|
on Computational Economics |
| By: | Wendy E. Dunn; Raakin Kabir; Ellen E. Meade; Nitish R. Sinha |
| Abstract: | In an era increasingly shaped by artificial intelligence (AI), the public’s understanding of economic policy may be filtered through the lens of generative AI models (also called large language models or LLMs). Generative AI models offer the promise of quickly ingesting and interpreting large amounts of textual information. |
| Date: | 2024–12–06 |
| URL: | https://d.repec.org/n?u=RePEc:fip:fedgfn:2024-12-06-1 |
| By: | Mahalakshmi Manian (Research Scholar); Parthajit Kayal ((corresponding author), Assistant Professor Madras School of Economics, Chennai) |
| Abstract: | This research investigates the phenomenon of economic or financial bubbles within the Indian stock market context, characterized by pronounced asset price inflation exceeding the intrinsic worth of the underlying assets. Leveraging data from the NIFTY 500 index spanning the period 2003 to 2021, the study utilizes the Phillips, Shi, and Yu (PSY) method (Phillips et. al., 2015b), which employs a right-tailed unit root test, to discern the presence of financial bubbles. Subsequently, machine learning algorithms are employed to predict real-time occurrences of such bubbles. Analysis reveals the manifestation of financial bubbles within the Indian stock market notably in the years 2007 and 2017. Moreover, empirical evidence underscores the superior predictive efficacy of Artificial Neural Networks, Random Forest, and Gradient Boosting algorithms vis-à-vis conventional statistical methodologies in forecasting financial bubble occurrences within the Indian stock market. Policymakers should use advanced machine learning techniques for real-time financial bubble detection to improve regulation and mitigate market risks. |
| Keywords: | Financial Bubbles; Machine Learning; K-nearest Neighbour; Random Forest Classifier; Artificial Neural Network; Naïve Bayes |
| JEL: | G1 G2 G3 C1 C5 |
| Date: | 2024–10 |
| URL: | https://d.repec.org/n?u=RePEc:mad:wpaper:2024-270 |
| By: | Herbert Dawid (Bielefeld University, Germany); Philipp Harting (Université Côte d'Azur, CNRS, GREDEG, France; Bielefeld University, Germany); Michal Neugart (Technical University of Darmstadt, Germany) |
| Abstract: | Artificial intelligence algorithms are increasingly used for online pricing and are seen as a major threat to competitive markets. We show that if firms use a deep Q-network (DQN) as an example of a state-of-the-art machine learning algorithm, prices are supra-competitive in duopoly but quickly move to competitive prices as the number of competitors in an oligopoly increases. This finding is very robust concerning variations of the exploration and learning rate used in the DQN algorithm. |
| Keywords: | algorithmic price setting, deep Q-network, oligopoly, supracompetitive prices |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:gre:wpaper:2024-32 |
| By: | Federico Giorgi (DEF, University of Rome "Tor Vergata"); Stefano Herzel (DEF, University of Rome "Tor Vergata"); Paolo Pigato (DEF, University of Rome "Tor Vergata") |
| Abstract: | We propose an algorithm, based on Reinforcement Learning, to hedge the payoff on a European call option. The algorithm is first tested in a model where the problem has a well known analytic solution, so that we can compare the strategy obtained by the algorithm to the theoretical optimal one. In a more realistic case, considering transaction costs, the algorithm outperforms the standard delta hedging strategy. |
| Keywords: | Reinforcement Learning; Dynamic Strategies; Risk management |
| Date: | 2024–12–17 |
| URL: | https://d.repec.org/n?u=RePEc:rtv:ceisrp:586 |
| By: | Sebastian Bell; Ali Kakhbod; Martin Lettau; Abdolreza Nazemi |
| Abstract: | Machine learning methods in asset pricing are often criticized for their black box nature. We study this issue by predicting corporate bond returns using interpretable machine learning on a high-dimensional bond characteristics dataset. We achieve state-of-the-art performance while maintaining an interpretable model structure, overcoming the accuracy-interpretability trade-off. The estimation uncovers nonlinear relationships and economically meaningful interactions in bond pricing, notably related to term structure and macroeconomic uncertainty. Subsample analysis reveals stronger sensitivities to these effects for small firms and long-maturity bonds. Finally, we demonstrate how interpretable models enhance transparency in portfolio construction by providing ex ante insights into portfolio composition. |
| JEL: | C45 C55 G11 G12 |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:nbr:nberwo:33320 |
| By: | Tobias Schimanski (University of Zurich); Jingwei Ni (ETH Zurich); Mathias Kraus (University of Erlangen-Nuremberg-Friedrich Alexander Universität Erlangen Nürnberg); Elliott Ash (ETH Zürich); Markus Leippold (University of Zurich; Swiss Finance Institute) |
| Abstract: | Advances towards more faithful and traceable answers of Large Language Models (LLMs) are crucial for various research and practical endeavors. One avenue in reaching this goal is basing the answers on reliable sources. However, this Evidence-Based QA has proven to work insufficiently with LLMs in terms of citing the correct sources (source quality) and truthfully representing the information within sources (answer attributability). In this work, we systematically investigate how to robustly fine-tune LLMs for better source quality and answer attributability. Specifically, we introduce a data generation pipeline with automated data quality filters, which can synthesize diversified high-quality training and testing data at scale. We further introduce four test sets to benchmark the robustness of fine-tuned specialist models. Extensive evaluation shows that fine-tuning on synthetic data improves performance on both in- and out-of-distribution. Furthermore, we show that data quality, which can be drastically improved by proposed quality filters, matters more than quantity in improving Evidence-Based QA. |
| Date: | 2024–03 |
| URL: | https://d.repec.org/n?u=RePEc:chf:rpseri:rp2494 |
| By: | Munipalle, Pravith |
| Abstract: | Bot trading, or algorithmic trading, has transformed modern financial markets by using advanced technologies like artificial intelligence and machine learning to execute trades with unparalleled speed and efficiency. This paper examines the mechanisms and types of trading bots, their impact on market liquidity, efficiency, and stability, and the ethical and regulatory challenges they pose. Key findings highlight the dual nature of bot trading—enhancing market performance while introducing systemic risks, such as those observed during the 2010 Flash Crash. Emerging technologies like blockchain and predictive analytics, along with advancements in AI, present opportunities for innovation but also underscore the need for robust regulations and ethical design. To provide deeper insights, we conducted an experiment analyzing the performance of different trading bot strategies in simulated market conditions, revealing the potential and pitfalls of these systems under varying scenarios. |
| Date: | 2024–12–22 |
| URL: | https://d.repec.org/n?u=RePEc:osf:osfxxx:p98zv |
| By: | Christoph Engel (Max Planck Institute for Research on Collective Goods) |
| Keywords: | comparative law, contract fulfilment, change in circumstances, experiment, large language model, GPT, manipulating language of stimulus material |
| JEL: | C45 C81 C88 C91 D91 K12 K40 P50 |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:mpg:wpaper:2024_12 |
| By: | Robert Kelchen; Dubravka Ritter; Douglas A. Webber |
| Abstract: | In this paper, we assemble the most comprehensive dataset to date on the characteristics of colleges and universities, including dates of operation, institutional setting, student body, staff, and finance data from 2002 to 2023. We provide an extensive description of what is known and unknown about closed colleges compared with institutions that did not close. Using this data, we first develop a series of predictive models of financial distress, utilizing factors like operational revenue/expense patterns, sources of revenue, metrics of liquidity and leverage, enrollment/staff patterns, and prior signs of significant financial strain. We benchmark these models against existing federal government screening mechanisms such as financial responsibility scores and heightened cash monitoring. We document a high degree of missing data among colleges that eventually close and show that this is a key impediment to identifying at risk institutions. We then show that modern machine learning techniques, combined with richer data, are far more effective at predicting college closures than linear probability models, and considerably more effective than existing accountability metrics. Our preferred model, which combines an off-the-shelf machine learning algorithm with the richest set of explanatory variables, can significantly improve predictive accuracy even for institutions with complete data, but is particularly helpful for predicting instances of financial distress for institutions with spotty data. Finally, we conduct simulations using our estimates to contemplate likely increases in future closures, showing that enrollment challenges resulting from an impending demographic cliff are likely to significantly increase annual college closures for reasonable scenarios. |
| Keywords: | higher education; college; university; enrollment; tuition; revenue; budget; closure; fiscal challenge; demographic cliff |
| JEL: | I2 I22 I23 |
| Date: | 2024–12–02 |
| URL: | https://d.repec.org/n?u=RePEc:fip:fedpwp:99207 |
| By: | Kaiji Chen; Mr. Yunhui Zhao |
| Abstract: | We construct a daily Chinese Housing Market Sentiment Index by applying GPT-4o to Chinese news articles. Our method outperforms traditional models in several validation tests, including a test based on a suite of machine learning models. Applying this index to household-level data, we find that after monetary easing, an important group of homebuyers (who have a college degree and are aged between 30 and 50) in cities with more optimistic housing sentiment have lower responses in non-housing consumption, whereas for homebuyers in other age-education groups, such a pattern does not exist. This suggests that current monetary easing might be more effective in boosting non-housing consumption than in the past for China due to weaker crowding-out effects from pessimistic housing sentiment. The paper also highlights the need for complementary structural reforms to enhance monetary policy transmission in China, a lesson relevant for other similar countries. Methodologically, it offers a tool for monitoring housing sentiment and lays out some principles for applying generative AI models, adaptable to other studies globally. |
| Keywords: | Chinese Housing Market Sentiment; Generative AI; Monetary Policy Transmission; Consumption; Crowding-Out |
| Date: | 2024–12–23 |
| URL: | https://d.repec.org/n?u=RePEc:imf:imfwpa:2024/264 |
| By: | Markus Leippold (University of Zurich; Swiss Finance Institute); Qian Wang (University of Zurich - Department Finance; Inovest Partners AG); Min Yang (Swiss Finance Institute - University of Zurich) |
| Abstract: | This paper explores the effectiveness of technical patterns in predicting asset prices and market movements, emphasizing the role of news sentiment. We employ an image recognition method to detect technical patterns in price images and assess whether this approach provides more information than traditional rule-based methods. Our findings indicate that many model-based patterns yield significant returns in the US market, whereas bottom-type patterns are less effective in the Chinese market. The model demonstrates high accuracy in training samples and strong out-of-sample performance. Our empirical analysis concludes that technical patterns remain effective in recent stock markets when combined with news sentiment, offering a profitable portfolio strategy. This study highlights the potential of image recognition methods in market data analysis and underscores the importance of sentiment in technical analysis. |
| Date: | 2024–08 |
| URL: | https://d.repec.org/n?u=RePEc:chf:rpseri:rp2488 |
| By: | Hao Hao (Global Data Insight & Analytics, Ford Motor Company, Michigan); Tae-Hwy Lee (Department of Economics, University of California Riverside) |
| Abstract: | When the endogenous variable is an unknown function of observable instruments,  its conditional mean can be approximated using the sieve functions of observable instruments. We propose a novel instrument selection method, Double-criteria Boosting (DB), that consistently selects only valid and relevant instruments from a large set of candidate instruments. In the Monte Carlo simulation, we compare GMM using DB (DB-GMM) with other estimation methods and demonstrate that DB-GMM gives lower bias and RMSE. In the empirical application to the automobile demand, the DBGMM estimator is suggesting a more elastic estimate of the price elasticity of demand than the standard 2SLS estimator. |
| Keywords: | Causal inference with high dimensional instruments; Irrelevant instruments; Invalid instruments; Instrument Selection; Machine Learning; Boosting. |
| JEL: | C1 C5 |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:ucr:wpaper:202411 |