Our client was looking to increase call centre efficiency by reducing the number of repeat callers. They needed a solution which could identify why people were calling, and the likelihood of repeat contacts. The Ipsos team addressed this challenge by building a propensity model, leveraging bespoke Python scripts.
A multinational consumer goods company found that their contact centres were experiencing a high volume of calls, especially from repeat callers. They were looking for a solution which would help them to identify the breakdown of repeat contacts so they could understand the likelihood of people repeat calling and why.
The Ipsos Jarmany team initially conducted a data exploration, which involved leveraging existing Power BI and Excel reports to audit the data that was currently accessible, and therefore what was feasible for us to achieve with that data. We then built bespoke Python scripts, allowing us to create a propensity model which predicted the likelihood of someone repeat calling within a timeframe of 1-90 days. Linking this to client data, we were able to attribute each contact event with specific customer characteristics in order to gain insights around who and why people were calling.
As a result of this solution, we were able to identify and group common query themes to provide insights around what topics people were typically calling for. This aided the client as it guided them on what online resources would be suitable to create to help offset the need for customers contacting the call centre. Our solution ultimately reduced the need for additional call centre resource, increased efficiency, and improved customer satisfaction.
What We Do
Resources
Careers
Important Information
Speak To A Member Of The Team
By entering your email address you’re agreeing to the terms outlined in our Privacy Policy.
