Forecasting platforms & libraries · Unit8 SA

Darts

Open-source Python library offering one unified API across dozens of classical, ML and deep-learning forecasting models.

Visit Darts Alternatives

Darts is a Python forecasting library built by the Swiss ML consultancy Unit8, whose distinguishing idea is a single, consistent API over a very wide range of model families: classical statistical models (ARIMA, exponential smoothing, Theta), gradient-boosting models (LightGBM, XGBoost, CatBoost), deep-learning architectures (N-BEATS, Temporal Convolutional Networks, Transformers, RNNs), and pretrained foundation models. Because every model exposes the same fit/predict interface, analysts can swap one model for another, backtest several side by side, or build ensembles without rewriting data-handling code. Darts also supports probabilistic forecasting, covariates (external variables), and anomaly detection through scorers and detectors. It requires Python familiarity and works best when a team wants to compare many candidate models rather than commit to one library's house model.

At a glance

Vendor Unit8 SA
Pricing model Open source + paid options
Free tier Yes
Deployment Self-hosted
Open source Yes (Apache-2.0)
Best for Teams that want to benchmark many forecasting model types against the same dataset through one consistent interface.

Pricing

Free and open source with no commercial tier.

Pricing has not been verified yet — see the vendor's site.

Features

  • Unified fit/predict API across 30+ forecasting models
  • Classical, gradient-boosting, deep-learning and foundation models in one library
  • Probabilistic forecasting with prediction intervals
  • Covariate (external variable) support
  • Backtesting and model comparison utilities
  • Anomaly detection via scorers and detectors
  • Ensemble and conformal prediction wrappers

Integrations

Profile last reviewed September 21, 2026

Head to head

Alternatives

sktime Open-source Python toolkit that extends scikit-learn conventions to forecasting, classification and clustering of time series. Nixtla Open-source statistical/ML forecasting libraries plus TimeGPT, a hosted foundation model for time series. PyTorch Forecasting Open-source deep-learning forecasting library built on PyTorch and PyTorch Lightning for panel/multi-series data.

Darts in the index now

Terms to know

Time series forecasting Predicting future values of a metric using patterns found in its own historical sequence over time. Predictive analytics Analytics that uses historical data and statistical models to estimate what is likely to happen next. Anomaly detection Identifying data points or patterns that deviate significantly from expected or normal behavior. Backtesting Testing a trading or investment strategy against historical data to see how it would have performed. ARIMA (autoregressive integrated moving average) A classical time-series forecasting model that combines a series' own past values, differencing, and past forecast errors. Exponential smoothing A forecasting technique that weights recent observations more heavily than older ones, with the weight decaying exponentially with age.

Related guides

How to choose a forecasting platform or library Pick a time-series forecasting library by how many series you're forecasting and how much modeling control your team wants. How to forecast demand Baselines worth beating, where seasonality and model choice actually matter, and how to judge accuracy honestly. Time series analysis, explained How analysts model data ordered in time — the patterns forecasting methods look for, the pitfalls, and where the data actually lives.