COR Brief
Data & Analytics

Sktime

Sktime is an open-source Python library that offers a unified framework for machine learning tasks involving time series data. It supports multiple learning tasks such as forecasting, classification, clustering, and regression through a consistent and composable API modeled after scikit-learn. The library enables users to build composite models using pipelines, ensembles, hyperparameter tuning, and task reduction, and it supports both univariate and multivariate time series data. Sktime operates primarily on in-memory data structures based on pandas and NumPy, targeting medium-sized datasets. The framework includes dedicated time series algorithms rather than relying solely on adaptations of general-purpose methods. It also provides hierarchical forecasting capabilities and tools for fair model assessment and benchmarking. Sktime is designed for Python developers and data scientists familiar with scikit-learn, as well as researchers and practitioners working on various time series problems. The project is actively maintained and distributed under an open-source MIT license.

Updated Feb 8, 2026open-source

Sktime is a Python library providing a unified, scikit-learn-like API for multiple time series machine learning tasks including forecasting, classification, clustering, and regression.

Pricing
open-source
Category
Data & Analytics
Company
Interactive PresentationOpen Fullscreen ↗
01
Provides a consistent interface for multiple time series learning tasks, allowing users to build, fit, apply, and validate models with the same conventions.
02
Includes algorithms specifically designed for time series analysis rather than adapted from general-purpose methods.
03
Supports pipelines with transformations, ensembles, hyperparameter tuning, and task reduction to create complex models.
04
Enables users familiar with scikit-learn to switch between models without changing code preparation or execution.
05
Allows application of different forecasting models at various levels of data aggregation.
06
Provides tools to build, inspect, and validate models while avoiding common pitfalls in time series evaluation.
07
Offers templates to add custom algorithms compatible with sktime's API.

Time Series Forecasting

Building and validating forecasting models for univariate or multivariate time series data using dedicated algorithms and hierarchical forecasting.

Time Series Classification

Applying classification algorithms to time series data with a consistent API and the ability to compose models via pipelines and ensembles.

Composite Model Development

Creating complex workflows involving pipelines, ensembling, hyperparameter tuning, and task reduction for various time series learning tasks.

1
Install Sktime
Follow the installation guide on the official website to install sktime via pip or conda.
2
Explore Documentation
Review the Get Started section and API Reference on the official documentation site to understand usage patterns.
3
Watch Tutorial
Watch the 2021 PyData Global video tutorial for practical examples and demonstrations.
📊

Strategic Context for Sktime

Get weekly analysis on market dynamics, competitive positioning, and implementation ROI frameworks with AI Intelligence briefings.

Try Intelligence Free →
7 days free · No credit card
Pricing
Model: open-source

Sktime is distributed as an open-source library, typically free to use. Specific licensing details are under the MIT license. No commercial pricing information is available.

Assessment
Strengths
  • Consistent interface across multiple time series tasks simplifies experimentation and model switching.
  • Includes dedicated time series algorithms designed specifically for temporal data.
  • Supports composite model building with pipelines, ensembles, and hyperparameter tuning.
  • Hierarchical forecasting capabilities enable modeling at different aggregation levels.
  • Open-source with active maintenance and MIT licensing.
Limitations
  • No detailed pricing or commercial support information available.
  • Operates primarily on in-memory data, which may limit scalability for very large datasets.
  • Limited information on competitor comparisons.