cure-lab/LTSF-Linear

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

2508 stars · 510 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

library · maturity maintenance

machine-learning deep-learning benchmarking deep-learning time-series python time-series-forecasting pytorch linear-models transformers aaai-2023 research-code research

Member repositories

For agents

markdown · JSON · MCP: product_card(name="cure-lab/LTSF-Linear")