Our challenge was to create a recommendation engine capable of identifying the next best offer that would maximize the return of value for each client by increasing revenue, reducing the churn rate, increasing the acceptance rate, and leveraging previous interactions with the end-user.
By collecting more than 1000 variables from each client based on historical info and previous interactions, we developed predictive models to leverage information into useful client insights.
Thus, we estimated tendencies and prioritized actions by the client, consequently optimizing the best offer.
This approach resulted in a higher revenue per client and in a higher hit rate outbound commercial activity, whilst reinforcing consistent communication throughout different channels. In addition, a lower churn rate and better client lifetime management were achieved.
Overall, this methodology resulted in a customized approach to each client.