12-03, 13:30–15:00 (UTC), Data/ Data Science Track
skchange is a python compatible framework library for detecting anomalies, changepoints in time series, and segmentation.
skchange is based on and extends sktime, the most widely used scikit-learn compatible framework library for learning with time series. Both packages are maintained under permissive license, easily extensible by anyone, and interoperable with the python data science stack.
This workshop gives a hands-on introduction to the new joint detection interface developed in skchange and sktime, for detecting point anomalies, changepoints, and segment anomalies, in unsupervised, semi-supervised, and supervised settings.
The tutorial will give an introduction to the detection API in skchange and sktime, with a focus on unsupervised detection of anomalies and change points. The tutorial includes:
- An introduction to the different types of detection tasks for time series data: anomalies, changepoints, point/set/segment, un/supervised, stream, panel, uni/multivariate
- skchange and sktime for anomaly, changepoint detection
- cost and score functions for anomaly and changepoint detectors
- shared estimator marketplace for skchange, sktime, and other extension packages
- case studies and use case challenges: failure detection and health monitoring
skchange is developed at Norsk Regnesentral. Both skchange and sktime are developed by open communities, with aims of ecosystem integration in a neutral, charitable space. We welcome contributions and seek to provides opportunity for anyone worldwide.
No previous knowledge expected
Core developer and founder of sktime.
Director of the German Center for Open Source AI Software.
Senior Research Scientist at the Norwegian Computing Center, Department of Statistics and Machine Learning. Interests: Anomaly detection, changepoint detection, sensor data.
Christopher is a computer science Ph.D. student from the University of Waterloo, specializing in artificial intelligence. Christopher is a member of the Computational Health Informatics Lab (CHIL), a Consultant, AI Research & Health Insights at Gluroo Imaginations Inc., and co-founder of the Blood Glucose Control AI Design Team.
Christopher's research focuses on developing AI systems for aiding and supporting decision making in the management of diabetes.
LinkedIn: https://www.linkedin.com/in/christopherrisi/
BGC AI Design Team: https://github.com/RobotPsychologist/bg_control/wiki/About-Us