|
on Financial Markets |
| By: | Antonio Gil de Rubio Cruz; Steven A. Sharpe |
| Abstract: | This study scrutinizes the quality of “bottom-up” forecasts of near-term S&P 500 Composite earnings, derived by aggregating analysts’ forecasts for individual firm-level earnings. We examine whether forecasts are broadly consistent with current macroeconomic conditions reflected in economists’ near-term outlook and other available data. To the contrary, we find that a simple macroeconomic model of aggregate S&P 500 earnings, coupled with GDP forecasts from the Blue Chip Survey and recent dollar exchange rate movements, can predict large and statistically significant errors in equity analysts’ bottom-up forecasts for S&P 500 earnings in the current quarter and the quarter ahead. This finding is robust to the requirement that our econometric model is calibrated using only data available at the time of forecast. Moreover, the discrepancy between the macro-model-based earnings forecasts and analysts’ forecasts has notable predictive power for 3-month-ahead returns on the S&P500 stock index. |
| Keywords: | Bottom-up Forecast; Earnings Forecasts; Equity Analyst Bias; Forecast Efficiency; Predicting Returns |
| JEL: | E44 G14 G40 G12 |
| Date: | 2024–07–11 |
| URL: | https://d.repec.org/n?u=RePEc:fip:fedgfe:2024-49 |
| By: | Natalia Roszyk; Robert \'Slepaczuk |
| Abstract: | Predicting the S&P 500 index volatility is crucial for investors and financial analysts as it helps assess market risk and make informed investment decisions. Volatility represents the level of uncertainty or risk related to the size of changes in a security's value, making it an essential indicator for financial planning. This study explores four methods to improve the accuracy of volatility forecasts for the S&P 500: the established GARCH model, known for capturing historical volatility patterns; an LSTM network that utilizes past volatility and log returns; a hybrid LSTM-GARCH model that combines the strengths of both approaches; and an advanced version of the hybrid model that also factors in the VIX index to gauge market sentiment. This analysis is based on a daily dataset that includes S&P 500 and VIX index data, covering the period from January 3, 2000, to December 21, 2023. Through rigorous testing and comparison, we found that machine learning approaches, particularly the hybrid LSTM models, significantly outperform the traditional GARCH model. Including the VIX index in the hybrid model further enhances its forecasting ability by incorporating real-time market sentiment. The results of this study offer valuable insights for achieving more accurate volatility predictions, enabling better risk management and strategic investment decisions in the volatile environment of the S&P 500. |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2407.16780 |
| By: | Tian Guo; Emmanuel Hauptmann |
| Abstract: | Large language models (LLMs) and their fine-tuning techniques have demonstrated superior performance in various language understanding and generation tasks. This paper explores fine-tuning LLMs for stock return forecasting with financial newsflow. In quantitative investing, return forecasting is fundamental for subsequent tasks like stock picking, portfolio optimization, etc. We formulate the model to include text representation and forecasting modules. We propose to compare the encoder-only and decoder-only LLMs, considering they generate text representations in distinct ways. The impact of these different representations on forecasting performance remains an open question. Meanwhile, we compare two simple methods of integrating LLMs' token-level representations into the forecasting module. The experiments on real news and investment universes reveal that: (1) aggregated representations from LLMs' token-level embeddings generally produce return predictions that enhance the performance of long-only and long-short portfolios; (2) in the relatively large investment universe, the decoder LLMs-based prediction model leads to stronger portfolios, whereas in the small universes, there are no consistent winners. Among the three LLMs studied (DeBERTa, Mistral, Llama), Mistral performs more robustly across different universes; (3) return predictions derived from LLMs' text representations are a strong signal for portfolio construction, outperforming conventional sentiment scores. |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2407.18103 |
| By: | Yuriy Gorodnichenko; Xiao Yin |
| Abstract: | We combine a customized survey and randomized controlled trial (RCT) to study the effect of higher-order beliefs on U.S. retail investors’ portfolio allocations. We find that investors’ higher-order beliefs about stock market returns are correlated with but distinct from their first-order beliefs. Furthermore, the differences between the two vary systematically according to investor characteristics. We use information treatments in the RCT to create exogenous differential variations in first- and higher-order beliefs. We find that an exogenous increase in first-order beliefs increases the portfolio share allocated to the stock market (risky assets), while an exogenous increase in higher-order beliefs reduces it. |
| JEL: | C83 D84 G11 G12 G51 |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:nbr:nberwo:32680 |
| By: | Yacine Aït-Sahalia; Chen Xu Li; Chenxu Li |
| Abstract: | This paper relates jumps in high frequency stock prices to firm-level, industry and macroeconomic news, in the form of machine-readable releases from Thomson Reuters News Analytics. We find that most relevant news, both idiosyncratic and systematic, lead quickly to price jumps, as market efficiency suggests they should. However, in the reverse direction, the vast majority of price jumps do not have identifiable public news that can explain them, in a departure from the ideal of a fair, orderly and efficient market. Microstructure-driven variables have only limited predictive power to help distinguish between jumps with and without news. |
| JEL: | G12 G14 |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:nbr:nberwo:32746 |
| By: | Hélène Rey; Adrien Rousset Planat; Vania Stavrakeva; Jenny Tang |
| Abstract: | We introduce a novel empirical decomposition of equity price growth rates in terms of equity holdings, based on market-clearing conditions. Although our sample holdings cover only an average of 5% of market capitalization, our reconstructed equity holdings account for, on average, 89% of the time variation in over 20, 000 individual stock prices and 96% of the fluctuations in 33 aggregate stock markets. Using this decomposition, we introduce new stylized facts to inform asset pricing models. We find that changes in portfolio weights explain most of the variation of individual stock prices, while aggregate wealth effects are more important for the overall stock market fluctuations. Equity markets are global and exchange rates play a key equilibrating role. They dampen local stock market volatility for all stock markets, except those associated with the three safe-haven currencies---USD, JPY, and CHF---and currencies pegged to the USD. |
| JEL: | F30 G11 G23 |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:nbr:nberwo:32756 |
| By: | David Bowman; Yesol Huh; Sebastian Infante |
| Abstract: | In this paper, we provide a comprehensive investigation of the potential for expanded central clearing to reduce the costs of the supplementary leverage ratio (SLR) on Treasury market intermediation in both cash and repo markets. Combining a detailed analysis of the rules involved in calculating the SLR with a unique set of regulatory data, we conclude that expanding central clearing would have relatively limited effects on the level of SLRs. We do find intermediaries’ increase their balance sheet netting when their regulatory balance sheet costs are higher. Our data permits us to establish a number of empirical facts related to the noncentrally cleared bilateral (NCCB) repo segment, and to repo activity overall, at the bank holding company level. We find that sizeable amounts of bilaterally-cleared activity would not be nettable even if centrally cleared. We also find that a significant portion of activity is already nettable outside of central clearing because dealers are structuring their NCCB trades to net. While expanded central clearing could have other benefits, such as imposing a more uniform margin regime on Treasury market intermediation, the scope of its effects on reducing balance sheet costs associated with the leverage ratio is limited. |
| Keywords: | Treasury securities; Supplementary leverage ratio; Central clearing; Netting |
| JEL: | G21 G28 |
| Date: | 2024–07–18 |
| URL: | https://d.repec.org/n?u=RePEc:fip:fedgfe:2024-57 |
| By: | An Pham Ngoc Nguyen; Thomas Conlon; Martin Crane; Marija Bezbradica |
| Abstract: | Herding behavior has become a familiar phenomenon to investors, carrying the potential danger of both undervaluing and overvaluing assets, while also threatening market stability. This study contributes to the literature on herding behavior by using a more recent dataset to cover the most impactful events of recent years. To our knowledge, this is the first study examining herding behavior across three different types of investment vehicle. Furthermore, this is also the first study observing herding at a community (subset) level. Specifically, we first explore this phenomenon in each separate type of investment vehicle, namely stocks, US ETFs and cryptocurrencies, using the widely recognized Cross Sectional Absolute Deviation (CSAD) model. We find similar herding patterns between stocks and US ETFs, while these traditional assets reveal a distinction from cryptocurrencies. Subsequently, the same experiment is implemented on a combination of all three investment vehicle types. For a deeper investigation, we adopt graph-based techniques such as Minimum Spanning Tree (MST) and Louvain community detection to partition the given combination into smaller subsets whose assets are most similar to each other, then seek to detect the herding behavior on each subset. We find that herding behavior exists at all times across all types of investment vehicle at a subset level, although the herding might not manifest at the superset level. Additionally, this herding behavior tends to stem from specific events that solely impact that subset of assets. Given these findings, investors can construct an appropriate investment strategy composed of their choice of investment vehicles they are interested in. |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2407.08069 |
| By: | Ingomar Krohn; Mariel Maguiña |
| Abstract: | Global currency risk factors continue to explain a large share of the variation in the Canadian dollar during the period following the 2008–09 global financial crisis. We show that they are also systematically important for risk premiums, and only in recent months has the role of idiosyncratic country-specific risks grown. |
| Keywords: | Asset pricing; Exchange rates; International financial markets |
| JEL: | F3 F31 G1 G12 |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:bca:bocsan:24-20 |
| By: | Guglielmo Maria Caporale; Luis Alberiko Gil-Alana; Sakiru A. Solarin; OlaOluwa S. Yaya |
| Abstract: | This study examines the stochastic properties of German green and brown stock prices; more specifically, fractional integration methods are applied to daily data on representative green and brown stock indices for the Berlin, Dusseldorf, Frankfurt, Gettex, Munich, and Stuttgart stock exchanges over the period from 13 May 2019 to 8 May 2024. The results indicate a higher degree of persistence in the case of green stock prices vis-à-vis brown ones, although the differences are not statistically significant over the full sample. However, when splitting the sample into three subperiods (pre-Covid-19, Covid-19 and post-Covid-19), statistically significant differences are found, especially during the pandemic period. Moreover, the estimation of a GARCH (1, 1) model for stock returns shows that their conditional volatility is characterised by lower persistence and shorter half-lives in the case of brown stocks. |
| Keywords: | green stocks, brown stocks, fractional integration persistence, Covid-19 pandemic, Germany |
| JEL: | C22 G10 Q50 |
| Date: | 2024 |
| URL: | https://d.repec.org/n?u=RePEc:ces:ceswps:_11207 |