nep-fmk New Economics Papers
on Financial Markets
Issue of 2023‒05‒01
eleven papers chosen by

  1. Behavioral Machine Learning? Computer Predictions of Corporate Earnings also Overreact By Murray Z. Frank; Jing Gao; Keer Yang
  2. Complexity in Factor Pricing Models By Antoine Didisheim; Shikun Ke; Bryan T. Kelly; Semyon Malamud
  3. Mean-variance hybrid portfolio optimization with quantile-based risk measure By Jianjun Gao; Yu Lin; Weiping Wu; Ke Zhou
  4. Election-Day Market Reactions to Tax Proposals: Evidence from a Close Vote By Masanori Orihara
  5. Interbank asset-liability networks with fire sale management By Feinstein, Zachary; Hałaj, Grzegorz
  6. Does ESG Affect The Firm Value? By Agustin Palupi
  7. Reverse Mortgages and Financial Literacy By Ismael Choinière-Crèvecoeur; Pierre-Carl Michaud
  8. An Intangibles-Adjusted Profitability Factor By Ravi Jagannathan; Robert Korajczyk; Kai Wang
  9. NFT Bubbles By Andrea Barbon; Angelo Ranaldo
  10. The Wall Street Neophyte: A Zero-Shot Analysis of ChatGPT Over MultiModal Stock Movement Prediction Challenges By Qianqian Xie; Weiguang Han; Yanzhao Lai; Min Peng; Jimin Huang
  11. The Green Innovation Premium: Evidence from U.S. Patents and the Stock Market By Markus Leippold; Tingyu Yu

  1. By: Murray Z. Frank; Jing Gao; Keer Yang
    Abstract: There is considerable evidence that machine learning algorithms have better predictive abilities than humans in various financial settings. But, the literature has not tested whether these algorithmic predictions are more rational than human predictions. We study the predictions of corporate earnings from several algorithms, notably linear regressions and a popular algorithm called Gradient Boosted Regression Trees (GBRT). On average, GBRT outperformed both linear regressions and human stock analysts, but it still overreacted to news and did not satisfy rational expectation as normally defined. By reducing the learning rate, the magnitude of overreaction can be minimized, but it comes with the cost of poorer out-of-sample prediction accuracy. Human stock analysts who have been trained in machine learning methods overreact less than traditionally trained analysts. Additionally, stock analyst predictions reflect information not otherwise available to machine algorithms.
    Date: 2023–03
  2. By: Antoine Didisheim (Swiss Finance Institute, UNIL); Shikun Ke (Yale School of Management); Bryan T. Kelly (Yale SOM; AQR Capital Management, LLC; National Bureau of Economic Research (NBER)); Semyon Malamud (Ecole Polytechnique Federale de Lausanne; Centre for Economic Policy Research (CEPR); Swiss Finance Institute)
    Abstract: We theoretically characterize the behavior of machine learning asset pricing models. We prove that expected out-of-sample model performance—in terms of SDF Sharpe ratio and average pricing errors—is improving in model parameterization (or “complexity”). Our results predict that the best asset pricing models (in terms of expected out-of-sample performance) have an extremely large number of factors (more than the number of training observations or base assets). Our empirical findings verify the theoretically predicted “virtue of complexity” in the cross-section of stock returns and find that the best model combines tens of thousands of factors. We also derive the feasible Hansen- Jagannathan (HJ) bound: The maximal Sharpe ratio achievable by a feasible portfolio strategy. The infeasible HJ bound massively overstates the achievable maximal Sharpe ratio due to a complexity wedge that we characterize.
    Keywords: Portfolio choice, asset pricing tests, optimization, expected returns, predictability
    JEL: C3 C58 C61 G11 G12 G14
    Date: 2023–03
  3. By: Jianjun Gao; Yu Lin; Weiping Wu; Ke Zhou
    Abstract: This paper addresses the importance of incorporating various risk measures in portfolio management and proposes a dynamic hybrid portfolio optimization model that combines the spectral risk measure and the Value-at-Risk in the mean-variance formulation. By utilizing the quantile optimization technique and martingale representation, we offer a solution framework for these issues and also develop a closed-form portfolio policy when all market parameters are deterministic. Our hybrid model outperforms the classical continuous-time mean-variance portfolio policy by allocating a higher position of the risky asset in favorable market states and a less risky asset in unfavorable market states. This desirable property leads to promising numerical experiment results, including improved Sortino ratio and reduced downside risk compared to the benchmark models.
    Date: 2023–03
  4. By: Masanori Orihara (Department of Policy and Planning Sciences, Faculty of Engineering, Information and Systems, University of Tsukuba)
    Abstract: We ask whether the stock market immediately reacts to the underlying will of political leaders to tax shareholders from the moment of their election, much earlier than previously documented. Our natural laboratory is the surprising outcome of the September 2021 Japanese Prime Ministerial election: whereby the winning candidate secured a narrow victory of just one vote and thus promoted a second “runoff” election. The eventual election victor—Fumio Kishida—proposed increasing taxes on shareholders, leading to a market drop referred to as “Kishida Shock” by news outlets such as the Financial Times and The Wall Street Journal. Using an event study approach, we find firms that were vulnerable to a potential tax increase, such as dividend payers, experienced lower stock returns. As predicted by financial constraints theory, smaller firms with more cash holdings could lessen their losses. Likewise, larger firms could reduce the severity of their negative stock returns via bond market access. As a direct target of the potential tax increase, it appears that domestic individual investors sold their highdividend yield stocks while foreign investors in fact purchased shares of the same.
    Keywords: Taxation, Election, Financing, Ownership Structure, Dividend, Japan
    JEL: G32 G35 G38 H24 H25
    Date: 2023–03
  5. By: Feinstein, Zachary; Hałaj, Grzegorz
    Abstract: Interconnectedness is an inherent feature of the modern financial system. While it con-tributes to efficiency of financial services, it also creates structural vulnerabilities: pernicious shock transmission and amplification impacting banks’ capitalization. This has recently been seen during the Global Financial Crisis. Post-crisis reforms addressed many of the causes of this event, but contagion effects may not be fully eliminated. One reason for this may be related to financial institutions’ incentives and strategic behaviours. We propose a model to study contagion effects in a banking system capturing network effects of direct exposures and indirect effects of market behaviour that may impact asset valuation. By doing so, we can embed a well-established fire-sale channel into our model. Unlike in related literature, we relax the assumption that there is an exogenous pecking order of how banks would sell their assets. Instead, banks act rationally in our model; they optimally construct a portfolio subject to budget constraints so as to raise cash to satisfy creditors (interbank and external). We assume that the guiding principle for banks is to maximize risk-adjusted returns gener-ated by their balance sheets. We parameterize the theoretical model with publicly available data for a representative sample of European banks; this allows us to run simulations of bank valuations and asset prices under a set of stress scenarios. JEL Classification: C62, C63, G11, G21
    Keywords: fire sales, interbank contagion, optimal portfolio, systemic risk
    Date: 2023–04
  6. By: Agustin Palupi (Trisakti School of Management, Jl. Kyai Tapa No.20, Tomang, Kec. Grogol petamburan, 11440, Jakarta, Indonesia Author-2-Name: Author-2-Workplace-Name: Author-3-Name: Author-3-Workplace-Name: Author-4-Name: Author-4-Workplace-Name: Author-5-Name: Author-5-Workplace-Name: Author-6-Name: Author-6-Workplace-Name: Author-7-Name: Author-7-Workplace-Name: Author-8-Name: Author-8-Workplace-Name:)
    Abstract: " Objective - As the concept of sustainability develops in the industrial world, stakeholders are compelled to consider ESG performance when measuring company value. A company needs to increase its value and demonstrate its sustainability capabilities by publishing sustainability reports on ESG factors. This research aims to inquire whether ESG affects the firm's value. Methodology/Technique - The causality research is analyzed with Eviews using ASEAN panel data from 2019-2021 to measure the effect of ESG on firm value with a total of 738 firm years of data. Findings - Environmental performance is associated with high ecological costs in developing nations and is a burdensome additional expense that will deteriorate the company's financial condition. Disclosure of nonfinancial information jeopardizes the creation of company value, resulting from meeting the demands of stakeholders imposed on the company, thereby causing other agency conflicts. The relatively low level of investor confidence in the signal contributes to ESG performance that lowers the company's market value. Most investors respond negatively to these signals, assuming that the activities disclosed in ESG reporting are too costly and detrimental to their interests. They could be more enthralling in investing, decreasing market demand, and reducing the company's value. Novelty - This study explains the determinants of firm value from ESG scores and separate ESG scores in the ASEAN market. Type of Paper - Empirical."
    Keywords: ESG, Firm value, Environment score, Social score, Governance score, Sustainability
    JEL: F64 L50 Q25 G02 G39 M14
    Date: 2023–03–31
  7. By: Ismael Choinière-Crèvecoeur; Pierre-Carl Michaud
    Abstract: Few retirees use reverse mortgages. In this paper, we investigate how financial literacy and prior knowledge of the product influence take-up by conducting a stated-preference experiment. We exogenously manipulate characteristics of reverse mortgages to tease out how consumers value them and investigate differences by financial literacy and prior knowledge of reverse mortgages. We find that those with higher financial knowledge are more likely to know about reverse mortgages, not more likely to purchase them at any cost but are more sensitive to the interest rate and the insurance value of these products in terms of the non-negative equity guarantee. Peu de retraités ont recours aux prêts hypothécaires inversés. Dans cet article, nous étudions l'influence de la littératie financière et de la connaissance préalable du produit sur son utilisation en menant une expérience de préférences déclarées. Nous manipulons de manière exogène les caractéristiques des prêts hypothécaires inversés afin de déterminer la valeur que leur accordent les consommateurs et d'étudier les différences en fonction de la littératie financière et de la connaissance préalable des prêts hypothécaires inversés. Nous constatons que les personnes ayant de meilleures connaissances financières sont plus susceptibles de connaître les prêts hypothécaires inversés; qu'elles ne sont pas plus susceptibles de les acheter à tout prix; mais qu'elles sont plus sensibles au taux d'intérêt et à la valeur d'assurance de ces produits en termes de garantie de valeur nette réelle non négative.
    Keywords: reverse mortgages, savings, retirement planning, insurance, hypothèques inversées, épargne, planification de la retraite, assurance
    JEL: G53 G21 R21
    Date: 2023–02–01
  8. By: Ravi Jagannathan; Robert Korajczyk; Kai Wang
    Abstract: We treat expenditures that create intangible assets as investments and instead of expensing them, we add them back to earnings when measuring the return on equity of firms while constructing the profitability factor in the Fama and French (2015) five factor model. The profitability factor we construct has significant alpha relative to many extant multi-factor asset-pricing models, including the standard Fama-French five factor model. When the profitability factor in the Fama and French (2015) five factor model is replaced with our intangibles adjusted profitability factor, the model performs better in explaining the cross section of stock returns, and several anomalies documented in the literature. Portfolios that exploit price momentum, earnings momentum, and operating leverage no longer have significant alphas. The improvement is consistent with the dividend discount model for equity valuation. Adjusted earnings constructed by treating expenditures that create intangible assets as investments help forecast the cross section of future cash dividends and operating cash flows on stocks better, especially at longer horizons. Adopting our adjustment when constructing the monthly rebalanced profitability factor in the Hou et al. (2015) four factor model improves its performance as well. Our intangible adjusted profitability factor has smaller left tail risk and co-tail risk with the market when compared to the standard profitability factor.
    JEL: G0 G1 G12
    Date: 2023–03
  9. By: Andrea Barbon (University of St. Gallen; Swiss Finance Institute); Angelo Ranaldo (University of St. Gallen; Swiss Finance Institute)
    Abstract: By investigating nonfungible tokens (NFTs), we provide the first systematic study of retail investor behavior through asset bubbles. Given that NFTs are recorded in public blockchains, we are able to track investor behavior over time, leading to the identification of numerous price run-ups and crashes. Our study reveals that agent-level variables, such as investor sophistication, heterogeneity, and wash trading, in addition to aggregate variables, such as volatility, price acceleration, and turnover, significantly predict bubble formation and price crashes. We find that sophisticated investors consistently outperform others and exhibit characteristics consistent with superior information and skills, supporting the narrative surrounding asset pricing bubbles.
    Keywords: Financial Bubbles, Nonfungible Tokens, Agent-level, Blockchain
    JEL: G14 G12
    Date: 2023–03
  10. By: Qianqian Xie; Weiguang Han; Yanzhao Lai; Min Peng; Jimin Huang
    Abstract: Recently, large language models (LLMs) like ChatGPT have demonstrated remarkable performance across a variety of natural language processing tasks. However, their effectiveness in the financial domain, specifically in predicting stock market movements, remains to be explored. In this paper, we conduct an extensive zero-shot analysis of ChatGPT's capabilities in multimodal stock movement prediction, on three tweets and historical stock price datasets. Our findings indicate that ChatGPT is a "Wall Street Neophyte" with limited success in predicting stock movements, as it underperforms not only state-of-the-art methods but also traditional methods like linear regression using price features. Despite the potential of Chain-of-Thought prompting strategies and the inclusion of tweets, ChatGPT's performance remains subpar. Furthermore, we observe limitations in its explainability and stability, suggesting the need for more specialized training or fine-tuning. This research provides insights into ChatGPT's capabilities and serves as a foundation for future work aimed at improving financial market analysis and prediction by leveraging social media sentiment and historical stock data.
    Date: 2023–04
  11. By: Markus Leippold (University of Zurich; Swiss Finance Institute); Tingyu Yu (University of Zurich)
    Abstract: This paper investigates if firms’ green innovation efforts are reflected in their stock market prices. Firms with a higher proportion of green patents experience lower stock returns than those with a lower percentage. A long-short portfolio based on green patent shares has an average annual return of 8%, which remains significant when we control for common risk factors. However, firms with high green patent shares outperform their counterparts after events that increase climate concerns and strengthen environmental regulations. Moreover, firms with green innovation attract more institutional ownership and can weakly decrease their future carbon intensity and incident involvement.
    Keywords: Green patents, cross-section of stock returns, event study, institutional investors
    JEL: G12 G14 O34 Q55
    Date: 2023–03

General information on the NEP project can be found at For comments please write to the director of NEP, Marco Novarese at <>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.