33% improvement in ROMI using CLTV models
Segmented customers and calculated customer lifetime value using revenue forecast and built churn models to forecast the probability of customer attrition
The client, a Fortune 500 bank, wanted to understand the potential contribution that each customer would make to their revenue and profits in the next 12 months. They also wanted to increase ROMI (Return on Marketing Investment) and customer lifetime value. The existing solution had a high average MAPE in the customer value forecast, and the results were inconsistent. The process wasn’t completely automated and couldn’t identify the new customers likely to become valuable.
Sigmoid aggregated the customer and transaction data for the last 6 years and cleansed it for anomalies. We also did revenue forecasting at the customer level using machine learning models and built churn models to forecast the probability of customer attrition in the next 12 months while calculating the customer lifetime value and increasing ROMI.
Our robust revenue forecast solution delivered a 33% improvement in ROMI, leading to a 50% increase in operational efficiency.