Forecasting platforms & libraries · sktime community (open source)
sktime
Open-source Python toolkit that extends scikit-learn conventions to forecasting, classification and clustering of time series.
sktime is a Python library that brings scikit-learn's familiar estimator interface (fit, predict, pipelines, cross-validation) to time series tasks, of which forecasting is one — the same toolkit also covers time-series classification, regression, clustering and annotation. It wraps and standardizes access to many underlying forecasting methods, including statistical models, machine-learning regressors adapted for forecasting, and interfaces to other libraries, so a data scientist already comfortable with scikit-learn pipelines can plug in forecasting with little new syntax. Its forecasting-validation tools (temporal train/test splitting, rolling-window cross-validation, pipeline composition with detrending and deseasonalizing transformers) are a particular strength for teams building rigorous, leakage-free evaluation workflows rather than ad hoc model fitting.
At a glance
| Vendor | sktime community (open source) |
|---|---|
| Pricing model | Open source + paid options |
| Free tier | Yes |
| Deployment | Self-hosted |
| Open source | Yes (BSD-3-Clause) |
| Best for | Data scientists who want rigorous, leakage-free forecast evaluation using scikit-learn-style pipelines. |
Pricing
Free and open source with no commercial tier.
Pricing has not been verified yet — see the vendor's site.
Features
- scikit-learn-compatible estimator interface for forecasting
- Time-series classification, regression and clustering in the same library
- Pipeline composition with detrending/deseasonalizing transformers
- Rolling-window and temporal cross-validation utilities
- Wrappers around statistical, ML and deep-learning forecasters
- Hierarchical and panel-data forecasting support
- Consistent API for model comparison and ensembling
Integrations
Profile last reviewed September 21, 2026