# cure-lab/LTSF-Linear

[AAAI-23 Oral] Official implementation of the paper "Are Transformers Effective for Time Series Forecasting?"

Repository: https://github.com/cure-lab/LTSF-Linear
Canonical: https://ross.abutalabs.com/products/ltsf-linear
Language: Python
License: Apache-2.0
License Family: permissive
Topics: deep-learning, forecasting, forecasting-model, linear-models, pytorch, time-series, time-series-forecasting, time-series-prediction, aaai, aaai2023
Last push: 2024-01-27T16:45:10+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 1560, "days_push": 949, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2508, forks 510 (observed 2026-08-28T04:06:57.249672+00:00)

## What it is
Official PyTorch implementation of LTSF-Linear (Linear, DLinear, NLinear) from the AAAI-23 paper 'Are Transformers Effective for Time Series Forecasting?'. It also includes reimplementations of five Transformer forecasting models and a benchmark for long-term time series forecasting.

## Use cases
- forecast long-term time series with simple linear models
- compare transformer forecasting models against linear baselines
- run benchmarks on multivariate and univariate time series forecasting
- study the effect of look-back window size on forecasting
- reproduce results from the LTSF-Linear paper

## When to choose
- you need strong, simple baselines for long-term time series forecasting
- you want to benchmark Transformer-based forecasters against linear models
- you need reproducible PyTorch code for DLinear, NLinear, or Linear models

## When to avoid
- you need production-ready forecasting infrastructure rather than research code
- you want state-of-the-art Transformer architectures rather than linear baselines
- you need maintained features beyond the paper's scope

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, benchmarking
- domain: deep-learning, time-series
- platform: python
- tags: time-series-forecasting, pytorch, linear-models, transformers, aaai-2023, research-code, research

## Member repositories
- cure-lab/LTSF-Linear (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:57.249672+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 2026-08-30T02:26:32.235090+00:00, confidence not recorded.
  - readme: https://github.com/cure-lab/LTSF-Linear (fetched 2026-08-28T04:06:57.249672+00:00, sha 1f8343fe22a0)
- Data as of 2026-08-30T08:39:29.467469+00:00.