A leading online insurance company in India sought to identify at-risk customers and implement effective retention strategies, ultimately improving the 13th-month persistency rate.
- Identify customers at risk of lapsing in the 13th month.
- Develop effective reactivation and retention strategies.
To achieve these objectives, Transorg implemented the following approach:
- Segmentation of customers into categories, including urban mass, rural, and urban affluent, among others.
- Comprehensive analysis of historical policy surrender data to predict the likelihood of surrender one month in advance.
- Utilization of advanced machine learning techniques, such as random forest and gradient boosting, to improve predictive accuracy.
- Ongoing monitoring and analysis, including coverage assessment, accuracy evaluation, trend analysis, and opportunity sizing on a monthly basis.
- Enhanced identification of potentially lapsed customers compared to random selection.
- Establishment of a proactive customer retention approach, with a focus on engaging high-value and high-propensity customers at risk of lapsing.