ESG Portfolio Research Articles

Advancing ESG Portfolio Optimization: Methods, Progress, and Future Directions

Objective - The integration of environmental, social, and governance (ESG) criteria into investment portfolios has emerged as a critical field of study, underscoring the interconnectedness between financial markets and global sustainability objectives. Methodology/Technique - This systematic literature review analyzes 157 academic documents, focusing on ESG portfolio optimization methodologies and identifying emerging trends. Key methods reviewed include genetic algorithms, dynamic optimization models, multi-objective optimization frameworks, and machine learning techniques. Findings - Despite considerable advancements, gaps remain, such as the need for broader application across diverse markets and asset classes, improved risk-return assessments, and standardized ESG data reporting. Future research should also investigate the role of central banks and regulators in fostering sustainable finance. Novelty - By addressing these gaps, stakeholders can better align investment practices with sustainability goals, contributing to a more resilient and inclusive global economy. Type of Paper: Review JEL Classification: G11, Q56, G28, G32 Keywords: Sustainable Investment, Sustainable Finance, ESG Portfolio Performance, ESG Risk Management, ESG Portfolio Optimization Reference to this paper should be referred to as follows: Billah, A.L; Koesrindartoto, D.P; Faturohman, T. (2024). Advancing ESG Portfolio Optimization: Methods, Progress, and Future Directions, Acc. Fin. Review, 9(2), 65 – 73. https://doi.org/10.35609/afr.2024.9.2(2)

ESG and firm value: A hybrid literature review on cost of capital implications from Scopus database

AbstractThe relationship between ESG and firm value has been a relevant subject of study in recent years. We conducted a hybrid literature review to understand the literature's findings on this relationship and its implications in terms of cost of capital. First, a keyword co‐occurrence analysis on a 122 ABS ranked journals articles selection from Scopus database was adopted to identify and investigate the main research fields of the current literature. Then a content analysis through the bibliographic coupling of the most globally cited contributions was made, defining a final sample of 50 articles obtained through a minimum threshold of at least 15 total global citations (TGCs). We found that studies on the cost of debt configuration are more aimed at determining the implications on firm value, while most contributions on the cost of equity focus on the assessment of the risk–return profile for the investor or the construction of an ESG portfolio. Furthermore, we found that most of the literature has a consensus view on the lack of transparency behind the ESG ratings and their construction methodology, stating that disagreement on ESG ratings not only limits the results of empirical analysis, but can also negatively affect firm value due to a higher level of uncertainty.

Implementation of deep learning models in predicting ESG index volatility

The consideration of environmental, social, and governance (ESG) aspects has become an integral part of investment decisions for individual and institutional investors. Most recently, corporate leaders recognized the core value of the ESG framework in fulfilling their environmental and social responsibility efforts. While stock market prediction is a complex and challenging task, several factors associated with developing an ESG framework further increase the complexity and volatility of ESG portfolios compared with broad market indices. To address this challenge, we propose an integrated computational framework to implement deep learning model architectures, specifically long short-term memory (LSTM), gated recurrent unit, and convolutional neural network, to predict the volatility of the ESG index in an identical environment. A comprehensive analysis was performed to identify a balanced combination of input features from fundamental data, technical indicators, and macroeconomic factors to delineate the cone of uncertainty in market volatility prediction. The performance of the constructed models was evaluated using standard assessment metrics. Rigorous hyperparameter tuning and model-selection strategies were implemented to identify the best model. Furthermore, a series of statistical analyses was conducted to validate the robustness and reliability of the model. Experimental results showed that a single-layer LSTM model with a relatively small number of neurons provides a superior fit with high prediction accuracy relative to more complex models.

Assessing risk profiles of ESG portfolios in global financial markets

Assessing risk profiles of ESG portfolios in global financial markets

Risk Characterization of Firms with ESG Attributes Using a Supervised Machine Learning Method

We examine the risk–return tradeoff of a portfolio of firms that have tangible environmental, social, and governance (ESG) attributes. We introduce a new type of penalized regression using the Mahalanobis distance-based method and show its usefulness using our sample of ESG firms. Our results show that ESG companies are exposed to financial state variables that capture the changes in investment opportunities. However, we find that there is no economically significant difference between the risk-adjusted returns of various ESG-rating-based portfolios and that the risk associated with a poor ESG rating portfolio is not significantly different than that of a good ESG rating portfolio. Although investors require return compensation for holding ESG stocks, the fact that the risk of a poor ESG rating portfolio is comparable to that of a good ESG rating portfolio suggests risk dimensions that go beyond ESG attributes. We further show that the new covariance-adjusted penalized regression improves the out-of-sample cross-sectional predictions of the ESG portfolio’s expected returns. Overall, our approach is pragmatic and based on the ease of an empirical appeal.

Beyond hype: Unveiling the herd effect in ESG and non-ESG cryptocurrency portfolios

This paper investigates herding behavior in the cryptocurrency market, specifically comparing environmental, social, and governance (ESG)-designated assets and non-ESG assets. It addresses a research gap concerning investor behavior towards ESG and non-ESG cryptocurrencies. Our study reveals that investor herding behavior manifests in specific years and in response to significant events, such as El Salvador’s adoption of Bitcoin. Notably, the findings suggest the presence of intentional herding behavior in 2023 data for ESG and non-ESG cryptocurrencies. These insights offer valuable guidance for investors and policymakers seeking to mitigate risks and optimize portfolio allocation strategies.

Unveiling the timeless potential: A comprehensive analysis of ESG integration in Chinese listed firms

This paper provides a practical guide for integrating Environmental, Social, and Governance (ESG) information into portfolio construction in Chinese listed firms. We analyze panel data from 2015 to 2019, revealing that higher ESG scores correlate with increased stock market returns. We construct an ESG portfolio, identifying strategies that affirm ESG's value. Notably, our enhancement portfolios for both CSI 300 and CSI 500 consistently outperform their benchmarks. Through Brinson attribution analyses, we attribute the excess return primarily to individual stock selection. Our findings underscore the incremental value of incorporating ESG information in stock price explanations.

ESG rating changes and portfolio returns: A wavelet analysis across market caps

This study implements advanced wavelet analysis to affirm a strong positive connectedness between E, S, and G pillar ratings and equity portfolio returns, particularly at low frequencies or long-term investment horizons. However, for E-pillar strategies, a transient negative "equity greenium" phase in 2019–2020 indicates that elevated E-ratings coincide with reduced financial performance. Bidirectional relationships challenge conventional ESG score notions, with weaker global ESG return connections, mid-cap portfolio exceptions (2015–2017), and short-term impacts on large caps (2019–2021). Inter-pillar connections, especially post-2015 E and S dynamics, unveil evolving complexities. Hierarchical connectedness patterns among portfolios underscore unique dynamics, emphasizing the multifaceted ESG landscape.

The trade-off between ESG screening and portfolio diversification in the short and in the long run

The trade-off between ESG screening and portfolio diversification in the short and in the long run

Comparative Risk Assessment of ESG Portfolios in Emerging Market Vs Developed Market

Comparative Risk Assessment of ESG Portfolios in Emerging Market Vs Developed Market

Machine learning for sustainable investing: Current applications and overcoming obstacles in ESG analysis

The intersection of Environmental, Social, and Governance (ESG) issues and Machine Learning (ML) has garnered significant attention in recent years as companies and investors increasingly recognize the paramount importance of sustainable and responsible business practices. ML techniques have been actively explored to tackle various ESG-related challenges, including enhancing ESG data quality and availability, developing comprehensive and dynamic ESG risk models, and optimizing ESG portfolios. The overall process of applying ML models in ESG analysis involves data collection, preprocessing, model training and evaluation, and model interpretation. Commonly used ML models in ESG analysis include logistic regression, decision trees, random forests, and support vector machines. However, there are notable obstacles to overcome, such as the lack of standardization and transparency in ESG data, as well as the potential for bias and ethical concerns in ML-based approaches. Further research and collaborative efforts among researchers and practitioners are crucial to fully realize the potential of ML in enhancing ESG analysis while ensuring transparency, ethical use, and alignment with sustainable and responsible investing principles.

The futility of measuring relative performance of ESG portfolios if ESG investing improves the market performance

The futility of measuring relative performance of ESG portfolios if ESG investing improves the market performance

An Analysis of Volatility and Risk-Adjusted Returns of ESG Indices in Developed and Emerging Economies

The importance of Environmental, Social, and Governance (ESG) aspects in investment decisions has grown significantly in today’s volatile financial market. This study aims to answer the important question of whether investing in ESG-compliant companies is a better option for investors in both developed and emerging markets. This study assesses ESG investment performance in diverse regions, focusing on developed markets with high GDP, specifically the USA, Germany, and Japan, alongside emerging nations, India, Brazil, and China. We compare ESG indices against respective broad market indices, all comprising large and mid-cap stocks. This study employs a variety of risk-adjusted criteria to systematically compare the performance of ESG indices against broad market indices. The evaluation also delves into downside volatility, a crucial factor for portfolio growth. It also explores how news events impact ESG and market indices in developed and emerging economies using the EGARCH model. The findings show that, daily, there is no significant difference in returns between ESG and conventional indices. However, when assessing one-year rolling returns, ESG indices outperform the overall market indices in all countries except Brazil, exhibiting positive alpha and offering better risk-adjusted returns. ESG portfolios also provide more downside risk protection, with higher upside beta than downside beta in most countries (except the USA and India). Furthermore, negative news has a milder impact on the volatility of ESG indices in all of the studied countries except for Germany. This suggests that designing a portfolio based on ESG-compliant companies could be a prudent choice for investors, as it yields relatively better risk-adjusted returns compared to the respective market indices. Furthermore, there is insufficient evidence to definitively establish that the performance of ESG indices varies significantly between developed and emerging markets.

ESG portfolio for TDFs with time‐varying higher moments and cardinality constraint

AbstractPension funds are crucial in supporting environmentally sustainable and socially responsible investments. This paper focuses on an essential product of pension funds, target date funds (TDFs), constructing its portfolio model that considers environmental, social, and governance (ESG) investment. Our model utilizes the mean–variance–skewness–kurtosis optimization framework and accounts for the time‐varying relationship between realized higher moments and subsequent TDFs performance. A cardinality constraint is included to prevent over‐diversification and reduce costs, controlling the number of constituent funds in the TDFs. Since the model is multiobjective, we transform it into a single‐objective optimization through the investment manager's preferences. The numerical experiments represent the most suitable time‐varying higher moment strategy for the Chinese market and demonstrate the model's applicability to managers prioritizing risk over returns, which resonates well with the conservative investment of pension funds. We prove that controlling the number of constituent funds with cardinality constraint is advantageous for improving TDFs' performance. By selecting ESG funds as underlying assets, we highlight that green TDFs have better long‐term performance in terms of higher moment risk.

Is There Any Effect of ESG Scores on Portfolio Performance in South Africa?

Abstract This study compares the performance of five portfolios built according to the level of integration of environmental, social and governance values in the case of South Africa, over the period of four years from 2 January 2019 to 29 December 2022. The portfolios were built according to (1) the two dimensions of ESG ratings (responsible and irresponsible) and (2) the two levels of ESG implication (partially and significantly), and there is also a portfolio for non-engaged companies (no-reporting). Many recent studies comparing ESG and non-ESG portfolio performance have reported contradictory results so that this debate remains inconclusive. The main question I explore is whether portfolios integrating ESG values really matter in the case of a developing country with many economic and social challenges, as in the case of South Africa. For the purpose of the study, I have used four risk-adjusted measures (Sharpe ratio, Treynor ratio, Modigliani-Squared and Jensen’s alpha) for the performance evaluation. This study found an adverse effect of ESG on portfolio performance. Overall, the ESG Irresponsible portfolios achieved a better performance as compared to its counterparts. The study findings contribute to and enrich the academic literature by comparing the performance of five ESG portfolios in the South African context.

An Efficient Predicative Approach of ESG Invest Scoring Using Random Forest Algorithm

Environmental, social, and governance (ESG) factors are considered while making business and investment choices. Human capital and climate change are causing firms to re-evaluate their focus away from conventional financial gains. Investors are drawn to socially responsible investments due to a shift in global attitudes toward sustainability and the availability of environmental, social, and governance (ESG) indicators. The strategic value of ESG measures has been researched extensively for private organisations, but less attention has been paid to public corporations. The use of quantitative methodologies for improving and standardising ESG grading, as well as for building ESG portfolios, is neglected, despite the fact that ESG-driven portfolios currently represent a significant and rising share of global assets under management. Deep learning is used to develop an ESG investment score prediction algorithm in this article. The ESG score is analysed and predicted using a random forest learning algorithm in the suggested system.

ESG, time horizons, risks and stock returns

Investment time horizon is an important part of significance of ESG factors. This research examines the role of ESG factors in returns and risks in short- and medium-term investment periods. It compares (a) the returns and risks of ESG portfolios between before scoring and after scoring, and (b) the returns and risks between ESG portfolios and their peers.The main results suggest that after scoring most short-term ESG portfolios have similar returns, but lower risks than before scoring. The returns of ESG portfolios are similar to those of nonESG portfolios for both short- and medium-term. There are more ESG portfolios, whose risks are different from nonESG portfolios, in the short-term investment than in the medium-term.ESG factors therefore play a greater role in risks than in returns, and in the short-term than in the medium-term. Additionally, the role of ESG factors in risks varies from industry to industry.

Analysis of Environmental, Social, and Governance Performance in Indonesia: Role of ESG on Corporate Performance

Issues regarding environmental, social, and governance have a positive role in corporate performance, especially in developed countries. Unlike accounting performance which only considers business performance, the ESG score reflects long-term performance because it considers environmental, social, and governance factors. Firms in Indonesia cannot improve their ESG score due to the limited resource and shareholders' reactions. This study compares the investment performance between the top 9 ESG constituents and the LQ45 index. Further, this study examines the impact of the ESG score on financial performance. This research used non-financial companies listed on Indonesia Stock Exchange as a sample. Modified Sharpe ratio and panel data regression were used as a method. The result showed that the ESG portfolio has a better Sharpe ratio than LQ45. However, the regression shows a negative effect on the ESG score on financial performance. Increasing the ESG score decreases financial performance because it requires higher investment and opportunity costs. This study has several recommendations related to implementing ESG at the corporate level.

Did ESG portfolio augment investors’ wealth during Covid19? Evidence from Indian stock market

Purpose This paper aims to empirically examine the performance of the high-ESG (environment, social and governance) portfolio vis-à-vis the low-ESG portfolio at the Indian stock market before and during the Covid19 pandemic. Design/methodology/approach The absolute rate of return and several risk-adjusted performance measures, for instance, Sharpe ratio, Modigliani–Modigliani measure, Treynor ratio, Jensen’s alpha, information ratio, Fama’s decomposition measure and Fama and French’s three-factor model, have been used in this study along with the t-test. Findings All three indices (CARBONEX, GREENEX and BSE 500) had better returns during Covid19 period as compared to the pre-Covid19 period. However, these returns were not statistically significant. During Covid19, the risk of the indices also rose, but they provided better returns for the additional risk taken. Finally, it is concluded that the performance of high-ESG and low-ESG stock portfolios did not differ significantly in both periods. Practical implications The study is relevant to individual and institutional investors, financial advisors, portfolio managers, corporations, policymakers, market regulators and society at large. Social implications This study emphasized the need to expand the role of ESG investment in India for the benefit of people, communities and society as a whole. Originality/value This research is the first of its kind, to the best of the authors’ knowledge, that compares the performance of a high-ESG portfolio with a low-ESG portfolio both before and during the Covid19, particularly in the Indian context.

Do lower environmental, social, and governance (ESG) rated companies have higher systemic impact? Empirical evidence from Europe and the United States

AbstractIn recent years, companies have increasingly been characterized by environmental, social, and governance (ESG) scores, and investors and academics have raised questions concerning financial performance and investment risks. Now, as the European Banking Authority has acknowledged that ESG risks can potentially impact the economic and financial system, the debate on systemic risk has gained traction. Understanding the relationship between ESG merit and systemic risk is of utmost importance for the stability of the economic and financial system, still, research is limited. Relying on real‐world European and United Stated data, we quantify systemic risk by means of QL‐CoVaR. Empirical analyses of the entire period from 2007 to 2021 show that companies with high ESG scores tend to exhibit low QL‐CoVaR values indicating a positive effect of ESG scores. Such evidence is confirmed by clustering the individual companies into ESG portfolios and focusing on COVID‐19. Additional insights using the individual pillars are also provided.