Background
Our client is a multinational delivery services company based in the United States that ships over 18 million packages per business day. The company is known for its overnight shipping service and for pioneering a package tracking system with real-time updates on package locations.
Technology partners
Python
Challenge
In a highly competitive market with razor-thin margins, it is important to keep your existing customer base to safeguard customer revenue and margin. Therefore, the client’s Analytics Solutions department launched an initiative to improve customer experience through early identification of potential churn.
Approach
- Gain insight into what drives customers to churn by using data wrangling techniques. - Select the best-in-class algorithm to predict churn (XgBoost). - Translate the results of the algorithm into action plans for the Customer Services division, allowing them to take appropriate actions to avoid churn.
Key results
Benefits
It takes less effort to keep an existing customer engaged than to find a new one. By implementing a churn probability tracking system, our client was able to spot potential unhappy customers upfront. This allowed them to identify the root causes of customer churn and respond accordingly, resulting in a more satisfied customer base and an increase in revenue growth.
Share this key play
