arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.02898cs.LG
收藏

梯度提升机与精心预处理效果最佳:ASHRAE Great Energy Predictor III 的经验教训

Gradient boosting machines and careful pre-processing work best: ASHRAE Great Energy Predictor III lessons learned

National University of Singapore(新加坡国立大学)

Clayton Miller, Liu Hao, Chun Fu

AI总结:

本文总结ASHRAE GEPIII竞赛顶尖队伍经验,发现基于LightGBM等GBM树模型的集成、精心预处理与特征提取是建筑能耗预测获胜关键。

摘要:

ASHRAE Great Energy Predictor III(GEPIII)竞赛于2019年末举办,是有史以来规模最大的聚焦建筑性能的机器学习竞赛之一。该竞赛在Kaggle平台上主办,共产生39,402份预测提交,前五名团队分享了25,000美元奖金。本文概述了从参赛者,主要是竞赛成绩排名前5%的团队那里获得的经验教训。通过在线调查、对公开共享的提交和notebook的分析,以及获奖团队的文档,研究者从他们的经验中获得了多种洞见。表现最佳的解决方案大多使用基于树的Gradient Boosting Machine(GBM,梯度提升机)模型集成,其中LightGBM包最受欢迎。调查参与者表示,预处理和特征提取阶段是构建最佳建模方法中最重要的环节。所有调查受访者都使用Python作为主要建模工具,并且普遍使用Jupyter风格的Notebook作为开发环境。这些结论对于指导未来建筑能源计量预测的研究和实际实施至关重要。

英文摘要:

The ASHRAE Great Energy Predictor III (GEPIII) competition was held in late 2019 as one of the largest machine learning competitions ever held focused on building performance. It was hosted on the Kaggle platform and resulted in 39,402 prediction submissions, with the top five teams splitting $25,000 in prize money. This paper outlines lessons learned from participants, mainly from teams who scored in the top 5% of the competition. Various insights were gained from their experience through an online survey, analysis of publicly shared submissions and notebooks, and the documentation of the winning teams. The top-performing solutions mostly used ensembles of Gradient Boosting Machine (GBM) tree-based models, with the LightGBM package being the most popular. The survey participants indicated that the preprocessing and feature extraction phases were the most important aspects of creating the best modeling approach. All the survey respondents used Python as their primary modeling tool, and it was common to use Jupyter-style Notebooks as development environments. These conclusions are essential to help steer the research and practical implementation of building energy meter prediction in the future.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑