back to list

Project: Advanced root-cause analysis in customer contacts


Customers reach out to KPN for various purposes and one of the easiest way for them is to call customer service. There is already a process of analyzing customer calls to classify correct cause of the call but there are some challenges in terms of understanding the specific reasons. One of them is the usage of the different words for describing basically the same problem. The purpose of the project is to develop an advanced root cause analysis to automate understanding of customer calls. Here the idea is to combine keyword extraction, named entity recognition and word embeddings to detect words used for similar purpose, map them into a single entity and then doing the analysis afterwards. Also understanding this processes effects to the classification and other tasks is also an important objective.

Mykola Pechenizkiy
Secondary supervisor
KPN: Gianluigi Bardelloni
Get in contact