The client was struggling to reduce customer churn among non-respondents to customer satisfaction surveys. Identifying super detractors before they churn was critical for the business.
We built a machine learning model, based on 1200+ variables analyzed for each customer, detecting potential super detractors based on their behaviors and producing key talking points for the rescue call.
The model helped our client increase the likelihood of identifying a Super Detractor by 7 times and average NPS given by customers by 2 points.
1. Analysis of the in-depth behavior and attitude patterns of identified super detractors.
2. Machine learning model identifying potential Super Detractors based on their behaviours, products, care interactions and usage.
3. Daily list of top 100 customers at risk.
The client was struggling to reduce customer churn among non-respondents to customer satisfaction surveys. Identifying super detractors before they churn was critical for the business.
We built a machine learning model, based on 1200+ variables analyzed for each customer, detecting potential super detractors based on their behaviors and producing key talking points for the rescue call.
The model helped our client increase the likelihood of identifying a Super Detractor by 7 times and average NPS given by customers by 2 points.
1. Analysis of the in-depth behavior and attitude patterns of identified super detractors.
2. Machine learning model identifying potential Super Detractors based on their behaviours, products, care interactions and usage.
3. Daily list of top 100 customers at risk.
