|
on Financial Markets |
|
Issue of 2024‒02‒05
ten papers chosen by |
| By: | Vamsi K. Potluru; Daniel Borrajo; Andrea Coletta; Niccol\`o Dalmasso; Yousef El-Laham; Elizabeth Fons; Mohsen Ghassemi; Sriram Gopalakrishnan; Vikesh Gosai; Eleonora Krea\v{c}i\'c; Ganapathy Mani; Saheed Obitayo; Deepak Paramanand; Natraj Raman; Mikhail Solonin; Srijan Sood; Svitlana Vyetrenko; Haibei Zhu; Manuela Veloso; Tucker Balch |
| Abstract: | Synthetic data has made tremendous strides in various commercial settings including finance, healthcare, and virtual reality. We present a broad overview of prototypical applications of synthetic data in the financial sector and in particular provide richer details for a few select ones. These cover a wide variety of data modalities including tabular, time-series, event-series, and unstructured arising from both markets and retail financial applications. Since finance is a highly regulated industry, synthetic data is a potential approach for dealing with issues related to privacy, fairness, and explainability. Various metrics are utilized in evaluating the quality and effectiveness of our approaches in these applications. We conclude with open directions in synthetic data in the context of the financial domain. |
| Date: | 2023–12 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2401.00081&r=fmk |
| By: | Vahidin Jeleskovic; Claudio Latini; Zahid I. Younas; Mamdouh A. S. Al-Faryan |
| Abstract: | The growing interest in cryptocurrencies has drawn the attention of the financial world to this innovative medium of exchange. This study aims to explore the impact of cryptocurrencies on portfolio performance. We conduct our analysis retrospectively, assessing the performance achieved within a specific time frame by three distinct portfolios: one consisting solely of equities, bonds, and commodities; another composed exclusively of cryptocurrencies; and a third, which combines both 'traditional' assets and the best-performing cryptocurrency from the second portfolio.To achieve this, we employ the classic variance-covariance approach, utilizing the GARCH-Copula and GARCH-Vine Copula methods to calculate the risk structure. The optimal asset weights within the optimized portfolios are determined through the Markowitz optimization problem. Our analysis predominantly reveals that the portfolio comprising both cryptocurrency and traditional assets exhibits a higher Sharpe ratio from a retrospective viewpoint and demonstrates more stable performances from a prospective perspective. We also provide an explanation for our choice of portfolio optimization based on the Markowitz approach rather than CVaR and ES. |
| Date: | 2023–12 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2401.00507&r=fmk |
| By: | Lin William Cong; Shiyang Huang; Douglas Xu |
| Abstract: | We model financial innovations such as Exchange-Traded Funds, smart beta products, and many index-based vehicles as composite securities (CSs) that facilitate trading the common factors in assets' liquidation values. Through accessing a larger basket of assets in endogenously chosen proportions, CSs reduce investors' duplication of effort in trading multiple securities and attract more factor investors. We characterize analytically how competitive CS designers in equilibrium optimally select liquid underlying assets representative of the factors and find corroborating evidence in ETF data. CS trading entails investors' strategic and active decisions, consequently impounding more systematic information into prices. Their rise creates leads to greater informational efficiency, price variability, and co-movements in the underlying asset markets, as well as potentially heterogeneous effects on liquidity and asset-specific information acquisition/incorporation, depending on the importance of factors for asset value. The predictions explain and reconcile the rich (and often mixed) empirical observations about various types of CSs in the extant literature. |
| JEL: | D40 D82 G11 G14 G23 |
| Date: | 2024–01 |
| URL: | http://d.repec.org/n?u=RePEc:nbr:nberwo:32016&r=fmk |
| By: | Jules H. van Binsbergen; Svetlana Bryzgalova; Mayukh Mukhopadhyay; Varun Sharma |
| Abstract: | Using text from 200 million pages of 13, 000 US local newspapers and machine learning methods, we construct a 170-year-long measure of economic sentiment at the country and state levels, that expands existing measures in both the time series (by more than a century) and the cross-section. Our measure predicts GDP (both nationally and locally), consumption, and employment growth, even after controlling for commonly-used predictors, as well as monetary policy decisions. Our measure is distinct from the information in expert forecasts and leads its consensus value. Interestingly, news coverage has become increasingly negative across all states in the past half-century. |
| JEL: | E2 E3 E4 E40 E43 E44 G01 G1 G10 G14 G17 G18 G40 |
| Date: | 2024–01 |
| URL: | http://d.repec.org/n?u=RePEc:nbr:nberwo:32026&r=fmk |
| By: | Georgios Fatouros; Konstantinos Metaxas; John Soldatos; Dimosthenis Kyriazis |
| Abstract: | In the dynamic and data-driven landscape of financial markets, this paper introduces MarketSenseAI, a novel AI-driven framework leveraging the advanced reasoning capabilities of GPT-4 for scalable stock selection. MarketSenseAI incorporates Chain of Thought and In-Context Learning methodologies to analyze a wide array of data sources, including market price dynamics, financial news, company fundamentals, and macroeconomic reports emulating the decision making process of prominent financial investment teams. The development, implementation, and empirical validation of MarketSenseAI are detailed, with a focus on its ability to provide actionable investment signals (buy, hold, sell) backed by cogent explanations. A notable aspect of this study is the use of GPT-4 not only as a predictive tool but also as an evaluator, revealing the significant impact of the AI-generated explanations on the reliability and acceptance of the suggested investment signals. In an extensive empirical evaluation with S&P 100 stocks, MarketSenseAI outperformed the benchmark index by 13%, achieving returns up to 40%, while maintaining a risk profile comparable to the market. These results demonstrate the efficacy of Large Language Models in complex financial decision-making and mark a significant advancement in the integration of AI into financial analysis and investment strategies. This research contributes to the financial AI field, presenting an innovative approach and underscoring the transformative potential of AI in revolutionizing traditional financial analysis investment methodologies. |
| Date: | 2024–01 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2401.03737&r=fmk |
| By: | Thiago Fauvrelle; Mathias Skrutkowski |
| Abstract: | This paper studies whether Eurosystem collateral eligibility played a role in the portfolio choices of euro area asset managers during the “dash-for-cash” episode of 2020. We find that asset managers reduced their allocation to ECB-eligible corporate bonds, selling them in order to finance redemptions, while simultaneously increasing their cash holdings. These findings add nuance to previous studies of liquidity strains and price dislocations in the corporate bond market during the onset of the Covid-19 pandemic, indicating a greater willingness of dealers to increase their inventories of corporate bonds pledgeable with the ECB. Analysing the price impact of these portfolio choices, we also find evidence pointing to price pressure for both ECB-eligible and ineligible corporate bonds. Bonds that were held to a larger extent by investment funds in our sample experienced higher price pressure, although the impact was lower for ECB-eligible bonds. We also discuss broader implications for the related policy debate about how central banks could mitigate similar types of liquidity shocks. |
| Keywords: | Investment funds, dash-for-cash, corporate bonds, Eurosystem collateral eligibility |
| JEL: | G11 G23 |
| Date: | 2023–12–12 |
| URL: | http://d.repec.org/n?u=RePEc:stm:wpaper:58&r=fmk |
| By: | Vahidin Jeleskovic; Stephen Mackay |
| Abstract: | Cryptocurrencies have emerged as a novel financial asset garnering significant attention in recent years. A defining characteristic of these digital currencies is their pronounced short-term market volatility, primarily influenced by widespread sentiment polarization, particularly on social media platforms such as Twitter. Recent research has underscored the correlation between sentiment expressed in various networks and the price dynamics of cryptocurrencies. This study delves into the 15-minute impact of informative tweets disseminated through foundation channels on trader behavior, with a focus on potential outcomes related to sentiment polarization. The primary objective is to identify factors that can predict positive price movements and potentially be leveraged through a trading algorithm. To accomplish this objective, we conduct a conditional examination of return and excess return rates within the 15 minutes following tweet publication. The empirical findings reveal statistically significant increases in return rates, particularly within the initial three minutes following tweet publication. Notably, adverse effects resulting from the messages were not observed. Surprisingly, sentiments were found to have no discerni-ble impact on cryptocurrency price movements. Our analysis further identifies that inves-tors are primarily influenced by the quality of tweet content, as reflected in the choice of words and tweet volume. While the basic trading algorithm presented in this study does yield some benefits within the 15-minute timeframe, these benefits are not statistically significant. Nevertheless, it serves as a foundational framework for potential enhance-ments and further investigations. |
| Date: | 2023–12 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2401.00603&r=fmk |
| By: | Dirk Broeders; Marleen de Jonge; David Rijsbergen |
| Abstract: | We document a positive and statistically significant carbon premium that investors demand for investing in bonds issued by high carbon-emitting firms in the euro area. Over the entire sample period, we estimate that doubling a firm’s Scope 1 and 2 emissions results in an average increase of 6.6 basis points in the spread on the firm’s issued bonds. In addition, we find that the carbon premium has increased since 2020 and the effect reached 13.9 basis points by early 2022. These results suggest that European companies with high levels of carbon emissions are experiencing progressively higher financing costs. Our research also reveals a distinctive carbon premium term structure, rising with longer maturities. Interestingly, over time the term structure flat tens, suggesting investors’ confident anticipation of ongoing carbon pricing in the European Union at a stable pace. |
| Keywords: | Carbon Premium; Carbon Premium Term Structure; Climate Change; Climate Transition Risk |
| JEL: | G12 G15 G23 Q51 Q54 |
| Date: | 2024–01 |
| URL: | http://d.repec.org/n?u=RePEc:dnb:dnbwpp:798&r=fmk |
| By: | Martijn A. Boermans; Maurice Bun; Yasmine van der Straten |
| Abstract: | We study whether climate transition risk is priced in corporate bond markets. We assess whether corporate bond investors value companies’ efforts to mitigate climate change by innovating in the green space. By combining global firm-level data on greenhouse emissions and green patents with bond-level holdings data, we provide evidence of a positive transition risk premium, which is significantly lower for emission intensive companies that engage in green innovation. The joint effect of emission intensity and green innovation on bond yield spreads is driven by European investors, specifically institutional investors. Overall, our results indicate that investors care about whether companies are ‘fit’ for the green transition. |
| Keywords: | Climate Change; Climate Transition Risk; Carbon Premium; Greenium; Green Innovation; Green Patents; Institutional Investors; Institutional Ownership |
| JEL: | G12 G15 G23 Q51 Q54 |
| Date: | 2024–01 |
| URL: | http://d.repec.org/n?u=RePEc:dnb:dnbwpp:797&r=fmk |
| By: | KEIDA Masayuki; TAKEDA Yosuke |
| Abstract: | Environmental, social, and governance (ESG) investing in equity markets has surged for corporate firms, whose managerial efforts are disclosed and evaluated in favor of environmental, social, or governance-oriented issues. Since managerial information is costly for individual investors to acquire and process, “exit or voice†activities of speculators through market monitoring is necessary to reduce uncertainty associated with firms’ managerial performance (Holmstrӧm and Tirole, 1993; Tirole, 2006). This study examines Japan’s Government Pension Investment Fund (GPIF), which announced that it selected some ESG indices for Japanese equities and commenced passive investment tracking them. We estimate the effects of several announcements made by GPIF on the equity prices of the monitored firms, empirically showing the effects of informational efficiency in market monitoring on share prices in a case of positive screening through GPIF’s choice over the ESG indices based on public information. The panel regressions indicate that the GPIF’s soft voice influencing the corporations’ pro-ESG managerial efforts was loud enough to cause temporary increases in stock prices. However, the transient effects of the GPIF’s market monitoring are contradictory in that the effects are absent for the corporations whose sustainability reports reveal information on their positive ESG-related performances. Our finding that the ESG ratings accurately reflect the content of sustainability reports is supportive of the GPIF’s objectives of positive screening based on public information in choosing the ESG indices. |
| Date: | 2024–01 |
| URL: | http://d.repec.org/n?u=RePEc:eti:dpaper:24002&r=fmk |