Intro to sktime: A Unified Interface for Machine Learning with Time Series

Speaker: Markus Löning (PhD Student @UCL)

Abstract: We present sktime, a new unified toolbox for machine learning with time series in Python. We provide state-of-the-art time series algorithms and scikit-learn compatible tools for model composition. The goal of sktime is to make the time series analysis ecosystem more usable and interoperable. In this talk, you'll learn about different time series learning tasks, how algorithms for one task can be used to help solve another one, sktime's key design ideas and our plans for the future.

Resources:

• GitHub https://github.com/alan-turing-institute/sktime
• Paper: http://learningsys.org/neurips19/assets/papers/sktime_ml_systems_neurips2019.pdf