Corporate Climate assessment: an applied
CB
Published · 33 slides · 0 views
1 / 1
Description
Corporate Climate assessment: an applied NLP-clustering approach Giuseppe Bonavolonta, EIB, Ali Hirsa, Columbia and Oleg Reichmann, ECB 8th Annual Bloomberg-Columbia Machine Learning in Finance Workshop 2022, September 22, 2022, New York
Related Topics
Share
Embed code
Download this presentation From Below
"Corporate Climate assessment: an applied" is the property of its rightful owner. Permission is granted to download and print the materials on this website for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
Presentation Transcript
01
Corporate Climate assessment: an applied NLP-clustering approach
Giuseppe Bonavolonta, EIB*, Ali Hirsa, Columbia and Oleg Reichmann, ECB*
8th Annual Bloomberg-Columbia Machine Learning in Finance Workshop 2022, September 22, 2022, New York
*The views expressed are those of the authors and do not necessarily reflect those of the ECB and/or the EIB.<br>
Giuseppe Bonavolonta, EIB*, Ali Hirsa, Columbia and Oleg Reichmann, ECB*
8th Annual Bloomberg-Columbia Machine Learning in Finance Workshop 2022, September 22, 2022, New York
*The views expressed are those of the authors and do not necessarily reflect those of the ECB and/or the EIB.<br>
02
Agenda Part I: Background and Motivation
Climate risk as financial risk
Climate related disclosures
Part II: NLP for corporate reports
Representation based on topics
BERT embedding
Clustering and Numerical examples<br>
Climate risk as financial risk
Climate related disclosures
Part II: NLP for corporate reports
Representation based on topics
BERT embedding
Clustering and Numerical examples<br>
03
Background<br>
04
Background Conclusion. (IPCC 2013) It is extremely likely that more than half of the observed increase in global average surface temperature from 1951 to 2010 was caused by the anthropogenic increase in greenhouse gas concentrations[…]<br>
05
Background Physical risk
Acute risk: Risks due to likelihood of more frequent and more severe occurrence of natural hazards (e.g. floods, storms). They represent the economic costs and financial losses due to increasing frequency and severity of climate-related weather events (e.g. storms, floods or heat waves).<br>
Acute risk: Risks due to likelihood of more frequent and more severe occurrence of natural hazards (e.g. floods, storms). They represent the economic costs and financial losses due to increasing frequency and severity of climate-related weather events (e.g. storms, floods or heat waves).<br>
06
Background Physical risk
Acute risk: Risks due to likelihood of more frequent and more severe occurrence of natural hazards (e.g. floods, storms). They represent the economic costs and financial losses due to increasing frequency and severity of climate-related weather events (e.g. storms, floods or heat waves).
Chronic risk: Risks due to structural changes to the physical environment (e.g. reduction of perma-frost, sea-level rise, water scarcity, increase of the average temperature). They represent the effects of long-term changes in climate patterns (e.g. ocean acidification, rising sea levels or changes in precipitation).<br>
Acute risk: Risks due to likelihood of more frequent and more severe occurrence of natural hazards (e.g. floods, storms). They represent the economic costs and financial losses due to increasing frequency and severity of climate-related weather events (e.g. storms, floods or heat waves).
Chronic risk: Risks due to structural changes to the physical environment (e.g. reduction of perma-frost, sea-level rise, water scarcity, increase of the average temperature). They represent the effects of long-term changes in climate patterns (e.g. ocean acidification, rising sea levels or changes in precipitation).<br>
07
Background Transition risk
Risks for the business model of counterparties due to the transition towards a low-carbon economy (e.g. triggered by governments, technological advancement, and/or changing customer preferences). Transition risks are associated with the uncertain financial impacts that could result from a rapid low-carbon transition, including policy changes, reputational impacts, technological breakthroughs or limitations, and shifts in market preferences and social norms.<br>
Risks for the business model of counterparties due to the transition towards a low-carbon economy (e.g. triggered by governments, technological advancement, and/or changing customer preferences). Transition risks are associated with the uncertain financial impacts that could result from a rapid low-carbon transition, including policy changes, reputational impacts, technological breakthroughs or limitations, and shifts in market preferences and social norms.<br>
08
Climate risk as financial risk Source: BIS, Climate-related risk drivers and their transmission channels<br>
09
Climate risk as financial risk The EIB Group Climate Bank Roadmap 2021-2025 outlines group goals for climate finance that supports the European Green Deal and helps make Europe carbon-neutral by 2050. It maps the next stages in the journey to a sustainable planet and provides a framework to counter climate change. ECB launched a supervisory climate risk stress test to assess how prepared banks are for dealing with financial and economic shocks stemming from climate risk. The exercise was conducted in the first half of 2022.
Conclusion: Euro area banks must urgently step up efforts to measure and manage climate risk, closing the current data gaps and adopting good practices that are already present in the sector.<br>
Conclusion: Euro area banks must urgently step up efforts to measure and manage climate risk, closing the current data gaps and adopting good practices that are already present in the sector.<br>
10
Disclosures and disclosure quality in central banking Bank of England:
ECB: […] Better climate performance will be measured with reference to lower greenhouse gas emissions, more ambitious carbon reduction targets and better climate-related disclosures. Riksbank: […] will only purchase corporate bonds issued by companies that report their annual direct and indirect emissions of greenhouse gases (scope 1 and scope 2) in accordance with the recommendations of the Task Force for Climate-related Financial Disclosures<br>
ECB: […] Better climate performance will be measured with reference to lower greenhouse gas emissions, more ambitious carbon reduction targets and better climate-related disclosures. Riksbank: […] will only purchase corporate bonds issued by companies that report their annual direct and indirect emissions of greenhouse gases (scope 1 and scope 2) in accordance with the recommendations of the Task Force for Climate-related Financial Disclosures<br>
11
How to measure the quality of disclosures? Existence of dedicated climate report/climate chapter in annual report binary variable with limited information
Publication of (verified) emission figures informative with respect to emissions, however only one aspect of disclosures
Coverage of TCFD required topics (Strategy, Governance, Risk management, Metrics/Targets) binary variable with potentially limited information
Alternatives?<br>
Publication of (verified) emission figures informative with respect to emissions, however only one aspect of disclosures
Coverage of TCFD required topics (Strategy, Governance, Risk management, Metrics/Targets) binary variable with potentially limited information
Alternatives?<br>
12
NLP based approach Research question: can an automated assessment of climate related publications of corporates be meaningfully performed?
Approach: Analyse corporate publications with respect to relevant content on transition and physical risk based on NLP.
Characterize publications based on weights and concentration in topics.
Cluster corporates publication based on representations.<br>
Approach: Analyse corporate publications with respect to relevant content on transition and physical risk based on NLP.
Characterize publications based on weights and concentration in topics.
Cluster corporates publication based on representations.<br>
13
Corporate disclosures: Corpus 1420 Companies;
Annual Reports,
Letter to investors,
Sustainability reports
Recent publications (2018 onwards) No predefined structures (paragraphs, templates, Q&A)
No predefined labels (e.g. topic labels)
No specific Industry sector focus<br>
Annual Reports,
Letter to investors,
Sustainability reports
Recent publications (2018 onwards) No predefined structures (paragraphs, templates, Q&A)
No predefined labels (e.g. topic labels)
No specific Industry sector focus<br>
14
Topic definition Physical Risk Definition: refers to so-called ”acute risks”, as the likelihood of more frequent and more severe occurrence of natural hazards (e.g. floods, storms), and to ”chronic risks”, i.e. structural changes to the physical environment (e.g. reduction of perma-frost, sea-level rise, water scarcity, increase of the average temperature). They represent the economic costs and financial losses due to increasing frequency and severity of climate-related weather events (e.g. storms, floods or heat waves) and the effects of long-term changes in climate patterns (e.g. ocean acidification, rising sea levels or changes in precipitation). Physical Risk Topic ={heat wave, precipitation, floods, droughts, wildfires, storms, hazard, sea level, temperature increase, IPCC report. . . }<br>
15
Topic definition Transition Risk Definition: refers to risks for the business model of counterparties due to the transition towards a low-carbon economy (e.g. triggered by governments, technological advancement, and/or
changing customer preferences). Transition risks are associated with the uncertain financial impacts that could result from a rapid low-carbon transition, including policy changes, reputational
impacts, technological breakthroughs or limitations, and shifts in market preferences and social
norms. In particular, a rapid and ambitious transition to lower emissions pathways means that
a large fraction of proven reserves of fossil fuel cannot be extracted, becoming “stranded assets”,
with potentially systemic consequences for the financial system. Transition Risk Topic={polluting, green, Paris agreement, stranded, Kyoto, emissions, GHG, carbon tax, renewable, waste, well-below two degrees Celsius before pre-industrial age, TCFD-report,. . . }<br>
changing customer preferences). Transition risks are associated with the uncertain financial impacts that could result from a rapid low-carbon transition, including policy changes, reputational
impacts, technological breakthroughs or limitations, and shifts in market preferences and social
norms. In particular, a rapid and ambitious transition to lower emissions pathways means that
a large fraction of proven reserves of fossil fuel cannot be extracted, becoming “stranded assets”,
with potentially systemic consequences for the financial system. Transition Risk Topic={polluting, green, Paris agreement, stranded, Kyoto, emissions, GHG, carbon tax, renewable, waste, well-below two degrees Celsius before pre-industrial age, TCFD-report,. . . }<br>
16
BERT Embedding Bidirectional Encoder Representation via Transformer Some facts about BERT:
State of the art embedding model published by Google.
It is a context-based embedding model.
It is used for question answering, text generation, sentence classification, translation and many more
Two standard configurations BERT-base (110 M parameters) and BERT-large (340 M parameters)
Pre-training: via Toronto BookCorpus and Wikipedia dataset<br>
State of the art embedding model published by Google.
It is a context-based embedding model.
It is used for question answering, text generation, sentence classification, translation and many more
Two standard configurations BERT-base (110 M parameters) and BERT-large (340 M parameters)
Pre-training: via Toronto BookCorpus and Wikipedia dataset<br>
17
BERT Embedding Single Encoder BERT Base Base set-up:
Number of encoder layers N=12
Number of attention head A=12
Hidden unit H=768
Pre-trained (110M parameters) Bidirectional Encoder Representation via Transformer by Google<br>
Number of encoder layers N=12
Number of attention head A=12
Hidden unit H=768
Pre-trained (110M parameters) Bidirectional Encoder Representation via Transformer by Google<br>
18
Embedding Physical Risk Cluster ={heat wave, precipitation, floods, droughts, wildfires, storms, hazard, sea level, temperature,
. . . } Topic cluster: Corpus:<br>
. . . } Topic cluster: Corpus:<br>
19
Topic extraction Corpus sentence average Topic Cluster 1 Illustrative purposes<br>
20
Topic extraction Corpus sentence average Topic Cluster 1 Illustrative purposes Avoid spurious data (remove if):<br>
21
NLP & Von Mises-Fisher k = 5 (left) and k = 50 (right) with v = [√0.5, 0, √0.5] The density describes unit vectors distributed around the mean direction v with concentration parameter k<br>
22
Why the concentration matters? An example… 1997<br>
23
Why the concentration matters? An example… 1997 2019<br>
24
1997 2019 Why the concentration matters? An example…<br>
25
VM-Mixtures<br>
26
VM-Mixtures Clustering on the Unit Hypersphere using von Mises-Fisher Distributions, Journal of Machine Learning Research 6 (2005) 1<br>
27
Dissimilarity…<br>
28
Dissimilarity…<br>
29
Dissimilarity…<br>
30
Clustering: combined distances<br>
31
Clustering Numerical experiments<br>
32
Conclusions and future research directions Conclusions:
The BERT NLP-methodology definitely improves and automatises the assessment of climate related publications.
The use of weights and concentrations for each topics allows to distinguish the physical and transition risk dimensions of climate disclosures.
The overall machinery can be audited and validated (no black-box issue).
Future research directions :
(In our opinion) We need to leverage AI-ML in order to introduce new financial quantitative measures/methodologies supporting the green transition (climate finance and risk management). Disclosures is one dimension but others need to be investigated: e.g. emissions-paths, scenario generation, rare and plausible events, shocks simulation and new credit/market risk measures.<br>
The BERT NLP-methodology definitely improves and automatises the assessment of climate related publications.
The use of weights and concentrations for each topics allows to distinguish the physical and transition risk dimensions of climate disclosures.
The overall machinery can be audited and validated (no black-box issue).
Future research directions :
(In our opinion) We need to leverage AI-ML in order to introduce new financial quantitative measures/methodologies supporting the green transition (climate finance and risk management). Disclosures is one dimension but others need to be investigated: e.g. emissions-paths, scenario generation, rare and plausible events, shocks simulation and new credit/market risk measures.<br>
33
Thank you! Q&A<br>