Customer Churn Analytics & Management services help organizations identify key churn drivers to develop churn prevention strategies to improve customer retention, loyalty and Life time value.
Identifying these key (churn) drivers helps organizations design churn strategies to enhance customer loyalty by developing a customer focused churn management, retention and revival strategy.
The Market Equations Centre of Excellence in India combines advanced analytics expertise and decades of consulting experience to help organizations design innovative and customer centric churn management strategies to enhance customer satisfaction, customer loyalty, retention and life time value.

Case Study 1
Market Equations developed a Customer Churn analysis scorecard for a large Telecom service provider in the United States to identify key churn drivers, identify subscribers who were most likely to abandon the service as well as to tag subscribers as "one time subscriber" or " subscribers who have reached the "point of no return". The main objective was to help them retain subscribers by implementing churn prevention strategies. so that customer service could be focused on those subscribers who were most likely to continue their services.
Objective:
- Identification of key Churn drivers
- Early Identification of likely defectors
- Optimizing operational cost by developing a customer focused strategy
Approach
The first step was to analyze existing data including subscriber demographic data, spends, CRM records, vintage of customers, customer activity, usage history and product/package usage. Our goal was to identify the Win Back Opportunity and Point of No Return by identifying the optimal days after lapse for both these scenarios.
Our findings resulted in the conclusion that 92 percent of subscribers who did not reactivate the service in the last 7 days was most likely to defect. Based on this conclusion we defined a period of 7 days as win back and post 7 days as No return thereby, helping the client implement the necessary retention strategy to retain customers. The Key Churn drivers were selected using techniques such as correlation, clustering, PCA etc. Logistic regression was used as the most appropriate technique to develop the model due to the nature of the dependent variable.
Outcome:
Post implementation, the scorecard was used to score active portfolios every 15 days. The scores were used to identify segments with highest likelihood and propensity to churn. The entire exercise provides the churn management team a window of 15 days to implement and execute focused and targeted churn management strategies to prevent customer churn and encourage retention.
Case Study 2
Market Equations developed a Customer Churn Analysis solution for a large Auto dealership in the United States to identify key churn drivers and identify customers who were most likely to defect to the competition. The main objective was to implement churn prevention strategies so that customer service could be focused on those customers who were most likely to continue the services by developing targeted loyalty and retention strategies.
Approach:
Data: Approximately 300,000 transactional data over 3 years was provided including the following information:
- Transaction Type
- Previous Vehicle info
- New Vehicle Info
- Demographics
- Psychographics
- Financing details
- New vehicle Addition or Replacement
- Repair History/Warranty data
- Programs Incentives at time of purchase
- Customer satisfaction index from Survey conducted previously
Customer churn, retention and loyalty analytics outsourcing services from Market Equations India helps organizations identify key churn drivers to develop churn prevention strategies to improve customer retention, loyalty and Life time value.
Analysis : Analyze data to identify the drivers of Customer Loyalty, Conquest and Defection and address the following questions:
- Why are customers staying?
- Why are customers leaving?
- Why are new customers coming?
- Are there any demographic patterns or trends?
- What is the impact of incentives on the market?
- Is it different by customer segment? Model segment?
Various proprietary analytic techniques were applied on the demographic, and purchase data - their expectations, satisfaction levels, demographic & geographic & psychographic tendencies, etc. The next step was to perform an in-depth Analysis of the data using trend and segmentation to detect patterns and profile customers based on loyalty, conquest and defection. A segmentation model was applied to validate the hypothesis. A reliable model was built and validated to provide the customer the insights to develop targeted prevention strategies to encourage retention and loyalty.
Outcome:
Based on these results, the Manufacturer could take corrective action by understanding the key triggers that caused customer defection, implement the anti-churn loyalty strategies and focus customer service on targeted accounts based on propensity scores.