##Acknowledgements

We thank the organizers of the [ASHRAE - Great Energy Predictor III]( https://www.kaggle.com/c/ashrae-energy-prediction/) competition and [winning teams](https://www.kaggle.com/competitions/ashrae-energy-prediction/leaderboard) for their datasets and solutions. We would also like to thank the [Large-scale Energy Anomaly Detection (LEAD) project](https://github.com/samy101/lead-dataset) team members to establish a taxonomy of generalizable anomalies prevalent in the building energy data and then putting in several man-hours to carefully annotate and validate this extended dataset. The training set used in this competition is a subset from the [LEAD project](https://github.com/samy101/lead-dataset). A final complete version with annotated meter readings from all buildings will be released later. A detailed description of the anomaly annotation process and initial benchmarks are presented in [this article](https://arxiv.org/abs/2203.17256). 
```
@misc{https://doi.org/10.48550/arXiv.2203.17256,
  doi = {10.48550/ARXIV.2203.17256},
  url = {https://arxiv.org/abs/2203.17256},
  author = {Gulati, Manoj and Arjunan, Pandarasamy},
  title = {LEAD1.0: A Large-scale Annotated Dataset for Energy Anomaly Detection in Commercial Buildings},
  publisher = {arXiv},
  year = {2022},
  copyright = {Creative Commons Attribution 4.0 International}
}
```
If you have any suggestions or queries regarding this dataset, please feel free to contact the [competition host](https://www.kaggle.com/samy101).