![](https://d15shllkswkct0.cloudfront.net/wp-content/blogs.dir/1/files/2019/02/Guevara-Appugliese.jpg)
![](https://d15shllkswkct0.cloudfront.net/wp-content/blogs.dir/1/files/2019/02/Guevara-Appugliese.jpg)
What happens when customers leave and a business has no idea why?
That was the central question for Claro Colombia, the country’s largest mobile carrier, when it was confronted with the need to address customer churn. The answer came from working jointly with the Data Science Elite Team at IBM Corp.
By gathering a massive amount of data and applying machine learning and artificial-intelligence tools, engineers for IBM and Claro were able to develop models that could predict customer departure with over 90-percent accuracy.
“I said to the business people, ‘OK, these customers are going to leave the company,’” said Carlos Guevara (pictured, left), chief data officer at Claro Colombia. “Two months later, they said, ‘Your model is very good; all those customers are gone.’ We are closing the circle; we are taking care of that.”
Guevara spoke with Dave Vellante (@dvellante) and John Furrier (@furrier), co-hosts of theCUBE, SiliconANGLE Media’s mobile livestreaming studio, during the IBM Think event in San Francisco. They were joined by Carlo Appugliese (pictured, right), program director of machine learning and AI at IBM, and they discussed the approach taken by IBM’s data science team and what Claro has learned from the experience. (* Disclosure below.)
Claro’s efforts to reduce customer turnover came through collaboration with an AI and machine learning team developed by IBM in 2017 to help solve business problems. The group currently has 100 data scientists worldwide, according to Appugliese.
“We work side-by-side with clients, and our job is to really understand the problem from end-to-end and help in all areas,” Appugliese said. “At the end of the day, we prove out that we can get a model, we can do a prediction, we get certain accuracy, and it’s going to add value to the organization.”
IBM’s team spun up a new environment and ingested usage and billing data from Claro for in-depth analysis in the cloud. After building predictive models, these were then deployed to interact with the telecommunications company’s mobile applications.
“We needed to use machine-learning models and AI to make better decisions for the company,” Guevara said. “Our question was why customers were leaving us. The answer was in the data.”
Watch the complete video interview below, and be sure to check out more of SiliconANGLE’s and theCUBE’s coverage of the IBM Think event. (* Disclosure: IBM Corp. sponsored this segment of theCUBE. Neither IBM nor other sponsors have editorial control over content on theCUBE or SiliconANGLE.)
THANK YOU