Introduction to Machine Learning with Time Series
summary
A practical primer shows a new Python toolbox sktime that actually implements reduction-to-regression, ensembling, pipelining, detrending and temporal CV rather than just promising examples. Baselines are the last-value and seasonal-last forecasts; evaluations use sMAPE on a 36-step horizon. A grid search picks a window length of 15 for the reduced regressor, residual-boosting pipelines improve accuracy, and classification examples use TimeSeriesForest and DTW k‑NN — the code and notebooks run and reproduce the results.
AI-written summary · about
chapters (6)
- 0:00Introduction
- 10:25Time series ML landscape
- 35:15Forecasting with sktime
- 57:16Composite models and pipelines
- 1:06:43Time series classification
- 1:24:40sktime development
related talks
30msktime: python toolbox for time series- next-generation AI
26mTime Series Analysis in Python: Easy Tools for Scientific Insight
01h 26mSktime—Python Toolbox for Time Series: How to Implement Your Own Estimator
01h 30msktime - python toolbox for time series
31mAdvanced machine learning time series....
43mFeature Engineering for Time Series Forecasting
29mTime Series Forecasting Techniques in Python
01h 43m(Serious) Time for Time Series