GiftEval

## GIFT-Eval
<!-- Provide a quick summary of the dataset. -->

We present GIFT-Eval, a benchmark designed to advance zero-shot time series forecasting by facilitating evaluation across diverse datasets. GIFT-Eval includes 23 datasets covering 144,000 time series and 177 million data points, with data spanning seven domains, 10 frequencies, and a range of forecast lengths. This benchmark aims to set a new standard, guiding future innovations in time series foundation models.

To facilitate the effective pretraining and evaluation of foundation models, we also provide a non-leaking pretraining dataset --> [GiftEvalPretrain](https://huggingface.co/datasets/Salesforce/GiftEvalPretrain).

[📄 Paper](https://arxiv.org/abs/2410.10393)

[🖥️ Code](https://github.com/SalesforceAIResearch/gift-eval)

[📔 Blog Post]()

[🏎️ Leader Board](https://huggingface.co/spaces/Salesforce/GIFT-Eval)

## Submitting your results

If you want to submit your own results to our leaderborad please follow the instructions detailed in our [github repository](https://github.com/SalesforceAIResearch/gift-eval)

## Ethical Considerations

This release is for research purposes only in support of an academic paper. Our models, datasets, and code are not specifically designed or evaluated for all downstream purposes. We strongly recommend users evaluate and address potential concerns related to accuracy, safety, and fairness before deploying this model. We encourage users to consider the common limitations of AI, comply with applicable laws, and leverage best practices when selecting use cases, particularly for high-risk scenarios where errors or misuse could significantly impact people’s lives, rights, or safety. For further guidance on use cases, refer to our AUP and AI AUP.

## Citation

If you find this benchmark useful, please consider citing:

```
@article{aksu2024giftevalbenchmarkgeneraltime,
title={GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluation},
author={Taha Aksu and Gerald Woo and Juncheng Liu and Xu Liu and Chenghao Liu and Silvio Savarese and Caiming Xiong and Doyen Sahoo},
journal = {arxiv preprint arxiv:2410.10393},
year={2024},
}
```

# GIFT-Eval
<!-- 提供数据集的简要概述。 -->

我们提出GIFT-Eval，一款旨在推动零样本（Zero-shot）时间序列预测研究的基准测试集，通过支持跨多样化数据集的评估来助力相关技术发展。GIFT-Eval包含23个数据集，覆盖144000条时间序列与1.77亿个数据点，数据涵盖7个领域、10种采样频率，并支持多种预测长度。该基准测试旨在树立新的行业标准，为时间序列基础模型（time series foundation model）的后续创新提供指引。

为助力基础模型的高效预训练与评估，我们还提供了一款无数据泄露风险的预训练数据集——[GiftEvalPretrain](https://huggingface.co/datasets/Salesforce/GiftEvalPretrain)。

[📄 论文](https://arxiv.org/abs/2410.10393)
[🖥️ 代码](https://github.com/SalesforceAIResearch/gift-eval)
[📔 博客文章]()
[🏎️ 排行榜](https://huggingface.co/spaces/Salesforce/GIFT-Eval)

## 提交研究结果
若您希望将自身研究结果提交至我们的排行榜，请遵循[GitHub仓库](https://github.com/SalesforceAIResearch/gift-eval)中详述的操作指南。

## 伦理考量
本发布仅用于支持学术论文的研究用途。我们的模型、数据集与代码并非针对所有下游应用场景专门设计或完成评估。我们强烈建议用户在部署该模型前，对其准确性、安全性与公平性相关的潜在问题进行评估与整改。我们鼓励用户考量人工智能的常见局限性，遵守适用法律法规，并在选择应用场景时采用最佳实践，尤其是在那些失误或滥用可能严重影响民众生命、权利或安全的高风险场景中。如需进一步的应用场景指导，请参阅我们的AUP与AI AUP。

## 引用说明
若您认为本基准测试对您的研究有所助益，请引用以下文献：

@article{aksu2024giftevalbenchmarkgeneraltime,
title={GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluation},
author={Taha Aksu and Gerald Woo and Juncheng Liu and Xu Liu and Chenghao Liu and Silvio Savarese and Caiming Xiong and Doyen Sahoo},
journal = {arxiv preprint arxiv:2410.10393},
year={2024},
}