Abstract
One of the key challenges faced by cellular network customer care agents is identifying if the service problem is caused by network-related issues or user-device-related issues. Some service providers [5], [6], therefore, employ machine learning-based troubleshooting frameworks to aid care agents in identifying the root cause of service problems experienced by users. However, obtaining large-scale and comprehensive ground truth troubleshooting result data is costly and requires tremendous manual efforts from networking operators. Due to this limitation, training such a machine learning (ML) model is rather challenging as the model can easily overfit to the limited available ground truth data. In this work, we propose a novel two-stage learning framework to improve the classification accuracy of ML-based troubleshooting frameworks. Our proposed framework uses resolution action taken by the care agent coupled with network/device data collected after the care call to infer accurate ground truth which is then used to train classification models.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.