Journal of Finance and Data Science最新文献

This paper introduces the minCluster portfolio, which is a portfolio optimization method combining the optimization of downside risk measures, hierarchical clustering and cellwise robustness. Using cellwise robust association measures, the minCluster portfolio is able to retrieve the underlying hierarchical structure in the data. Furthermore, it provides downside protection by using tail risk measures for portfolio optimization. We show through simulation studies and a real data example that the minCluster portfolio produces better out-of-sample results than mean-variances or other hierarchical clustering based approaches. Cellwise outlier robustness makes the minCluster method particularly suitable for stable optimization of portfolios in highly volatile markets, such as portfolios containing cryptocurrencies.

China's markets gained 3.86% around December 4, 2012, when the Party announced anti-corruption reforms. State-owned enterprises (SOEs) with higher past entertainment and travel costs (ETC) gained more. NonSOEs gained in more liberalized provinces, especially those with high past ETC, productivity, growth opportunities, and external financing. NonSOEs lost in the least liberalized provinces, especially those with high past ETC. These findings support investors' expect reduced official corruption to create value overall, reduce SOE waste, lower bureaucratic barriers to efficient resource allocation where markets function, and impede business in unliberalized provinces, where “getting things done” still requires investment in greasing bureaucratic gears.

The paper aims to indentify and compare the determinants of the overall FinTech market expansion and its major segments – cryptocurrency and peer-to-peer lending markets – in a dataset, which covers 64 countries and 51 potentially relevant factors. To this end, we apply a battery of state-of-the-art variable selection techniques from machine learning, comprising Bayesian model averaging (BMA), least absolute shrinkage and selection operator (LASSO), variable selection using random forests (VSURF) as well as spike-and-slab regression. We document substantial heterogeneity of the pivotal determinants across the FinTech market as a whole and its major segments. Thus, specific rather than general policy measures are needed to foster the development of standalone FinTech market segments. Moreover, our findings suggest that most countries don't need to seek a universal specialization in FinTech activities, concentrating on the segment where they have a competitive edge in terms of the pivotal determinants which drive its expansion.

We use supervised learning to identify factors that predict the cross-section of returns and maximum drawdown for stocks in the US equity market. Our data run from January 1970 to December 2019 and our analysis includes ordinary least squares, penalized linear regressions, tree-based models, and neural networks. We find that the most important predictors tended to be consistent across models, and that non-linear models had better predictive power than linear models. Predictive power was higher in calm periods than in stressed periods. Environmental, social, and governance indicators marginally impacted the predictive power of non-linear models in our data, despite their negative correlation with maximum drawdown and positive correlation with returns. Upon exploring whether ESG variables are captured by some models, we find that ESG data contribute to the prediction nonetheless.

Climate change and sustainability have become societal focal points in the last decade. Consequently, companies have been increasingly characterized by non-financial information, such as environmental, social, and governance (ESG) scores, based on which companies can be grouped into ESG classes. While many scholars have questioned the relationship between financial performance and risks of assets belonging to different ESG classes, the question about dependence among ESG classes is still open. Here, we focus on understanding the dependence structures of different ESG class indices and the market index through the lens of copula models. After a thorough introduction to vine copula models, we explain how cross-sectional and temporal dependencies can be captured by models based on vine copulas, more specifically, using ARMA-GARCH and stationary vine copula models. Using real-world ESG data over a long period with different economic states, we find that assets with medium ESG scores tend to show weaker dependence to the market, while assets with extremely high or low ESG scores tend to show stronger, non-Gaussian dependence.

In this paper, we document the importance of memory in machine learning (ML)-based models relying on firm characteristics for asset pricing. We find that predictive algorithms perform best when they are trained on long samples, with long-term returns as dependent variables. In addition, we report that persistent features play a prominent role in these models. When applied to portfolio choice, we find that investors are always better off predicting annual returns, even when rebalancing at lower frequencies (monthly or quarterly). Our results remain robust to transaction costs and risk scaling, thus providing useful indications to quantitative asset managers.

This paper reviews research that uses big data and/or machine learning methods to provide insight relevant for equity valuation. Given the huge volume of research in this area, the review focuses on studies that either use or inform on accounting variables. The article concludes by providing recommendations for future research and practice.

We selectively review recent advancements in research on predictive models of earnings and returns. We discuss why applying statistical, econometric, and machine learning advancements to forecasting earnings and returns presents difficult challenges. In the context of these challenges, we discuss recent papers that confront the challenges and present promising advancements and paths for future research.

Credit risk is the most significant risk by impact for any bank and financial institution. Accurate credit risk assessment affects an organisation's balance sheet and income statement, since credit risk strategy determines pricing, and might even influence seemingly unrelated domains, e.g. marketing, and decision-making. This article aims at providing a systemic review of the most recent (2016–2021) articles, identifying trends in credit scoring using a fixed set of questions. The survey methodology and questionnaire align with previous similar research that analyses articles on credit scoring published in 1991–2015. We seek to compare our results with previous periods and highlight some of the recent best practices in the field that might be useful for future researchers.