The open-source tool for time series forecasting and anomaly detection

Accurate Forecasting saves you time and money. Effective Anomaly Detection reduces costs.

What Darts can do for your business

up down


Large collection of classical and state-of-the-art forecasting models: from statistical models (such as ARIMA) to deep learning models (such as N-BEATS). We are constantly scouting research and bringing the best models to Darts. Some of Darts’ models have extra features not present in the original versions.

up down

Anomaly Detection

Detect and classify anomalies in your series: It’s trivial to apply PyOD, or Darts’ forecasting and Filtering models to obtain fully fledged anomaly detection models.

up down


Handling multiple series: All of Darts machine learning models support being trained on multiple series, as well as large datasets.

up down


Multivariate series: Each of the time series can have multiple dimensions, to more easily model complex systems

up down

External Data

Taking static, past, and future external data into account to improve your forecasts: Use some static information about your target series and/or past-observed as well as future-known external time series as inputs for producing forecasts.

up down


Probabilistic Support: Usually point forecasts are not sufficient. Darts’ models can output whole probability distributions or just the distribution parameters, for example to obtain confidence intervals or take more optimal decisions.

up down


Regression Models: You can also easily use your favorite scikit-learn regression model for forecasting your series

up down


A variety of metrics for evaluating time series’ goodness of fit; from R2-scores to Mean Absolute Scaled Error.

up down


Evaluating forecasts correctly is very important: Darts provides the tools to simulate and evaluate historical forecasts, using moving or expanding time windows.

up down


Understand what your model learned: from feature importances and shap explanations for regression models, to self attention for transformer models.

up down

Easy processing

Data processing: Easily manipulate and/or apply (and potentially revert) common transformations on time series data (window transformations, missing values handling, normalization, etc …)

up down


De-noise your series: Darts provides several filtering methods from Gaussian Process Regressor to Moving Average filters..

up down

PyTorch Lightning

All deep learning models are implemented using PyTorch Lightning: supporting among other things custom callbacks, GPUs/TPUs training, checkpointing, weights loading for fine-tuning, etc.

Entirely open-source, introducing...

by Unit8

Darts is an open-source Python solution for time series forecasting and anomaly detection. Its versatile toolkit enables effortless time series data preprocessing and model building – from classical techniques to state-of-the-art deep learning approaches – all tailored to your specific needs. With its user-friendly design, Darts makes it easy to quickly experiment with and compare a variety of models on any use case.

  • Open-source

  • Battle tested

  • State-of-the-art

  • Easy to use

Read more
Stars on github
2 Mio+
Downloads in total
Forecasting models

Technical support

Need help with Darts — applying it to your data, productizing the models with best MLOps practices, or improving your forecasts?

Data science consulting

Need any help on advance data science or machine learning use-cases? We consult and deliver both strategic and engineering/research services.

Custom development

Darts does not (yet) have the feature you need? Let us know, chances are we can develop it for you and provide you with a tailored version stafisfying your needs.

Want to know how you can leverage Darts in your industry?

Contact us!

    Want to receive updates from us?

    Our newsletter features industry news, the latest case studies, and future Unit8 events.


    This page is only available in english