T-Mobile Netherlands (TMNL), is a leading telecom provider in the Netherlands with an annual growth of 5% in the number of clients. TMNL currently serves more than 6 million mobile subscribers, using more than 6 thousands antenna bases installed around the country. When it comes to customer satisfaction, TMNL has been the top one in the Netherlands for several years in a row.

TMNL upgrades the capacity of the access network every year to assure a high quality of the network and to achieve an even higher customer satisfaction rate while limiting the unnecessary expenses. In this way, better connectivity and higher internet speed are guaranteed to be delivered to the customers. In order to determine the upgrade requirements for each antenna location, TMNL relies on smart predictive analytics methods. The challenge was whether an AI based model can be built that can deliver a more accurate estimate on the number of users per location.

Compound Formulation

In 2019, Machine2Learn got the opportunity to develop an AI based prediction model to determine the upgrade requirements for each antenna location. After proving satisfactory results, Machine2Learn software is getting integrated within the pipeline of TMNL by adding all the codes required to analyse and process the information on a weekly basis. Making use of Machine2Learn, AI software resulted in a more accurate estimate of the number of upgrades. It reduces required budget by reducing the number of falsely triggered upgrades, while it also helps maintaining the customer experience by reducing the number of falsely skipped upgrades.

If you are interested to learn more about how to utilize machine learning to solve real world problems, we offer a brief workshop which combines a theoretical overview of machine learning with practical examples.

Find more about M2L Quick Start workshop