnichannel interactions.
Ensemble methods using XGBoost and Neural Networks often create stable and powerful churn models.
Churn models can be sensitive to aggressive and targeted competitor offerings, especially during the holidays.
Score customers every 30 days. Monitor and refresh the model as needed to maximize predictive performance.
Build an offer taker model for predicting customers that are likely to accept a retention offer if targeted.
Include data that describes the customers' line-of-service, including past campaign and offer data.
For best offer taker model performance, incorporate a counterfactual model for offer takers that were not targeted.
Offer taker models are highly sensitive to the specific retention offer. Consider building a generalized model for different offer types.
Customers express different behavior based on the offer's communication channel. It is strongly recommended to create a separate model per channel.
Identify the group of customers that will receive retention offers, and then evaluate the impact of the retention strategy to measure ROI.
Identify customers who are both high-risk for churn and highly likely to accept a retention offer.
Split targeted segment into control and treatment groups, usually a 10/90 or 5/95 split to maximize impact and measure performance.
Evaluate the incremental conversion rate between control and treatment groups, and adjust offer/split if needed.
After 30 days, assess the difference in churn rate between measurement groups, and calculate ROI using CLV.
Prime your AI agent with a unique context from churn and taker models to create relevant interactions, improving retention and customer satisfaction.
For every customer, Identify key features driving churn and offer-taking behavior.
Determine the semantic meaning for each driving feature, building a model-level profile for each scored customer.
Condense the customer's profile into text for the AI agent, and inject the text at the beginning of each conversation.
Click on the model cards to learn more about our Churn, Offer Taker and CLV model offerings and how they can be used to improve retention and drive business results.
