# zalandoresearch/pytorch-ts

PyTorch based Probabilistic Time Series forecasting framework based on GluonTS backend

Repository: https://github.com/zalandoresearch/pytorch-ts
Canonical: https://ross.abutalabs.com/products/pytorch-ts
Language: Python
License: MIT
License Family: permissive
Topics: pytorch, time-series, probabilistic, deepar, lstnet, n-beats
Last push: 2024-06-14T10:33:12+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2361, "days_push": 810, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1370, forks 197 (observed 2026-08-28T04:04:31.967627+00:00)

## What it is
PyTorchTS is a PyTorch-based probabilistic time series forecasting library that uses GluonTS as its backend API for loading, transforming, and backtesting time series datasets. It provides state-of-the-art models such as DeepAR, LSTNet, and N-BEATS implemented in PyTorch.

## Use cases
- forecast future values of a time series with probabilistic predictions
- train a DeepAR model on hourly or minute-level data
- backtest time series forecasting models
- compare DeepAR, LSTNet, and N-BEATS on the same dataset
- run forecasting models on GPU with PyTorch
- predict demand or traffic from historical time series data

## When to choose
- you want probabilistic time series forecasts in PyTorch
- you already use GluonTS but prefer PyTorch over MXNet
- you need models like DeepAR, LSTNet, or N-BEATS with a consistent API

## When to avoid
- you need actively developed features or frequent updates
- you want a non-probabilistic point-forecast-only library
- you work outside the Python/PyTorch ecosystem

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, data-science
- domain: machine-learning, deep-learning, time-series, data-science
- platform: python, cross-platform
- tags: pytorch, time-series-forecasting, probabilistic-forecasting, gluonts, deepar, n-beats, lstnet, gpu

## Member repositories
- zalandoresearch/pytorch-ts (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:31.967627+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:40:56.542249+00:00, confidence not recorded.
  - readme: https://github.com/zalandoresearch/pytorch-ts (fetched 2026-08-28T04:04:31.967627+00:00, sha 733433d4077a)
- Data as of 2026-08-30T08:39:29.467469+00:00.