Jelena Malic & Joana Soares Machado
7 - 8 September 2021 | Alte Kaserne Winterthur
Jelena is a Data Scientist in the Swisscom’s Data, Analytics and AI department. She recently finished her master studies at EPFL and joined Swisscom firstly as an intern, before becoming a full-time employee in the Software Analytics team. In addition to helping the team improve the existing anomaly detection models for business process monitoring, Jelena is trying to make data science tools useful and accessible to many different stakeholders.
Joana Soares Machado
Joana is a data scientist at Swisscom. As part of the Data, Analytics and AI department, she develops ML solutions to automate the real-time monitoring of Swisscom's business processes and IT services. Joana holds a Master's degree in Communication Systems from EPFL, where she previously worked as a research scientist in the domain of applied machine learning in privacy and security.
End-to-End Monitoring at Scale
In order to fulfil service quality and customer satisfaction requirements, Swisscom DevOps teams must make sense of high volume of relevant metrics, events, and traces generated by numerous distributed systems. Behind the scenes, it is necessary for applications to work not only in isolated fashion but also in the end-to-end context, while at the same time quickly addressing all of the issues that could affect the users.
In this talk, we will demonstrate how we empower DevOps teams in Swisscom in their constant effort to ensure stability and continuous improvement of their systems. Our real-time monitoring tool provides root cause analysis and meaningful alarms, which are based on anomaly detection, dependency graphs, and integrated user feedback. In particular, we will show how this was achieved using open source technologies such as Prophet models, PySpark, MLflow, and Prometheus.