|
on Financial Markets |
| By: | DeMarzo, Peter (Stanford U); Krishnamurthy, Arvind (Stanford U); Nagel, Stefan (U of Chicago) |
| Abstract: | We develop a theoretical and empirical framework to estimate bank franchise value. In contrast to regulatory guidance and some existing models, we show that sticky deposits combined with low deposit rate betas do not imply a negative duration for franchise value. Operating costs could in principle generate negative duration, but they are more than offset by fixed interest rate spreads that arise largely from banks’ lending activity. As a result, bank franchise value declines as interest rates rise, and this decline exacerbates, rather than offsets, losses on banks’ security holdings. We also show that in the cross section, banks with the least responsive deposit rate tend to invest the most in long-term securities, suggesting that they are motivated to hedge cash flows rather than market value. Finally, despite significant losses to both asset and franchise values stemming from recent rate hikes, our analysis suggests that most U.S. banks still retain sufficient franchise value to remain solvent as ongoing concerns. |
| Date: | 2024–09 |
| URL: | https://d.repec.org/n?u=RePEc:ecl:stabus:4194 |
| By: | Peter Andre (Leibniz Institute for Financial Research SAFE); Philipp Schirmer (University of Bonn); Johannes Wohlfart (University of Cologne) |
| Abstract: | Investors’ return expectations are pivotal in stock markets, but the reasoning behind these expectations is not well understood. This paper sheds light on economic agents’ mental models – their subjective understanding – of the stock market. We conduct surveys with the general population, retail investors, financial professionals, and academic experts. Respondents forecast and explain how future returns respond to stale news about the future earnings streams of companies. We document four main results. First, while academic experts view stale news as irrelevant, households and professionals often believe that stale good news leads to persistently higher expected future returns. Second, academic experts refer to market efficiency to explain their forecasts, whereas households and many professionals directly equate higher future earnings with higher future returns, neglecting the offsetting effects of endogenous price adjustments. Third, additional experiments with households demonstrate that this neglect of equilibrium pricing does not reflect inattention to trading or price responses or ignorance about how returns are calculated. Instead, it reflects a gap in respondents’ mental models: they are unfamiliar with the concept of equilibrium pricing. Lastly, we illustrate the potential consequences of neglecting equilibrium pricing. We use panel data on household expectations to show that this neglect predicts previously documented belief anomalies such as return extrapolation and pro-cyclicality. |
| Keywords: | Mental models, Return expectations |
| JEL: | D83 D84 G11 G12 G41 G51 G53 |
| Date: | 2024–11–13 |
| URL: | https://d.repec.org/n?u=RePEc:kud:kucebi:2307 |
| By: | Hunter Ng |
| Abstract: | This article investigates whether the Federal Reserve Chair strategically controls facial expressions during FOMC press conferences and how these nonverbal cues affect financial markets. I use facial recognition technology on videos of press conferences from April 2011 to December 2020 to quantify changes in the Chair's nonverbal signals. Results show that facial expressions serve as a separate public signal, distinct from verbal content. Using deepfakes, I find that the same facial expressions expressed by different Fed Chairs are interpreted differentially. As their tenure increases, negative expressions become more frequent, eliciting adverse market reactions. Furthermore, the markets interpretation of these expressions evolves over time, suggesting that investors process facial cues with dual-processing finite-state Markov memory. In line with the Fed's goals of transparency and non-volatility, I find that Fed Chairs do not strategically control their expressions. |
| Date: | 2024–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2410.20214 |
| By: | Ali Elahi; Fatemeh Taghvaei |
| Abstract: | Predicting financial markets and stock price movements requires analyzing a company's performance, historic price movements, industry-specific events alongside the influence of human factors such as social media and press coverage. We assume that financial reports (such as income statements, balance sheets, and cash flow statements), historical price data, and recent news articles can collectively represent aforementioned factors. We combine financial data in tabular format with textual news articles and employ pre-trained Large Language Models (LLMs) to predict market movements. Recent research in LLMs has demonstrated that they are able to perform both tabular and text classification tasks, making them our primary model to classify the multi-modal data. We utilize retrieval augmentation techniques to retrieve and attach relevant chunks of news articles to financial metrics related to a company and prompt the LLMs in zero, two, and four-shot settings. Our dataset contains news articles collected from different sources, historic stock price, and financial report data for 20 companies with the highest trading volume across different industries in the stock market. We utilized recently released language models for our LLM-based classifier, including GPT- 3 and 4, and LLaMA- 2 and 3 models. We introduce an LLM-based classifier capable of performing classification tasks using combination of tabular (structured) and textual (unstructured) data. By using this model, we predicted the movement of a given stock's price in our dataset with a weighted F1-score of 58.5% and 59.1% and Matthews Correlation Coefficient of 0.175 for both 3-month and 6-month periods. |
| Date: | 2024–11 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2411.01368 |
| By: | Xinlin Wang; Zs\'ofia Kr\"aussl; Mats Brorsson |
| Abstract: | Bankruptcy prediction is an important research area that heavily relies on data science. It aims to help investors, managers, and regulators better understand the operational status of corporations and predict potential financial risks in advance. To improve prediction, researchers and practitioners have begun to utilize a variety of different types of data, ranging from traditional financial indicators to unstructured data, to aid in the construction and optimization of bankruptcy forecasting models. Over time, not only instrumentalized data improved, but also instrumentalized methodology for data structuring, cleaning, and analysis. With the aid of advanced analytical techniques that deploy machine learning and deep learning algorithms, bankruptcy assessment became more accurate over time. However, due to the sensitivity of financial data, the scarcity of valid public datasets remains a key bottleneck for the rapid modeling and evaluation of machine learning algorithms for targeted tasks. This study therefore introduces a taxonomy of datasets for bankruptcy research, and summarizes their characteristics. This paper also proposes a set of metrics to measure the quality and the informativeness of public datasets The taxonomy, coupled with the informativeness measure, thus aims at providing valuable insights to better assist researchers and practitioners in developing potential applications for various aspects of credit assessment and decision making by pointing at appropriate datasets for their studies. |
| Date: | 2024–11 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2411.01928 |
| By: | Abdoulaye Ndiaye |
| Abstract: | Blockchains, the technology underlying cryptocurrencies, face large fluctuations in user demand and marginal costs. These fluctuations make effective fee policies necessary to manage transaction service allocation. This paper models the conflict between the blockchain designer and validators with monopoly power in choosing between price-setting and quantity-setting fee policies. The key determinants of the advantage of price-setting on blockchains are the validators’ bargaining power, the elasticity of demand, the validators’ uncertainty about demand, and the covariance of demand and marginal costs. My results help account for differences between the fee policy designs of Bitcoin and Ethereum, the leading blockchains, and have implications for how they can be improved. |
| Keywords: | blockchain, transaction costs, fee policies, Bitcoin, Ethereum, demand fluctuations, price elasticity |
| Date: | 2024 |
| URL: | https://d.repec.org/n?u=RePEc:ces:ceswps:_11274 |
| By: | \'Isak P\'etursson; Mar\'ia \'Oskarsd\'ottir |
| Abstract: | We present a novel approach for predicting the distribution of asset returns using a quantile-based method with Long Short-Term Memory (LSTM) networks. Our model is designed in two stages: the first focuses on predicting the quantiles of normalized asset returns using asset-specific features, while the second stage incorporates market data to adjust these predictions for broader economic conditions. This results in a generalized model that can be applied across various asset classes, including commodities, cryptocurrencies, as well as synthetic datasets. The predicted quantiles are then converted into full probability distributions through kernel density estimation, allowing for more precise return distribution predictions and inferencing. The LSTM model significantly outperforms a linear quantile regression baseline by 98% and a dense neural network model by over 50%, showcasing its ability to capture complex patterns in financial return distributions across both synthetic and real-world data. By using exclusively asset-class-neutral features, our model achieves robust, generalizable results. |
| Date: | 2024–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2410.23296 |
| By: | Zhengyang Chi; Junbin Gao; Chao Wang |
| Abstract: | The interconnectedness of global financial markets has brought increasing attention to modeling volatility spillover effects. Via incorporating Graph Signal Processing techniques, a novel multivariate framework, extending the traditional Heterogeneous Auto-Regressive model, is developed in the spectral domain constructed by the graph Fourier transformation method. Further, a set of convolution filters with learnable weights is employed to more flexibly aggregate the past mid-term and long-term information. Using 24 global stock market indices, the effectiveness of the proposed model is demonstrated through comprehensive empirical evaluations. |
| Date: | 2024–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2410.22706 |
| By: | Quechen Yang |
| Abstract: | With the increasing maturity and expansion of the cryptocurrency market, understanding and predicting its price fluctuations has become an important issue in the field of financial engineering. This article introduces an innovative Genetic Algorithm-generated Alpha Sentiment (GAS) blending ensemble model specifically designed to predict Bitcoin market trends. The model integrates advanced ensemble learning methods, feature selection algorithms, and in-depth sentiment analysis to effectively capture the complexity and variability of daily Bitcoin trading data. The GAS framework combines 34 Alpha factors with 8 news economic sentiment factors to provide deep insights into Bitcoin price fluctuations by accurately analyzing market sentiment and technical indicators. The core of this study is using a stacked model (including LightGBM, XGBoost, and Random Forest Classifier) for trend prediction which demonstrates excellent performance in traditional buy-and-hold strategies. In addition, this article also explores the effectiveness of using genetic algorithms to automate alpha factor construction as well as enhancing predictive models through sentiment analysis. Experimental results show that the GAS model performs competitively in daily Bitcoin trend prediction especially when analyzing highly volatile financial assets with rich data. |
| Date: | 2024–11 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2411.03035 |