公司层面气候变化暴露指数

一、数据简介

     Firm-level Climate Change Exposure

  • Contributors: Zacharias Sautner, Laurence van Lent, Grigory Vilkov, Ruishen Zhang

  • Date created: 2020-06-29 10:50 PM | Last Updated: 2021-10-08 05:02 PM

  • Identifier: DOI 10.17605/OSF.IO/FD6JQ

  • Description: We introduce a method that identifies firm-level climate change exposures from conversation in earnings conference calls of more than 10,000 firms from 34 countries between 2002 and 2020. The method captures exposures related to opportunity, physical, and regulatory shocks associated with climate change. The exposure measures exhibit cross-sectional and time-series variations which align with reasonable priors, and are better in capturing firm-level variation than carbon intensities or ratings. The exposure measures relate to economic factors that prior work has identified as important correlates of climate change exposure (e.g., public climate attention). Exposure to regulatory shocks negatively correlates with firm valuations, but only in recent years.

  • Background: For an extensive description of this data, please read the data and methodology sections of the paper cited below. For convenience, here is a brief description.The exposure measures count the frequency with which certain climate change bigrams occur in the transcript, scaled by the total number of bigrams in the transcript. We construe these measures as indicating the occurrence of climate change events or shocks at the firm. Our method also allows us to construct measures of the first and second moment associated with these shocks. In other words, whether the events represent (in expectation) good or bad news to the firm and whether the shocks are uncertain. For the first moment, we construct "sentiment'' measures, which count the relative frequency of climate change bigrams that occur in the vicinity of positive and negative tone words (Loughran and McDonald2011). For the second moment, or risk measures, we count the relative frequency of climate change bigrams mentioned in the same sentence as the words "risk" or "uncertainty" (or their synonyms). Following prior practice in Hassan et al. (2019), we interpret these sentiment and risk measures as components of the exposure measures.

  • Updates 2021-05-14: We have updated our data to 2020Q4.

  • Updates 2021-04-03: Last update missed 2019 Q3 and Q4. We added the data of these two quarters in the latest version.

  • Updates 2021-01-19: We have updated our data to 2020Q3.

     Please cite the following study when using this Climate Change Exposure/Risk/Sentiment data:

  • Sautner, Z., L. van Lent, G. Vilkov, and R. Zhang, Firm-level Climate Change Exposure, 2020. Available at SSRN: https://ssrn.com/abstract=3642508

     The data is publicly available and free to use, provided its source is acknowledged as follows:

  • Sautner, Z., L. van Lent, G. Vilkov, and R. Zhang, 2020. ”Data for ‘Firm-level Climate Change Exposure’”. https://doi.org/10.17605/OSF.IO/FD6JQ and both data and the associated paper are cited in any work that uses these resources.

     经上海财经大学会计学院张瑞申教授授权,CnOpenData建立了该数据的展示区及数据索引,便于学者浏览。

     数据下载请点击Firm-level Climate Change Exposure,或在本页页末直接下载。

二、时间区间

2001-2020

三、字段展示

四、样本数据

firm-year-level  Climate Change Exposure

isindateQcc_expocc_riskcc_poscc_negcc_sentiop_cc_expoop_cc_riskop_cc_posop_cc_negop_cc_sentirg_cc_exporg_cc_riskrg_cc_posrg_cc_negrg_cc_sentiph_cc_expoph_cc_riskph_cc_posph_cc_negph_cc_sentigvkeyheadquarterscountryhqcountrycode
AEA0020010132016q40.0003215430000000000000000000284153United Arab EmiratesAE
AEA0020010132017q10.000738280000000000000000000284153United Arab EmiratesAE
AEA0020010132017q200000000000000000000284153United Arab EmiratesAE
AEA0020010132017q300000000000000000000284153United Arab EmiratesAE
AEA0020010132017q40.0005165290000000000000000000284153United Arab EmiratesAE
AEA0020010132018q100000000000000000000284153United Arab EmiratesAE
AEA0020010132018q200000000000000000000284153United Arab EmiratesAE
AEA0020010132018q300000000000000000000284153United Arab EmiratesAE
AEA0020010132018q400000000000000000000284153United Arab EmiratesAE
AEA0020010132019q100000000000000000000284153United Arab EmiratesAE

firm-quarter-level  Climate Change Exposure

isinyearcc_expocc_riskcc_poscc_negcc_sentiop_cc_expoop_cc_riskop_cc_posop_cc_negop_cc_sentirg_cc_exporg_cc_riskrg_cc_posrg_cc_negrg_cc_sentiph_cc_expoph_cc_riskph_cc_posph_cc_negph_cc_sentigvkeyheadquarterscountryhqcountrycode
AEA00200101320160.0003215430000000000000000000284153United Arab EmiratesAE
AEA00200101320170.0003137020000000000000000000284153United Arab EmiratesAE
AEA002001013201800000000000000000000284153United Arab EmiratesAE
AEA002001013201900000000000000000000284153United Arab EmiratesAE
AEA00200101320200.00108519600.000688055-0.000714754-2.67E-050.0001323800-0.00013238-0.000132380.00019179100.000191791-0.000191791000000284153United Arab EmiratesAE
AEA002301017201100000000000000000000274887United Arab EmiratesAE
AEA00240101520090.00231000400.000591299-0.0005826128.69E-060.0007293250.0001467140.000435898-0.0002913060.0001445920.00015105700.00015105700.0001510570.00015105700.00015105700.000151057279336United Arab EmiratesAE
AEA00240101520100.0018459900-0.000510032-0.0005100320.000544780000000000.00018910700-0.000189107-0.000189107279336United Arab EmiratesAE
AEA00240101520110.00180556700.000394011-0.000625029-0.0002310180.00068150200.00019700600.000197006000000.00026652500-0.000266525-0.000266525279336United Arab EmiratesAE
AEA00240101520120.0014718920.000414250-0.000528821-0.0005288210.0002644100000000000000279336United Arab EmiratesAE

五、参考文献

  • Sautner, Zacharias and van Lent, Laurence and Vilkov, Grigory and Zhang, Ruishen, Firm-level Climate Change Exposure (May 10, 2021). European Corporate Governance Institute–Finance Working Paper No. 686/2020, Available at SSRN: https://ssrn.com/abstract=3642508 or http://dx.doi.org/10.2139/ssrn.3642508

六、数据更新频率

不定期更新(CnOpenData Firm-level Climate Change Exposure

内容概要:本文详细探讨了基于樽海鞘算法(SSA)优化的极限学习机(ELM)在回归预测任务中的应用,并与传统的BP神经网络、广义回归神经网络(GRNN)以及未优化的ELM进行了性能对比。首先介绍了ELM的基本原理,即通过随机生成输入层与隐藏层之间的连接权重及阈值,仅需计算输出权重即可快速完成训练。接着阐述了SSA的工作机制,利用樽海鞘群体觅食行为优化ELM的输入权重和隐藏层阈值,从而提高模型性能。随后分别给出了BP、GRNN、ELM和SSA-ELM的具体实现代码,并通过波士顿房价数据集和其他工业数据集验证了各模型的表现。结果显示,SSA-ELM在预测精度方面显著优于其他三种方法,尽管其训练时间较长,但在实际应用中仍具有明显优势。 适合人群:对机器学习尤其是回归预测感兴趣的科研人员和技术开发者,特别是那些希望深入了解ELM及其优化方法的人。 使用场景及目标:适用于需要高效、高精度回归预测的应用场景,如金融建模、工业数据分析等。主要目标是提供一种更为有效的回归预测解决方案,尤其是在处理大规模数据集时能够保持较高的预测精度。 其他说明:文中提供了详细的代码示例和性能对比图表,帮助读者更好地理解和复现实验结果。同时提醒使用者注意SSA参数的选择对模型性能的影响,建议进行参数敏感性分析以获得最佳效果。
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值