Predictive Analytics Driven Net Promoter Score Estimation

Business Objective:

A leading global Financial Services firm wanted to estimate Net Promoter Score (NPS) for its non-survey responders and align business strategies accordingly.

Business Context:

Less than 1% of customers were responders to survey requests across all campaigns. Net Promoter Score (NPS) being important to understand share of wallet, it was desired to build estimate of NPS for non-survey responders.

Net Promoter Score

Proposed solution included building a predictive model to score non-survey responders into three categories promoters, detractors and neutral. Survey data (from Refer to Friend survey) had series of questions and responses. Using same, on a scale of 1 to 10, a promoter was defined to have a score of 9 or 10, 7 or 8 as neutral or passive and remaining detractors.

Post this, models were integrated with CRM and Avaya (Call Management Tool) so that if any customer calls in, model would score with all the data available till that instant. As result of scoring, customer care executive would be aware of customer’s score and would give a guiding, gentle or lavish touch. This was later implemented across all customer touch points. Some of the variables (leading KPIs) we used were SOW, call hold time, resolution codes, frequency usage, touch points, internal cluster profiles, customer care executive rankings etc.


In control sample, we were able to demonstrate higher satisfaction and increased transaction affinity over a period of 6 Months. In long term, it increased share of wallet significantly.

I agree to have my personal information transfered to MailChimp ( more information )
Join over 3.000 like minded AI enthusiasts who are receiving our weekly newsletters talking about the latest development in AI, Machine Learning and other Automation Technologies
We hate spam. Your email address will not be sold or shared with anyone else.