Abstract
Trustable models exploit the diversity of model forms developed using symbolic regression via genetic programming to define ensemble models. These models have been shown empirically to have a strong predictive performance and the ability to extrapolate into regions of unknown parameter space or detect changes in the underlying system. This chapter demonstrates how the same technique for quantifying uncertainty is helpful in risk management workflows for alternative investing, especially when applying behavioral science principles. The use cases cover assets such as publicly traded private equities, specifically when the optimization objectives include financial and environmental, social, and governance (ESG) criteria, and ESG ETFs. This chapter provides an overview of these asset classes and a critical review of the issues with how current ESG ratings are formulated by rating agencies. Additionally, explicit uncertainty ranges are obtained, using an ensemble modeling approach, at a sufficiently high accuracy level to trust the uncertainty measurement. Future research is necessary to refine the approach presented as more data becomes available.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Fallender (2020) emphasized the novelty of the ESG acronym and the need for clarity so that the ESG investment space is clearer to entrants: “I think there are still a lot of people. And think of large companies like Intel who’ve been working on these issues for many years. But there are a lot of companies out there to which it’s relatively new. It’s an acronym. So I think it’s also about language and understanding how to kind of frame it for people in the language that they understand”.
Sand (2021) raises the issue of ESG and returns: “Many believe it [ESG investment] does come at the expense of returns; in the US many sponsors don’t take the topic seriously, but the data will suggest otherwise and we’ve started to try to build something to evaluate this”.
Agudo (2022) raises the question of current data gaps in the market: “There is a clear demand from the market to move to more sustainable data, but we are lacking accuracy, transparency, and data and this is where we need to move to have a clearer position.”
- 2.
In 2019, more than 630 investors collectively managing more than $37 trillion signed the Global Investor Statement to Governments on Climate Change urging governments to require climate-related financial reporting (GIS, 2019).
- 3.
According to the US Securities and Exchange Commission (2022, p. 7), information is material if there is a substantial likelihood that a reasonable investor would consider it important in deciding how to vote or make. From the SEC 2010 docket, it is understood that “these [material] effects can impact a registrant’s personnel, physical assets, supply chain and distribution chain.” They can include the impact of changes in weather patterns, such as increases in storm intensity, sea-level rise, melting of permafrost and temperature extremes on facilities or operations. Changes in the availability or quality of water, or other natural resources on which the registrant’s business depends, or damage to facilities or decreased efficiency of equipment can have material effects on companies.
- 4.
According to the 2022s (2022, p. 290) resolution, from 2024, it will be mandatory for public companies to disclose their company data on climate change risk. In 2021, The European Union published its first Taxonomy on ESG. We expect public companies to have a greater degree of open climate and ESG risk information. The relevance of increasing data for this research is needed to further model through SR and risk comprehension.
- 5.
Some of the main ratings available now are CSA, from S&P; GIC’s sustainability; ISE from B3; Paris agreement commitment; SDGs commitment; UNGP participation and the IRIS + system; Revinitiv ESG score; Marketpsych scores; FTSE; and MSCI. One example of the kind of objections leveled at these ratings is the one that falls under the use of the SDGs commitment: it is suggested that SDGs should be developed through governmental initiatives.
- 6.
Cheong (2022): “There is a lot of lack of consistency in environmental and social reporting, and it’s an area where we have been promoting and calling for some standardization. We often look at a variety of sources, and as S&P global, we have other divisions of the company that provide valuable data. Truecost, for example, aggregates environmental data; but more importantly, we have a relation with company management, so we’ll often get data from company management itself; we have the ESG scores, and we sort of triangulate all of the sources”.
- 7.
From 2022 onward, the UK government is preparing to make mandatory “ESG reporting from all UK private companies and LLPs [Limited Liability Partnerships] with more than 500 employees, as well as all publicly quoted UK companies” (Glover, 2021). Increasingly, considering ESG factors alongside financial factors is no longer an option. As we see the United States Security Exchange Commission, the Indian Security Exchange Board, and the European Union’s movement toward ESG regulation for public companies, we can expect to know more about ESG investing in the future, easing the alignment between investments and ESG criteria.
- 8.
“Well-run index funds track the market almost exactly and charge very low management fees, often less than 0.1% per year. (…) they have attracted about $2 trillion from investors” (Brealey et al., 2017, p. 180).
- 9.
Source Datasets and Predictions Tables are Available at https://www.autonomous.economymonitor.com/s/Evolving-Algorithms-for-Uncertainty-Estimation-in-ESG-and-Alternative-Investments-Supplementary-Mate.zip.
- 10.
Refinitiv ESG scores measure the ESG performance of companies, based on reported data in the public domain across three pillars and 10 different ESG topics. Refinitiv ESG combined score is an overall company score based on the reported information in the environmental, social and corporate governance pillars (ESG Score) with an ESG Controversies overlay.
- 11.
MSCI ESG Quality Score. This is the overall ESG score. It measures the ability of underlying holdings to manage key medium to long-term risks and opportunities arising from environmental, social, and governance factors.
References
Agudo, A. 2022. Solving the ESG data conundrum [Webinar]. Reuters. https://vimeo.com/681041950
Awasthi, S., & Muvija, M. (2017). BAT warns of steeper declines in cigarette sales, shares slip. https://www.reuters.com/article/us-brit-am-tobacco-outlook-idUSKCN1TD0NH
Brealey, R. A., Myers, S. C., & Allen, F. (2017). Principles of corporate finance. McGraw-Hill/Irwin.
Briand. R. (2022). What is environmental, social and governance? MSCI. https://www.msci.com/esg-101-what-is-esg
Cheong, M. (2022). How ESG factors impact Credit Risk. [Webinar]. S&P Global.
Eccles, R., & Serafeim, G. (2013). The performance frontier—Innovating for a sustainable strategy. Harvard Business Review. https://hbr.org/2013/05/the-performance-frontier-innovating-for-a-sustainable-strategy
Evolved Analytics LLC, DataModeler, Version 9.5, Rancho Santa Fe, CA USA. (2021). The number of investors that actively hold a stake in the company after the company's most recent transaction.
Fallender, S. (2020). Quick chat on ESG disclosure: Through the lens of reporting. Refinitiv [Webinar]. https://www.refinitiv.com/en/sustainable-finance/sustainability-perspectives/episode-41-through-the-lens-of-corporate-reporting.
Glover, J. (2021, October 15). ESG rules and regulations will hamper business growth and wider societal change. RSM UK. Insider.co.uk. https://www.insider.co.uk/news/esg-rules-regulations-hamper-business-25265333
IIGCC. (2019). Global investor statement to governments on climate change. https://www.iigcc.org/download/global-investor-statement/?wpdmdl=2600&refresh=625ed38bb70ad1650381707.
Kotin, A (host). Howard-Grenville, J. The Resonance Test. (2021). Episode number 65 [Audio podcast episode]. In The Resonance Test. Epam Continuum. https://soundcloud.com/futuremadereal/the-resonance-test-66-jennifer-howard-grenville
Kotanchek, M., Smits, G., & Vladislavleva, E. (2008). Trustable symbolic regression models—Using ensembles, interval arithmetic and Pareto Fronts to develop Robust and Trust-aware Models. In Rick L. Riolo, Terence Soule and Bill Worzel (Editors), Genetic Programming Theory and Practice V, chapter 12, Published 2008, ISBN: 978–0–387–76307–1.
Peterson, R., & Neuville, F. (2021). Incorporating ESG Sentiment into Investment Strategies [Webinar]. Refinitiv. https://solutions.refinitiv.com/ESGSentimentWebinar.
MSCI. (2020, December). MSCI ESG ratings methodology. https://www.msci.com/documents/1296102/4769829/MSCI+ESG+Ratings+Methodology+-+Exec+Summary+Dec+2020.pdf/15e36bed-bba2-1038-6fa0-2cf52a0c04d6?t=1608110671584
Rick, R., Ekaterina Vladislavleva, R., Ritchie, M. D., & Moore, J. H. (Editors). (2013, May). Genetic programming theory and practice X. Series: Genetic and evolutionary computation. ISBN 978–1–4614–6845–5, Hardcover. Springer.
Sand, C. (2021). ESG is arriving faster than expected. [Podcast]. Privcap Private Equity & Real Estate Podcast. https://open.spotify.com/episode/0VF7RZofs7TfmVDIvlvMou?si=8wqHrdHoTe2urMmCC3MDFQ&nd=1.
Stijven, S., Minnebo, W., & Vladislavleva, K. (2011). Separating the wheat from the chaff: on feature selection and feature importance in regression random forests and symbolic regression. In Steven Gustafson and Ekaterina Vladislavleva editors, 3rd symbolic regression and modeling workshop for GECCO 2011, pp. 623–630, Dublin, Ireland, ACM.
Securities and Exchange Board of India (SEBI). (2022). Consultation Paper on Environmental, Social and Governance (ESG) Rating Providers for Security Markets. https://www.sebi.gov.in/reports-and-statistics/reports/jan-2022/consultation-paper-on-environmental-social-and-governance-esg-rating-providers-for-securities-markets_55516.html
SECURITIES AND EXCHANGE COMMISSION. 2010. Volume 97 No 15. P. 2416. https://books.google.pt/books/about/SEC_Docket.html?id=LBk7AQAAMAAJ&redir_esc=y.
SECURITIES AND EXCHANGE COMMISSION. 2022. Release Nos. 33–11042; 34–94478; File No. S7–10–22. https://www.sec.gov/rules/proposed/2022/33-11042.pdf.
S&P Global. (2021). The Sustainability Yearbook 2021. https://www.upl-ltd.com/press_release/Fanzip28HTTQt9cyBTrxk31z9HQU9VtQ1reSgEXG.pdf.
Smits, G. F., Vladislavleva, E., & Kotanchek, M. (2011). Scalable symbolic regression by continuous evolution with very small populations. In Genetic Programming Theory and Practice VIII, Genetic and Evolutionary Computation Vol.8, Rick Riolo,Trent McConaghy, and Ekaterina Vladislavleva (Editors), Chapter 9, Published: 2011, Springer, ISBN: 978–1–4419–7746–5.
Snow, D. 2021. ESG is arriving faster than expected. [Podcast]. Privcap Private Equity & Real Estate Podcast. https://open.spotify.com/episode/0VF7RZofs7TfmVDIvlvMou?si=8wqHrdHoTe2urMmCC3MDFQ&nd=1.
S&P Global, How ESG factors impact Credit Risk.
The Global Compact. (2005). Who cares wins: Connecting financial markets to a changing world.
Thorne, J. (2021, Novomber 14). At COP26, investors steal the stage from diplomats. Pitchbook, Inc. https://pitchbook.com/news/articles/cop26-investors-venture-capital-clean-tech-climate
Venegas, P. (2021). Trustable risk scoring for non-bank gateways in blockchain and DLT financial networks. Unifying Themes in Complex Systems X.
Wheeler, M. (2019). The future of Denim, Part #3: Waste not; water not—innovation. Fashion Revolution. https://www.fashionrevolution.org/the-future-of-denim-part-3-waste-not-water-not-innovation/
Wolfram Research, Inc., Mathematica, Version 12.2.0, Champaign, IL (2021).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix
Appendix
See Table 1.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Venegas, P., Britez, I., Gobet, F. (2022). Ensemble Models Using Symbolic Regression and Genetic Programming for Uncertainty Estimation in ESG and Alternative Investments. In: Walker, T., Davis, F., Schwartz, T. (eds) Big Data in Finance. Palgrave Macmillan, Cham. https://doi.org/10.1007/978-3-031-12240-8_5
Download citation
DOI: https://doi.org/10.1007/978-3-031-12240-8_5
Published:
Publisher Name: Palgrave Macmillan, Cham
Print ISBN: 978-3-031-12239-2
Online ISBN: 978-3-031-12240-8
eBook Packages: Economics and FinanceEconomics and Finance (R0)