Euro Stoxx Research Articles

Combination of ESG scores and prediction-based returns using long short-term memory neural networks to generate responsible portfolios

ABSTRACT The significance of the environmental, social, and governance (ESG) factors has risen substantially among investors in recent years. Similarly, machine learning techniques have allowed for improvements in the prediction of stock prices. Our research combines ESG factors and prediction-based returns using recurrent neural networks to create profitable-sustainable portfolios that can consistently beat the market index in return and ESG scores. Our analysis focuses on the components of the EURO STOXX 50Ⓡ Index during the year 2021 and the first half of 2022, allowing us to analyze two different market scenarios, continuous growth and bear market, respectively. This paper provides empirical evidence that combining machine learning with ESG scores and its application in portfolio optimization can achieve higher returns and higher ESG performance depending on the macroeconomic context and presents the trade-off between the Sharpe Ratio and the ESG score of the optimized portfolios for different scenarios.

Exploring Entropy-Based Portfolio Strategies: Empirical Analysis and Cryptocurrency Impact

Exploring Entropy-Based Portfolio Strategies: Empirical Analysis and Cryptocurrency Impact

Portfolio Optimization with Prediction-Based Return Using Long Short-Term Memory Neural Networks: Testing on Upward and Downward European Markets

AbstractIn recent years, artificial intelligence has helped to improve processes and performance in many different areas: in the field of portfolio optimization, the inputs play a crucial role, and the use of machine learning algorithms can improve the estimation of the inputs to create robust portfolios able to generate returns consistently. This paper combines classical mean–variance optimization and machine learning techniques, concretely long short-term memory neural networks to provide more accurate predicted returns and generate profitable portfolios for 10 holding periods that present different financial contexts. The proposed algorithm is trained and tested with historical EURO STOXX 50® Index data from January 2015 to December 2020, and from January 2021 to June 2022, respectively. Empirical results show that our LSTM neural networks are able to achieve minor predictive errors since the average of the MSE of the 10 holding periods is 0.00047, the average of the MAE is 0.01634, and predict the direction of returns with an average accuracy over the 10 investment periods of 95.8%. Our prediction-based portfolios consistently beat the EURO STOXX 50® Index, achieving superior positive results even during bear markets.

The degree of Asian-European markets connectedness: examining the impact of global disorders using a spectral analysis

PurposeThis paper aims to examine potential diversification benefits between Eurozone (i.e. EURO STOXX 50) and key Asia markets: HSI (Hong Kong), KOSPI (South Korea), NIKKEI 225 (Japan) and TSEC (Taiwan). The sample covers the period from 04-01-2008 to 19-10-2023 in daily frequency.Design/methodology/approachThe empirical investigation is based on the wavelet coherence analysis, which is a localized correlation coefficient in the time and frequency domain.FindingsThe results provide evidence that long-term diversification benefits exist between EURO STOXX and NIKKEI, EURO STOXX and KOSPI (after 2015) and there are signs for the pair and EURO STOXX-TSEC (after 2014). During the short term, there are signs of diversification benefits during the sample period. However, during the medium term, the diversification benefits seem to diminish.Originality/valueThese results have crucial implications for investors regarding the benefits of international portfolio diversification.

Quantum Computing Approach to Realistic ESG-Friendly Stock Portfolios

Finding an optimal balance between risk and returns in investment portfolios is a central challenge in quantitative finance, often addressed through Markowitz portfolio theory (MPT). While traditional portfolio optimization is carried out in a continuous fashion, as if stocks could be bought in fractional increments, practical implementations often resort to approximations, as fractional stocks are typically not tradeable. While these approximations are effective for large investment budgets, they deteriorate as budgets decrease. To alleviate this issue, a discrete Markowitz portfolio theory (DMPT) with finite budgets and integer stock weights can be formulated, but results in a non-polynomial (NP)-hard problem. Recent progress in quantum processing units (QPUs), including quantum annealers, makes solving DMPT problems feasible. Our study explores portfolio optimization on quantum annealers, establishing a mapping between continuous and discrete Markowitz portfolio theories. We find that correctly normalized discrete portfolios converge to continuous solutions as budgets increase. Our DMPT implementation provides efficient frontier solutions, outperforming traditional rounding methods, even for moderate budgets. Responding to the demand for environmentally and socially responsible investments, we enhance our discrete portfolio optimization with ESG (environmental, social, governance) ratings for EURO STOXX 50 index stocks. We introduce a utility function incorporating ESG ratings to balance risk, return and ESG friendliness, and discuss implications for ESG-aware investors.

The Influence of Board Characteristics on Corporate Social Performance

This paper explores the relationship between relevant board characteristics and the corporate social performance represented by the Social pillar of ESG scores. By applying the generalised method of moments (GMM) system version of the Arellano-Bond estimator, we analyse the 50 biggest and most traded companies in the Eurozone from 2015 to 2022. Our empirical evidence shows that more gender-diverse and independent boards, as well as the presence of a CSR sustainability committee, enhance corporate social performance. These results are largely confirmed by investigating the four sub-pillars of Social score, i.e. Human Rights, Workforce, Product Responsibility, and Community. To our knowledge, this paper is the first to highlight how high corporate governance standards positively affect the Social pillar in the Euro Stoxx 50 index context. Our findings provide important implications for several stakeholders, including regulators and policymakers. Increasing attention should be paid to board characteristics to improve corporate social performance.

The Impact of COVID-19 Epidemic on the Hedging Islamic and Conventional Stock Markets with Financial Assets

This study investigates optimal hedging ratios for Islamic and conventional stock markets during the COVID-19 pandemic using the DCC (Dynamic Conditional Correlation), ADCC (Asymmetric Dynamic Conditional Correlation), and GO-GARCH (Generalized Orthogonal GARCH) models. The effectiveness of various financial assets as hedges is evaluated, and findings indicate that the DJCOM (Dow Jones Commodity), VISTOXX (Euro STOXX 50 Volatility Index), and VIX (Chicago Board Options Exchange Volatility Index) indices exhibit superior effectiveness across both market types, particularly DJCOM showing exceptional performance during the COVID-19 period. The hedging analysis indicates that the hedge ratios vary and depend upon the hedge instrument included in the portfolio. Furthermore, the empirical results indicate that the global impact of the pandemic diminishes the viability of one of the six assets as a safe haven instrument. In conclusion, these findings provide valuable insights for investors and portfolio managers aiming to utilize Gold, Brent, VISTOXX, VIX, CDS (Credit Default Swap), and DJCOM for portfolio rebalancing to mitigate risks associated with volatile Islamic and conventional stock returns. These conclusions contribute significantly to helping investors adjust their investment strategies more effectively and adapt to changing market conditions.

Финансовое заражение российского фондового рынка от европейского в период пандемии COVID-19

This paper investigates the transmission of financial contagion from the European to the Russian stock market during the COVID-19 pandemic. Financial contagion refers to the spread of instability and shocks across individual countries, sectors, or markets during a crisis, where the relationship between returns and volatility of different assets goes beyond normal interactions. Using the construction of extended autoregressive models, we test the contagion of the RTSI composite index from the EURO STOXX 50 index, with the US dollar exchange rate and the spot price of Urals crude oil serving as control variables. The calculation of the moving coefficient of variation in assets prices allows us to distinguish the pre-crisis, crisis and post-crisis periods, for which three separate autoregressive models are built. The contagion of the Russian stock market from the European stock market in these models is identified in two ways: 1) based on the growth and significance of estimated coefficient for the tested variable (STOXX 50 index return) during the crisis; 2) through an increase in the contribution of the tested variable to the explained variance of the dependent variable (RTSI return). In addition, we tested contagion based on the method of central co-moments of the distribution of returns, skewness and volatility of the tested and dependent variable. The analysis has convincingly demonstrated the existence of a financial contagion effect from the European stock market to the Russian stock market in the short term — strengthening of the impact of the European STOXX 50 index on the Russian RTSI index in the acute phase of the pandemic. Understanding the factors contributing to the spread of market shocks in the context of financial globalization can help policymakers to implement effective financial regulatory measures and maintain long-term financial stability in line with national interests. For investors, it helps to identify potential risks and opportunities, enabling optimal hedging and diversification response strategies.

The impact of intangible assets on market valuation: evidence from EURO STOXX 50 companies

The impact of a company's intangible assets on its market value has been a topic of great interest. Many studies have focused on various factors, such as industry, size, age, indebtedness, and profitability of companies, which influence decisions regarding the disclosure of information about intangible assets. This study examines the role of intangible assets in the valuation of a company's market value and takes into account other firm-specific characteristics. Our analysis was conducted on a sample of 50 publicly traded companies that are part of the EURO STOXX 50 index and come from eight countries in the eurozone: Belgium, Finland, France, the Netherlands, Ireland, Germany, Spain, and Italy. The study covered a five-year period from 2018 to 2022.The results of our study indicate that intangible assets have a significant impact on a company's market value. In conclusion, our study highlights the growing importance of intangible assets in today's economy and their significant influence on a company's market value. Investors can benefit from a deeper understanding of these factors, aiding them in investment decisions. For companies, the strategic management of intellectual assets is essential for long-term success. As the importance of intangible assets continues to rise, further research in this area is necessary to gain deeper insights into their impact on the business world.

PERSISTENCE IN EUROPEAN STOCK MARKET RETURNS AND VOLATILITY

This paper applies fractional integration techniques to analyze persistence in stock market returns and volatility at different frequencies in the case of various European indices, specifically the French CAC, the Spanish IBEX 35, the German DAX, the British FTSE 100, and the Euro Stoxx 50, over the period from January 2018 to January 2023.Returns are calculated as the first differences of the logged prices, while absolute and squared returns are used as volatility proxies. The method used yields estimates of the differencing parameter d, which is allowed to take any real value, including fractional ones, and represents a measure of persistence. This parameter provides information about whether the series of interest exhibit either long memory or mean reversion. Specifically, a value of d greater than 0 indicates the presence of long memory in the series, while a value less than 1 implies mean reversion, with the effects of shocks being transitory. The results vary depending on the data frequency. More precisely, evidence of long memory is found for returns at the daily frequency only and for volatility proxies at both the weekly and daily frequencies but not at the monthly frequency. In most cases our findings imply that stock prices are I(1) and thus follow a random walk, which is consistent with the efficiency markets hypothesis (EMH).

Diversity as value driver in Euro Stoxx 50 companies

PurposeCorporate diversity encompasses the different talents, knowledge, cultures, experiences and values of its employees. This diversity is reflected in multiple characteristics, such as race, age, gender, social class, religion, sexual orientation, ethnicity, culture and disability. The objective of this study is to identify if diversity is a value driver.Design/methodology/approachWe take the diversity score from the Diversity Leaders Index 2023 published by Financial Times (FT) and Statista; this will be our independent variable in linear regression models whose objective variables are relevant fundamental indicators of the Euro Stoxx 50 companies. It is, therefore, a cross-sectional sample with financial data taken as of the current date. We have 37 Euro Stoxx 50 components included in the diversity ranking.FindingsThe results indicate that diversity is not a value driver for trading volume, for its revenue, or for systematic risk measured by the beta parameter. However, it is observed, in a confidence interval of 90%, that the most diverse companies are larger (according to their market capitalization). In addition, the most diverse companies are more profitable [return on assets (ROA)] and valued by the market [price to earnings ratio (PER)] in a confidence interval of 95%.Originality/valueThese results indicate that companies should promote corporate diversity as a management strategy, as it is observed that more diverse companies are more profitable and valued by the market. This study provides a quantitative vision in the context of homogeneous companies such as the Euro Stoxx 50 Index on the aspects in which diversity is a value driver.

The impact of a firm’s ESG score on its cost of capital: can a high ESG score serve as a substitute for a weaker legal environment

PurposeThis article aims to analyse the relationship between the environmental, social and governance (ESG) score and the cost of capital of 600 large, mid and small capitalization companies across 17 countries that are component of the EURO STOXX 600 Index. By examining whether ESG has an impact on the cost of capital, this article contributes to the solutions to improve the impact of organizations and societies on sustainable development. The article further examines whether the effect is because of the environmental, social and/or governance components. In addition, the article analyses which WACC component (i.e. the cost of equity, the cost of debt, the beta or the leverage ratio) is affected. Furthermore, this article analyses whether a high ESG score can substitute for a weaker legal environment.Design/methodology/approachThe results were obtained by using ordinary least squares panel data modelling to analyse the relationship between the ESG score and the cost of capital. The sample consists of companies that are part of the STOXX Europe 600 Index over the period 2018–2021, which is composed of 600 companies, including large, mid and small capitalization firms listed across 17 countries. The sample finally includes 1,960 firm-year observations.FindingsCompanies with a higher ESG score tend to have a lower cost of capital, but this relationship holds only for firms domiciled in countries with a weaker legal environment. In addition, these firms should not only increase their ESG score to create a more sustainable environment but also to reduce their cost of debt. Environmental and social factors have a significantly negative impact on the cost of capital only in countries with a weaker legal environment, while the governance component positively impacts the cost of capital by allowing firms to borrow more.Research limitations/implicationsThere is not yet a standardized taxonomy to define ESG, making the study dependent on commercial data providers.Practical implicationsThe new insights can be used by companies domiciled in countries with weaker legal environments to reduce their cost of capital. The results also allow us to know on which components of the ESG score to focus. It can also help policymakers, specifically those in countries with a weaker legal environment, to provide incentives to further stimulate ESG investments and disclosure, thereby contributing to a more sustainable society.Social implicationsTo achieve the sustainable development goals put forward by the United Nations, it is important for firms to invest in ESG projects. It is nevertheless insightful to know whether these ESG investments, which are currently observed as a cost, also provide benefits to firms and in which countries. If firms clearly see the advantages of investing in ESG projects, they are likely to proactively engage in them.Originality/valueThis article is the first, to the best of the authors’ knowledge, to focus on 17 European countries, thereby capturing divergent legal environments. This setting allows us to answer the main novel research question, namely, whether the ESG score can act as a substitute for the legal environment in which the company is domiciled. The article also goes further than previous articles by examining whether the effect is because of the environmental, social and/or governance component and whether these impact the components of the weighted cost of capital, namely, the cost of equity, the cost of debt, the beta or the leverage ratio of the companies.

Rethinking the effect of ESG practices on profitability through cross-dimensional substitutability

Over the last thirty years, sustainable business practices and ESG ratings have become increasingly popular in the business context and academic debate. Nonetheless, due to differences in methodological and theoretical approaches, more consensus has yet to be reached in the economic literature on the relationship between ESG practices and financial performance at the firm level. This work addresses the question empirically, focusing on a sample of firms listed in the Euro Stoxx 300 index. Three novel indicators are proposed to measure the firm's sustainable practices and capture the business's Environmental, Social, and Governance (E, S, G) dimensions. These indicators combine qualitative ratings on adherence to ESG standards with quantitative observations on ESG data disclosure to account for strategic behaviors on the part of firms. A dynamic panel model is implemented, considering the three dimensions of ESG practices separately and introducing interaction terms to identify cross-dimensional substitutability/complementarity relations. The results indicate that environmentally friendly business practices are associated with increased profits, while trade-offs across ESG dimensions are revealed.

Does better sustainability reporting assurance lead to better reporting? Evidence from the EURO STOXX 600

Does better sustainability reporting assurance lead to better reporting? Evidence from the EURO STOXX 600

Extending corporate sustainability reporting indicators to projects’ sustainability

Measuring the sustainability performance of an organisation is a rather complex task. This study aims at analysing a broad number of performance indicators related to the economic, environmental, and social pillars of the Triple Bottom Line (TBL) framework and evaluates their applicability toward the development of a sustainable performance measurement system (SPMS) of projects. To this purpose, an analysis of the annual sustainability reports of the listed EURO STOXX Sustainability 40 companies was conducted, identifying the sustainability indicators incorporated in each individual report, and classifying them according to the three pillars of the TBL framework. The analysis of the reports yielded 67 economic indicators, 109 environmental, 130 social, and 38 additional ones, mainly combining the latter two categories, giving 344 unique indicators in total. The proposed system, based on empirical evidence, recommends that selected indicators for an SPMS for projects should relate to predefined subcategories. These are costs, efficiency, and shareholder return for the economic dimension; emissions, energy, paper, resource consumption, waste, and water for the environmental dimension; diversity & equality, ethical behaviour, external commitment, health & safety, training & development, and working conditions for the social dimension.

Fuzzy clustering approach to portfolio management considering ESG criteria: empirical evidence from the investment strategies of the EURO STOXX Index

Environmental, social and governance (ESG) criteria are becoming increasingly important in the construction of investment portfolios. Analysis of the investment markets confirms that these criteria are being actively integrated into investment strategies. This paper presents our approach to incorporating ESG criteria into the portfolio construction process based on an index investment strategy. This strategy is enhanced by the inclusion of ESG criteria in the form of ESG scoring. Investment portfolio construction focuses on the application of three criteria: maximizing ESG score, minimizing risk and maximizing expected return. Our approach applies a fuzzy clustering toolkit to the set of index components. In the resulting fuzzy clusters, their core part (companies that do not belong to other clusters) and the fuzzy part are separated. The proposed investment strategy involves the construction of portfolios with a variation of the components of the fuzzy part. A VAWI (Value Added Weekly Index) curve is designed for each portfolio. The optimal strategy is implemented by constructing and reconstructing portfolios according to the upper line of the VAWI set. This investment strategy is demonstrated using the example of the EURO STOXX 50 index, which includes large companies from 11 Eurozone countries.

ESG performance and firms’ business and geographical diversification: An empirical approach

Diversification is primarily associated with improved performance, although the increasing complexity of conglomerates may offset these benefits. ESG scores and their dimensions serve as performance indicators and may also be risk components influencing cash flows. This study aims to investigate the relationship between ESG performance and firms’ diversification. We hand-collected data on business segments and geographical diversification from the constituents of the Euro Stoxx 50 over a large period, from 2002 to 2020. Our findings indicate that geographical diversification does not influence ESG variability. However, better ESG scores are observed in firms with more business segments, that do not have a dominant business segment with a significant role in the firm nor are concentrated in the most representative business segments. However, better ESG scores are also associated with greater asymmetry in the contribution of each business segment to the entire group. Collectively, we shed light on the importance of business diversification in improving sustainability performance across ESG dimensions.

Testing the correct specification of a system of spatial dependence models for stock returns

This paper provides two specification tests for the system of spatial autoregressive model of order m. We derive the theoretical limit distributions and show in a detailed Monte Carlo simulation study that the tests result in reasonable sized testing procedures with large power. In the empirical application, we analyze Euro Stoxx 50 returns in two different time spans, looking for insights how well models with different specifications of the spatial weighting matrices (local, country, industry and country-industry specific dependencies including interaction effects) fit to the data. The analyzes also demonstrate the ability of the tests to detect inaccurate Value-at-Risk forecasts.

Herding behavior and the dynamics of ESG performance in the European banking industry

We investigate the dynamics of ESG performance and explore the potential driving force, including the role of herd behavior among banks. Utilizing Phillips and Sul (2007)'s panel data convergence model and data from the EURO STOXX Banks index, we identify a significant divergence in ESG performance followed by convergence towards separate clusters or clubs after 2018. Notably, banks with lower Return on Equity (ROE) and leverage demonstrate herding tendencies towards improved ESG performance, emphasizing sustainability objectives and community ties. The study contributes to understanding the potential driving forces behind ESG convergence among EU banks.

Global financial cycle: Impact on Ukraine

Global financial fluctuations that arise in the financial centres – the US and the EU through international channels of monetary transmission affect the financial markets of peripheral countries, including Ukraine, where the assessment and consideration of such an impact is an important element of monetary policy. Therefore, the purpose of the article was to assess the impact of cyclical fluctuations of the global financial situation on the financial sector of Ukraine’s economy. As a result of correlation analysis, a direct relationship between leverage indicators in Ukraine and the Chicago Board Options Exchange Volatility Index and Euro Stoxx Volatility Index has been revealed. At the same time, the direct relationship between these indices and the growth of domestic credit in Ukraine contradicts the concept of the global financial cycle and may indicate the presence of more important factors of domestic credit. Correlation analysis of the volatility index of the Chicago Board Options Exchange and capital flows in Ukraine showed that in the years of increased global uncertainty and volatility, the volume of capital flows decreased, especially for portfolio debt instruments. Analysis of the cyclical components of the global and domestic credit cycle in Ukraine obtained with the Godric-Prescott filter indicates a higher level of volatility in domestic lending. The obtained value of the concordance coefficient did not make it possible to draw an unequivocal conclusion about the counter- or procyclical nature of domestic credit fluctuations relative to the global volume of loans in the non-banking sector. It has been found that the global financial cycle was not a significant factor in domestic credit in Ukraine in the studied period. The practical significance of the results lies in the fact that the National Bank of Ukraine will be able to implement a monetary policy independent of the global financial fluctuations and limit the outflow of capital during the period of growing uncertainty in the international financial markets