Future Returns Research Articles

WITHDRAWN: Ex-ante expected changes in ESG and future stock returns based on machine learning

This study has two primary objectives. Firstly, it enhances the reliability and transparency of machine-learning-based models for predicting future changes in environmental, social and governance (ESG) performance. Secondly, it explores the relationship between ex-ante expected changes in ESG and future stock returns. This study collects 3258 STOXX Europe 600 firm-year observations. In the ESG prediction phase, two machine learning algorithms (logistic regression and random forest) are utilised to develop ESG forecasting models. Hyperparameter optimisation and walk-forward validation techniques are employed to address issues of underestimation and information leakage. The machine-learning-based ESG forecasting models are evaluated using three metrics: accuracy, area under the curve (AUC) and area under the precision-recall curve (AUPR). Subsequently, this study investigates the relationship between ex-ante expected ESG changes and future stock returns using the predicted ESG changes. A positive correlation is found between ex-ante expected ESG changes and future stock returns. The supplementary tests also reveal that this positive relationship is highly and statistically significant among large firms and after the COVID-19 pandemic. Moreover, this study introduces a robust and transparent approach for constructing effective machine-learning-based ESG forecasting models using hyperparameter optimisation and walk-forward validation. Additionally, traditional regression analyses are modernised by incorporating machine-learning-predicted independent variables. Furthermore, the findings provide empirical support for stakeholder, agency and resource-based theories. Finally, practical insights are provided to facilitate ESG-focused investment portfolio decision making.

A Research Study on Promoting Investment Awareness and Identifying Optimal Investment Choices Regarding Investor Opportunities

Individuals seek a secure and prosperous life, recognizing the role of financial resources in enhancing their appeal. As a result, they engage in various investment opportunities, viewing investment as the allocation of funds in anticipation of future positive returns. This research aims to explore the level of investment awareness among investors, focusing on understanding investment options and making informed decisions for optimal investment strategies.

Cycles in adult steelhead length suggest interspecific competition in the North Pacific Ocean

Anadromous fishes rely on abundant prey in the ocean to grow large quickly, but prey limitation leads to interspecific competition. When species interactions are difficult to observe, growth can be studied to detect otherwise cryptic signals of competition. We describe a previously undocumented 2-year cycle in the lengths of adult natural-origin steelhead ( Oncorhynchus mykiss) returning to spawn in the Snake River Basin. Returning steelhead were 38 mm shorter on odd return years, not accounting for sex, stock, and years of ocean residence. The well-known cycle in abundance of pink salmon ( Oncorhynchus gorbuscha) from eastern Kamchatka and North America had statistically significant negative effects on returning steelhead lengths that depended on sex and the number of years of ocean residence. These results suggest that competition for limited resources occurs well after initial ocean entry and that interactions during later stages of ocean residence can be influential. Interspecific competition has implications for future returns of steelhead from the ocean, especially as metabolic demands for steelhead increase as the ocean warms.

Hedge funds and the positive idiosyncratic volatility effect

Abstract While it is established that idiosyncratic volatility is negatively priced in the cross-section of stock returns, the relation between idiosyncratic volatility and hedge fund returns is largely unexplored. We document that hedge funds with high idiosyncratic volatility earn higher future risk-adjusted returns of 6 percent p.a. than hedge funds with low idiosyncratic volatility. The outperformance arises because hedge funds trade high idiosyncratic volatility stocks wisely. They pick high volatility stocks when they are underpriced and short-sell high volatility stocks when they are overpriced. Our results support the notion that hedge funds’ idiosyncratic volatility is a measure of managerial skill.

Option trading and equity price efficiency

This paper presents evidence that the reduction in option tick size enhances equity price efficiency. To address the endogeneity issue, I employ an exogenous event, namely the Penny Pilot program. The findings indicate that option trading mitigates equity misvaluation, reduces price delay, accelerates the incorporation of future earnings into equity prices, and eliminates the well-known Post-Earnings Announcement Drift (PEAD). The pilot program significantly increases trading volume and reduces trading costs during the pilot period. Furthermore, the effect of options-to-stock volume on future stock returns is stronger in firms with high short-sale costs. This evidence is consistent with the hypothesis that informed trading boosts trading volume in the options market and integrates information from the options market into equity prices, thereby enhancing equity price efficiency.

Social Capital, Government Expenditures, and Growth

Abstract This paper shows that social capital increases economic growth by raising government investment in human capital through better political incentives and selection. We provide empirical evidence that a greater share of output is spent on public education where social capital is higher, both across countries and across U.S. states. We develop a theoretical model of stochastic endogenous growth with imperfect political agency. Only some people correctly anticipate the future returns to current spending on public education. Greater social diffusion of information makes this knowledge more widespread among voters. As a result, social capital alleviates myopic political incentives to underinvest in human capital. It also helps voters select politicians who ensure high productivity in public education. Through this mechanism, we show that social capital raises the equilibrium growth rate of output and reduces its volatility.

Informed Trading and Return Predictability in China: Research Based on Ensemble Neural Network

ABSTRACT We construct a new informed trading index based on the high-frequency trading data of the Chinese A-share market using the ensemble neural network algorithm. We find that the informed trading index is a strong negative predictor of future aggregate stock market returns, with monthly in-sample and out-of-sample R 2 of 5.45% and 3.53%, respectively, which is far greater than the predictive power of other previously studied informed trading indicators and macroeconomic variables. The asset allocation strategy based on our index can generate large economic gains for the mean-variance investors, with annualized CER (certain equivalent return) gains ranging from 10.91% to 7.80% as the investor’s risk appetite varies. The driving force of the predictive power appears to stem from the liquidity provider role that informed traders play, which decreases the market’s illiquidity risk and lowers the risk premium of equity. Our analysis complements the returns predictability study by adding a new predictor on the one hand and informs market timing strategies on the other.

Sovereign momentum currency returns

We study the relationship between cross-sectional sovereign credit risk and currency spot prices. We find that past (up to 12-month average) sovereign credit risk, measured by sovereign credit default swap (CDS) spreads, predict future currency spot returns. In particular, we document a significant cross-sectional currency portfolio spread in excess of the risk-free rate of return (up to 9.6% p.a.) between the highest and the lowest quintile sovereign CDS spreads. Overall, our results indicate that sovereign credit risk is systematically important for currency returns. Moreover, the level of sovereign credit risk has a persistent effect on currency returns which is consistent with a sovereign momentum effect.

Accounting for bubbles: A discussion of Arif and Sul (2024)

A signal that identifies asset pricing bubbles would be valuable so investors could reposition their portfolios to weather the bubble, yet ex ante bubble identification has proven illusory. Arif and Sul (2024) study whether industry-level investment in net operating asset (NOA) accruals is an ex ante accounting-based signal that predicts bubbles. Using industry-level price run-ups across 49 countries, they find that NOA accruals predict a higher likelihood of a future crash, lower future returns, and larger analyst forecast errors, especially following run-up periods. The authors attribute these patterns to sentiment-driven overinvestment. My discussion summarizes the contributions of Arif and Sul's findings to the asset pricing bubbles, behavioral finance, and aggregate accruals literatures. I also outline empirical challenges faced by studies investigating bubbles and recommend approaches to further strengthen inferences. Finally, I propose opportunities for future research to integrate deeper accounting knowledge into bubble research.

Option‐Implied Ambiguity and Equity Return Predictability

ABSTRACTWe propose a model‐guided option‐implied ambiguity measure to capture uncertainty regarding the return distribution of a risky asset underlying a set of options, and investigate its predictive power on the asset return. A representative investor's ambiguous beliefs or prior distributions on the underlying asset returns are extracted from the market prices of options, the expected volatility of which is then defined as the option‐implied ambiguity and is calculated in line with Brenner and Izhakian. Simulated paths of the calibrated models are utilized to compute all pertinent probability characteristics from a forward‐looking perspective. The empirical results with SSE 50 ETF options indicate that the proposed option‐implied ambiguity has strong predictive power for future returns of SSE 50 ETF. Out‐of‐sample tests also verify the significant predictive ability of the option‐implied ambiguity to the equity returns.

Assessing the impact of climate change on high return levels of peak flows in Bavaria applying the CRCM5 large ensemble

Abstract. ​​​​​​​Severe floods with extreme return periods of 100 years and beyond have been observed in several large rivers in Bavaria in the last 3 decades. Flood protection structures are typically designed based on a 100-year event, relying on statistical extrapolations of relatively short observation time series while ignoring potential temporal non-stationarity. However, future precipitation projections indicate an increase in the frequency and intensity of extreme rainfall events, as well as a shift in seasonality. This study aims to examine the impact of climate change on the 100-year flood (HF100) events of 98 hydrometric gauges within hydrological Bavaria. A hydrological climate change impact (CCI) modeling chain consisting of a regional Single Model Initial-condition Large Ensemble (SMILE) and a single hydrological model was created. The 50 equally probable members of the Canadian Regional Climate Model version 5 large ensemble (CRCM5-LE) were used to drive the hydrological model WaSiM (Water balance Simulation Model) to create a hydro-SMILE. As a result, a database of 1500 model years (50 members × 30 years) per investigated time period was established for extreme value analysis (EVA) to illustrate the benefit of the hydro-SMILE approach for a robust estimation of HF100 based on annual maxima (AM) and to examine the CCI on the frequency and magnitude of HF100 in different discharge regimes under a strong-emission scenario (RCP8.5). The results demonstrate that the hydro-SMILE approach provides a clear advantage for a robust estimation of HF100 using the empirical probability of 1500 AM compared to its estimation using the generalized extreme value (GEV) distribution of 1000 samples of typically available time series sizes of 30, 100, and 200 years. Thereby, by applying the hydro-SMILE framework, the uncertainty from statistical estimation can be reduced. The study highlights the added value of using hydrological SMILEs to project future flood return levels. The CCI of HF100 varies for different flow regimes, with snowmelt-driven catchments experiencing severe increases in frequency and magnitude, leading to unseen extremes that impact the distribution. Pluvial regimes show a lower intensification or even decline. The dynamics of HF100 driving mechanisms depict a decline in snowmelt-driven events in favor of rainfall-driven events, an increase in events driven by convective rainfall, and almost no change in the ratio between single-driver and compound events towards the end of the century.

Does uncertainty affect the limits of arbitrage? Evidence from the U.S. stock markets

This study analyzes how uncertainty affects the correction process of mispricing. We extract stock market data from the United States spanning from January 1976 to December 2016, and discover that uncertainty exerts a notable impact on traders’ decision-making processes. Various robustness tests have been conducted to validate the credibility of our findings. Notably, the extension of the sample duration until December 2022, encompassing the disruptive COVID-19 pandemic, serves to fortify the cohesion and reliability of our primary analysis, with the findings exhibiting consistency. Additionally, we examine how investor sentiment affects future returns under different uncertainty and overpricing ranks. An inverse relation between investor sentiment and uncertainty is also detected. We contribute to the existing literature by revealing potential features that affect the limits of arbitrage. Our results provide insights in designing arbitrage mechanisms and assist arbitrageurs in strategizing their operations with stocks under different magnitudes of uncertainty.

Uncovering interfirm links through textual topic similarity: A comomentum analysis in financial markets

Using an unsupervised topic modelling methodology, we construct a cross-firm similarity measure based on the various topics extracted from Management Discussion and Analysis texts. Our findings indicate that the returns of firms with similar textual topics predict the focal firms’ future stock returns. A long-short portfolio constructed on this basis yields an annualised alpha of 17.03%. Further analyses show that the return predictability is stronger for stocks subject to limited investor attention and limits to arbitrage. Additionally, our textual linkage measure can also predict future earnings surprises. Overall, mispricing due to sluggish information incorporation acts as a potential explanation for return predictability.

A model for optimizing an investment portfolio in modern conditions

Subject. This article discusses the issues of improving the methodology for optimizing an investment portfolio in modern conditions. Objectives. The article aims to develop a model for optimizing the investment portfolio, taking into account the investor's risk profile and the limited budget. Methods. For the study, I used a comparative analysis, mathematical modeling in economics, machine learning methods, genetic algorithms, and the Python programming language. Results. The article presents the author-developed model of optimizing the investment portfolio of an enterprise, based on the symbiosis of individual elements and principles of the most effective methods of optimizing the investment portfolio, algorithms for their implementation, mathematical model and practical recommendations. Conclusions and Relevance. The combination of classical methods of investment portfolio optimization and machine learning in the model helps improve the accuracy of assessing the future return of assets and determine their weights in the investor's portfolio. The theoretical significance of the work lies in the fact that the scientific provisions that actualize the task of improving existing or developing new approaches to optimizing the investment portfolio are proved. The practical significance of the study lies in the fact that the presented model is of an applied nature, taking into account the risk profile of the investor, tactical and strategic goals of investment, and budget constraints. The results of the study may be of interest to novice stock market participants, experienced investors, IT specialists engaged in the creation of programs and robots for trading on the stock market using machine learning tools.

TESTING MEAN REVERSION OF STOCK PRICES IN OECD COUNTRIES: EVIDENCE FROM FOURIER THRESHOLD UNIT ROOT TEST

Researchers focus on whether stock prices have a unit root, that is, whether they contain a random walk process. If stock prices have a stationary process, that is, if they return to the mean, the effects of shocks are temporary, and it is interpreted that they will return to the trend path over time. If stock prices have transitory shocks, it allows for the prediction of future movements based on past behavior in terms of investment. This study investigates whether stock prices revert to the mean and thus have a random walk process. For this purpose, the Fourier Threshold Unit Root (FTUR) test based on the test methodology of Caner and Hansen (2001) for the period January 1990–January 2021 for 26 OECD countries is applied. The FTUR test takes into account both structural breaks and nonlinearities. The purpose of using Fourier functions to account for structural changes is that they are not affected by the number, location, or shape of breaks. Thus, the power of the test increases. According to the results of this test, stock prices in Austria, Canada, Germany, Italy, New Zealand, Spain, and the UK are linear. Therefore, Fourier Augmented Dickey-Fuller (FADF) unit root analysis was performed for these countries. The FTUR test was performed in other countries. According to the results of FTUR and FADF unit root tests, stock prices are found to contain unit roots in some countries except Italy. In some countries, stock prices have a partial unit root structure. In other words, the effects of shocks are permanent, and it is concluded that future returns cannot be predicted in these countries with the random walk process.

Spending on Intangibles and The Growth of Public Sector Enterprises In India: A Measure-Specific DEA Analysis

A recent surge of intangible investment to navigatethe productive capability of Central Public Sector Enterprises (CPSEs) resurrected a range of doubt about the trajectory of choices and the actual managerial space that actualizes these choices. Though spending on intangibles and more particularly on R&D contribute substantially to growth parameters but the ambiguous magnitude of spending patterns and treatment of such expenditure from regular business operation to an investment element, in particular, to enhance the valued capability, yet unresolved in the corporate world. Recent studies on the usefulness of intangibleoutlay and capitalization of the same in improving future returns evidenced a gloomy pattern of crisis in the measurement and allocation of intangibles. As evidenced, most of the spending on intangibles by the business units in India is targeted to secure “patent for profit” rather than to achieve “valued capability” to expand real opportunities to choose between alternatives. Based on the last ten years' dataset of Maharatna Enterprises this study critically examines the contribution of decisive one from the container of four inputs namely spending on software, other R&D expenditure, materials, and employee costs on a set of productive activities covering the revenue and net- value- added, as these are more regular in enhancing both profit and production capability with the help of input-oriented VRS weighted measure-specific DEA model. Results show that the multidimensional performances between the enterprises are not uniform throughout the study period and that the efficiency is highly correlated with the size of a few companies like ONGC, BHEL, and GALE and higher spending DMUs on intangibles do not necessarily have higher-ranked performance in terms of returns and net value added. This study provides valuable insights for managers aiming to maximize the benefit of variety in Software and other R&D spending patterns considering the sizes of the companies while minimizing the risk associated with excessive diversity beyond the moderate threshold in intangible investments.

The Role Of The Green Economy, Technological Innovation, Stock Market Advantages In Sustainable Development

A green economy to achieve sustainable development provides technological innovation and stock market profits in a sustainable social and environmental economy. To accelerate the transition to an environmentally friendly economy, companies need to understand the impact of implementing environmentally friendly policies and activities on the economy. Results show that green economic growth policies produce future aggregate stock market returns are lower, consistent with the perceived reduction in risk argument by investors. As this research increases our understanding of how the transition to a more sustainable green economy can impact the aggregate profitability of financial markets, implementing a green economy is important to implement appropriate measures to support it sensitively without incurring large costs that adversely impact the health of the economy. Increasing the driving force of technological innovation is the need to comply with environmentally friendly transformation in the economy and realize high-quality economic growth in technological innovation that does not provide support for green economic growth, but over time the impact of technological innovation on economic growth will change to positive. This shows that increasing the ability of technological innovation to encourage environmentally friendly economic efficiency.

Equilibrium bifurcation and extreme risk in the EU carbon futures market

Considering the long-term memory and volatility clustering of the European Union (EU) Carbon Emission Allowances (EUA) futures returns, based on the economy–energy–environment system perspective and the assumption of investors' heterogeneity, this study proposes a joint modeling approach combining the fractionally integrated generalized autoregressive conditional heteroscedasticity model (FIGARCH) and the stochastic cusp catastrophe model (SCC) to examine the equilibrium bifurcations and extreme risks in the EU carbon futures market. The relevant results are threefold. (1) The SCC model has good fitting effect and interpretability, and is an effective method for investigating catastrophe reactions under time-varying volatility conditions. (2) In the EUA futures market, chartists are mainly affected by short-term price and trading volume changes, which leads to the emergence of equilibrium bifurcations, while fundamentalists make investment decisions based on the economy, the energy market, and market supply–demand, which affects the asymmetry of equilibrium bifurcations. (3) Using the catastrophe criterion (i.e., Cardan's discriminant of the equilibrium surface equation), we identify148 equilibrium bifurcation time points in the EUA futures market from December 3, 2009 to September 16, 2020, most of which are concentrated in two upward periods with an average scale of extreme risks is about 32.51 %. Our analysis provides theoretical support for regulatory authorities to stabilize the carbon futures market and build a collaborative extreme risk management framework covering energy and macroeconomics, also proposing suggestions for traders to effectively prevent extreme risks.

The Korean Spotlight: The Effect of Culture on Stock Returns Through Investor Attention*

AbstractThis study empirically examines the relationship between “investor attention” and aggregate stock returns, seeking to determine whether interest in South Korea can predict the returns of the Korean stock market. The results confirm a positive relationship between interest in Korea and future stock market returns. Furthermore, this relationship is observed to have emerged with the widespread dissemination of Korean culture starting in 2017. This impact is found to be more significant on the KOSDAQ market compared to the KOSPI market. Within the KOSPI market, the influence of interest on stock returns is particularly pronounced in the case of small‐cap stocks. It is also observed that since 2017, as interest in South Korea has increased, information related to the improvement of Korea's corruption index has begun to significantly affect stock returns.

Trade co-occurrence, trade flow decomposition and conditional order imbalance in equity markets

The time proximity of high-frequency trades can contain a salient signal. In this paper, we propose a method to classify every trade, based on its proximity with other trades in the market within a short period of time, into five types. By means of a suitably defined normalized order imbalance associated to each type of trade, which we denote as conditional order imbalance (COI), we investigate the price impact of the decomposed trade flows. Our empirical findings indicate strong positive correlations between contemporaneous returns and COIs. In terms of predictability, we document that associations with future returns are positive for COIs of trades which are isolated from trades of stocks other than themselves, and negative otherwise. Furthermore, trading strategies which we develop using COIs achieve conspicuous returns and Sharpe ratios, in an extensive experimental setup on a universe of 457 stocks using daily data for a period of 4 years.