
Communications, Media & Telecom - Prediction of customer probability to churn
Communications, Media & Telecom
With support by synvert, a telecommunications company developed a pipeline using Azure and Python to predict customer churn reasons and timing, improving targeted marketing campaigns and increasing the likelihood of identifying true churners by 20%. Synvert tuned a classification model to report churn drivers and provide daily predictions for actionable insights.
Initial situation
The client was faced with the scenario that there was a high turnover and many of their customers wanted to terminate their contract after the first year.
The challenge was to predict what reasons a customer might have to terminate and when.
Architecture
Open source and Big Data technologies (Azure, Python) have enabled the development of the pipeline, which stores the predicted results in an additional database.
Companies can query the results there. The pipeline has been developed using Azure Data Factory and the project has been based on the Scrum methodology.
Generated benefits
The increased business understanding of churn drivers leads to improved and targeted marketing campaign design.
Given a specific target, they are now 20% more likely to identify a true churner.
Services accomplished by synvert
synvert has tuned a classification model based on specific client data.
After several iterations and through continuous business and technical validation, the model is able to report the most important drivers of churn as well as providing daily predictions to the business that can now take actions on specific customers.