|
on Big Data |
| By: | Fiona Xiao Jingyi; Lili Liu |
| Abstract: | Forecasting central bank policy decisions remains a persistent challenge for investors, financial institutions, and policymakers due to the wide-reaching impact of monetary actions. In particular, anticipating shifts in the U.S. federal funds rate is vital for risk management and trading strategies. Traditional methods relying only on structured macroeconomic indicators often fall short in capturing the forward-looking cues embedded in central bank communications. This study examines whether predictive accuracy can be enhanced by integrating structured data with unstructured textual signals from Federal Reserve communications. We adopt a multi-modal framework, comparing traditional machine learning models, transformer-based language models, and deep learning architectures in both unimodal and hybrid settings. Our results show that hybrid models consistently outperform unimodal baselines. The best performance is achieved by combining TF-IDF features of FOMC texts with economic indicators in an XGBoost classifier, reaching a test AUC of 0.83. FinBERT-based sentiment features marginally improve ranking but perform worse in classification, especially under class imbalance. SHAP analysis reveals that sparse, interpretable features align more closely with policy-relevant signals. These findings underscore the importance of integrating textual and structured signals transparently. For monetary policy forecasting, simpler hybrid models can offer both accuracy and interpretability, delivering actionable insights for researchers and decision-makers. |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2506.22763 |
| By: | Gorjian, Mahshid |
| Abstract: | It is becoming increasingly important to predict property prices to mitigate investment risk, establish policies, and preserve market stability. To determine the practical utility and anticipated efficacy of the sophisticated statistical and machine learning models that have emerged, a comparative analysis is required. The purpose of this systematic study is to assess the predictive effectiveness and interpretability of hedonic regression and complex machine learning models in the estimation of housing prices in a wide range of foreign scenarios. In May 2024, a thorough search was conducted in Scopus, Google Scholar, and Web of Science. The search terms included "hedonic pricing models, " "machine learning, " and "housing price prediction, " in addition to others. The inclusion criteria required the utilization of empirical research published after 2000, a comparison of at least two predictive models, and reliable transaction data. Research that utilized non-empirical methodologies or web- scraped prices was excluded. Twenty-three investigations met the eligibility criteria. The evaluation was conducted in accordance with the reporting criteria of PRISMA 2020. Random Forest was the most frequently employed and consistently high-performing model, being selected in 14 of 23 studies and regarded as exceptional in five. Despite their lack of precision, hedonic regression models provided critical explanatory insights into critical variables, such as proximity to urban centers, property characteristics, and location. The integration of hedonic and machine learning models improved the interpretability and accuracy of the predicted results. Many of the studies included in this review were longitudinal, covered a diverse range of international contexts (specifically, Asia, Europe, America, and Australia), and demonstrated a rise in research output beyond 2020. Even though hedonic models retain a significant amount of explanatory power, the precision of home price predictions is improved by machine learning, particularly Random Forest and neural networks. The optimal results for researchers, real estate professionals, and policymakers who aim to improve market transparency and enlighten effective policy decisions are achieved through the seamless integration of these techniques. |
| Keywords: | housing price prediction; machine learning; hedonic price model; Random Forest; real estate valuation; artificial neural networks; systematic review; property market analysis |
| JEL: | C00 C01 C10 |
| Date: | 2025 |
| URL: | https://d.repec.org/n?u=RePEc:pra:mprapa:125676 |
| By: | Nicholas Gray; Finn Lattimore; Kate McLoughlin; Callan Windsor |
| Abstract: | In a world of increasing policy uncertainty, central banks are relying more on soft information sources to complement traditional economic statistics and model-based forecasts. One valuable source of soft information comes from intelligence gathered through central bank liaison programs -- structured programs in which central bank staff regularly talk with firms to gather insights. This paper introduces a new text analytics and retrieval tool that efficiently processes, organises, and analyses liaison intelligence gathered from firms using modern natural language processing techniques. The textual dataset spans 25 years, integrates new information as soon as it becomes available, and covers a wide range of business sizes and industries. The tool uses both traditional text analysis techniques and powerful language models to provide analysts and researchers with three key capabilities: (1) quickly querying the entire history of business liaison meeting notes; (2) zooming in on particular topics to examine their frequency (topic exposure) and analysing the associated tone and uncertainty of the discussion; and (3) extracting precise numerical values from the text, such as firms' reported figures for wages and prices growth. We demonstrate how these capabilities are useful for assessing economic conditions by generating text-based indicators of wages growth and incorporating them into a nowcasting model. We find that adding these text-based features to current best-in-class predictive models, combined with the use of machine learning methods designed to handle many predictors, significantly improves the performance of nowcasts for wages growth. Predictive gains are driven by a small number of features, indicating a sparse signal in contrast to other predictive problems in macroeconomics, where the signal is typically dense. |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2506.18505 |
| By: | Yating Ru (Asian Development Bank); Elizabeth Tennant (Cornell University); David Matteson (Cornell University); Christopher Barrett (Cornell University) |
| Abstract: | Recent studies harnessing geospatial big data and machine learning have significantly advanced poverty mapping, enabling granular and timely welfare estimates in traditionally data scarce regions. While much of the existing research has focused on overall out-of-sample predictive performance, there is a lack of understanding regarding where such models underperform and whether key spatial relationships might vary across places. This study investigates spatial heterogeneity in machine learning-based poverty mapping, testing whether spatial regression and machine learning techniques produce more unbiased predictions. We find that extrapolation into unsurveyed areas suffers from biases that spatial methods do not resolve; welfare is overestimated in impoverished regions, rural areas, and single sector-dominated economies, whereas it tends to be underestimated in wealthier, urbanized, and diversified economies. Even as spatial models improve overall predictive accuracy, enhancements in traditionally underperforming areas remain marginal. This underscores the need for more representative training datasets and better remotely sensed proxies, especially for poor and rural regions, in future research related to machine learning-based poverty mapping. |
| Keywords: | poverty mapping;machine learning;spatial models;East Africa |
| JEL: | C21 C55 I32 |
| Date: | 2025–09–05 |
| URL: | https://d.repec.org/n?u=RePEc:ris:adbewp:021518 |
| By: | Linh Nguyen; Marcel Boersma; Erman Acar |
| Abstract: | Fraudulent activity in the financial industry costs billions annually. Detecting fraud, therefore, is an essential yet technically challenging task that requires carefully analyzing large volumes of data. While machine learning (ML) approaches seem like a viable solution, applying them successfully is not so easy due to two main challenges: (1) the sparsely labeled data, which makes the training of such approaches challenging (with inherent labeling costs), and (2) lack of explainability for the flagged items posed by the opacity of ML models, that is often required by business regulations. This article proposes SAGE-FIN, a semi-supervised graph neural network (GNN) based approach with Granger causal explanations for Financial Interaction Networks. SAGE-FIN learns to flag fraudulent items based on weakly labeled (or unlabelled) data points. To adhere to regulatory requirements, the flagged items are explained by highlighting related items in the network using Granger causality. We empirically validate the favorable performance of SAGE-FIN on a real-world dataset, Bipartite Edge-And-Node Attributed financial network (Elliptic++), with Granger-causal explanations for the identified fraudulent items without any prior assumption on the network structure. |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2507.01980 |
| By: | Paulo Andr\'e Lima de Castro |
| Abstract: | Autonomous trading strategies have been a subject of research within the field of artificial intelligence (AI) for aconsiderable period. Various AI techniques have been explored to develop autonomous agents capable of trading financial assets. These approaches encompass traditional methods such as neural networks, fuzzy logic, and reinforcement learning, as well as more recent advancements, including deep neural networks and deep reinforcement learning. Many developers report success in creating strategies that exhibit strong performance during simulations using historical price data, a process commonly referred to as backtesting. However, when these strategies are deployed in real markets, their performance often deteriorates, particularly in terms of risk-adjusted returns. In this study, we propose an AI-based strategy inspired by a classical investment paradigm: Value Investing. Financial AI models are highly susceptible to lookahead bias and other forms of bias that can significantly inflate performance in backtesting compared to live trading conditions. To address this issue, we conducted a series of computational simulations while controlling for these biases, thereby reducing the risk of overfitting. Our results indicate that the proposed approach outperforms major Brazilian market benchmarks. Moreover, the strategy, named AlphaX, demonstrated superior performance relative to widely used technical indicators such as the Relative Strength Index (RSI) and Money Flow Index (MFI), with statistically significant results. Finally, we discuss several open challenges and highlight emerging technologies in qualitative analysis that may contribute to the development of a comprehensive AI-based Value Investing framework in the future |
| Date: | 2025–08 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2508.13429 |
| By: | Boris Kriuk; Logic Ng; Zarif Al Hossain |
| Abstract: | Support and resistance (SR) levels are central to technical analysis, guiding traders in entry, exit, and risk management. Despite widespread use, traditional SR identification methods often fail to adapt to the complexities of modern, volatile markets. Recent research has introduced machine learning techniques to address the following challenges, yet most focus on price prediction rather than structural level identification. This paper presents DeepSupp, a new deep learning approach for detecting financial support levels using multi-head attention mechanisms to analyze spatial correlations and market microstructure relationships. DeepSupp integrates advanced feature engineering, constructing dynamic correlation matrices that capture evolving market relationships, and employs an attention-based autoencoder for robust representation learning. The final support levels are extracted through unsupervised clustering, leveraging DBSCAN to identify significant price thresholds. Comprehensive evaluations on S&P 500 tickers demonstrate that DeepSupp outperforms six baseline methods, achieving state-of-the-art performance across six financial metrics, including essential support accuracy and market regime sensitivity. With consistent results across diverse market conditions, DeepSupp addresses critical gaps in SR level detection, offering a scalable and reliable solution for modern financial analysis. Our approach highlights the potential of attention-based architectures to uncover nuanced market patterns and improve technical trading strategies. |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2507.01971 |
| By: | Jakub Micha\'nk\'ow |
| Abstract: | This study evaluates deep neural networks for forecasting probability distributions of financial returns. 1D convolutional neural networks (CNN) and Long Short-Term Memory (LSTM) architectures are used to forecast parameters of three probability distributions: Normal, Student's t, and skewed Student's t. Using custom negative log-likelihood loss functions, distribution parameters are optimized directly. The models are tested on six major equity indices (S\&P 500, BOVESPA, DAX, WIG, Nikkei 225, and KOSPI) using probabilistic evaluation metrics including Log Predictive Score (LPS), Continuous Ranked Probability Score (CRPS), and Probability Integral Transform (PIT). Results show that deep learning models provide accurate distributional forecasts and perform competitively with classical GARCH models for Value-at-Risk estimation. The LSTM with skewed Student's t distribution performs best across multiple evaluation criteria, capturing both heavy tails and asymmetry in financial returns. This work shows that deep neural networks are viable alternatives to traditional econometric models for financial risk assessment and portfolio management. |
| Date: | 2025–08 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2508.18921 |
| By: | Jonathan Garita-Garita (Department of Economic Research, Central Bank of Costa Rica); César Ulate-Sancho (Department of Economic Research, Central Bank of Costa Rica) |
| Abstract: | This paper offers a daily-frequency analysis and short-term forecasting of Costa Rica’s foreign currency market using deep neural network algorithms. These algo-rithms efficiently integrates multiple high-frequency data to capture trends, seasonal patterns, and daily movements in the exchange rate from 2017 to March 2025. The results indicate that these models excels in predicting the observed exchange rate up to five days in advance, outperforming traditional time series forecasting methods in terms of accuracy. *** Resumen: Este artículo realiza un análisis de alta frecuencia del mercado de divisas de Costa Rica utilizando algoritmos de redes neuronales profundas. Se emplean datos diarios de acceso público de MONEX desde 2017 hasta marzo de 2025 para identificar quiebres de tendencia, patrones estacionales y la importancia relativa de las variables explicativas que determinan los movimientos diarios del tipo de cambio en MONEX. El modelo calibrado muestra una alta precisión para comprender la información histórica y realizar proyecciones del tipo de cambio a cinco días. Los resultados sugieren que los movimientos observados del tipo de cambio en 2024 están alineados con su tendencia y que existen factores estacionales significativos que influyen en el tipo de cambio a lo largo del año. |
| Keywords: | Exchange Rate, Forecast, Deep Neural Network, Tipo de cambio, Pronóstico, Redes neuronales profundas |
| JEL: | C45 C53 F31 O24 |
| Date: | 2025–07 |
| URL: | https://d.repec.org/n?u=RePEc:apk:doctra:2505 |
| By: | Ryan Samson; Adrian Banner; Luca Candelori; Sebastien Cottrell; Tiziana Di Matteo; Paul Duchnowski; Vahagn Kirakosyan; Jose Marques; Kharen Musaelian; Stefano Pasquali; Ryan Stever; Dario Villani |
| Abstract: | We introduce a novel proxy for firm linkages, Characteristic Vector Linkages (CVLs). We use this concept to estimate firm linkages, first through Euclidean similarity, and then by applying Quantum Cognition Machine Learning (QCML) to similarity learning. We demonstrate that both methods can be used to construct profitable momentum spillover trading strategies, but QCML similarity outperforms the simpler Euclidean similarity. |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2506.19856 |
| By: | Jonathan Benchimol (BoI - Bank of Israel); Sophia Kazinnik (Stanford University); Yossi Saadon (BoI - Bank of Israel) |
| Abstract: | In this study, we examine the Federal Reserve's communication strategies during the COVID-19 pandemic, comparing them with communication during previous periods of economic stress. Using specialized dictionaries tailored to COVID-19, unconventional monetary policy (UMP), and financial stability, combined with sentiment analysis and topic modeling techniques, we identify a distinct focus in Fed communication during the pandemic on financial stability, market volatility, social welfare, and UMP, characterized by notable contextual uncertainty. Through comparative analysis, we juxtapose the Fed's communication during the COVID-19 crisis with its responses during the dot-com and global financial crises, examining content, sentiment, and timing dimensions. Our findings reveal that Fed communication and policy actions were more reactive to the COVID-19 crisis than to previous crises. Additionally, declining sentiment related to financial stability in interest rate announcements and minutes anticipated subsequent accommodative monetary policy decisions. We further document that communicating about UMP has become the "new normal" for the Fed's Federal Open Market Committee meeting minutes and Chairman's speeches since the Global Financial Crisis, reflecting an institutional adaptation in communication strategy following periods of economic distress. These findings contribute to our understanding of how central bank communication evolves during crises and how communication strategies adapt to exceptional economic circumstances. |
| Keywords: | Data science, Machine leaning, Text analysis, Text analytics, COVID-19, Text mining, Financial stability, Unconventional monetary policy, Central bank communication |
| Date: | 2025–09 |
| URL: | https://d.repec.org/n?u=RePEc:hal:journl:hal-05203069 |
| By: | Ayato Kitadai; Yusuke Fukasawa; Nariaki Nishino |
| Abstract: | Large language models (LLMs) are increasingly used to simulate human decision-making, but their intrinsic biases often diverge from real human behavior--limiting their ability to reflect population-level diversity. We address this challenge with a persona-based approach that leverages individual-level behavioral data from behavioral economics to adjust model biases. Applying this method to the ultimatum game--a standard but difficult benchmark for LLMs--we observe improved alignment between simulated and empirical behavior, particularly on the responder side. While further refinement of trait representations is needed, our results demonstrate the promise of persona-conditioned LLMs for simulating human-like decision patterns at scale. |
| Date: | 2025–08 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2508.18600 |
| By: | Alper Deniz Karakas |
| Abstract: | This study examines the long-term economic impact of the colonial Mita system in Peru, building on Melissa Dell's foundational work on the enduring effects of forced labor institutions. The Mita, imposed by the Spanish colonial authorities from 1573 to 1812, required indigenous communities within a designated boundary to supply labor to mines, primarily near Potosi. Dell's original regression discontinuity design (RDD) analysis, leveraging the Mita boundary to estimate the Mita's legacy on modern economic outcomes, indicates that regions subjected to the Mita exhibit lower household consumption levels and higher rates of child stunting. In this paper, I replicate Dell's results and extend this analysis. I apply Double Machine Learning (DML) methods--the Partially Linear Regression (PLR) model and the Interactive Regression Model (IRM)--to further investigate the Mita's effects. DML allows for the inclusion of high-dimensional covariates and enables more flexible, non-linear modeling of treatment effects, potentially capturing complex relationships that a polynomial-based approach may overlook. While the PLR model provides some additional flexibility, the IRM model allows for fully heterogeneous treatment effects, offering a nuanced perspective on the Mita's impact across regions and district characteristics. My findings suggest that the Mita's economic legacy is more substantial and spatially heterogeneous than originally estimated. The IRM results reveal that proximity to Potosi and other district-specific factors intensify the Mita's adverse impact, suggesting a deeper persistence of regional economic inequality. These findings underscore that machine learning addresses the realistic non-linearity present in complex, real-world systems. By modeling hypothetical counterfactuals more accurately, DML enhances my ability to estimate the true causal impact of historical interventions. |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2506.18947 |
| By: | Irina G. Tanashkina; Alexey S. Tanashkin; Alexander S. Maksimchuik; Anna Yu. Poshivailo |
| Abstract: | In this article, we review modern approaches to building interpretable models of property markets using machine learning on the base of mass valuation of property in the Primorye region, Russia. The researcher, lacking expertise in this topic, encounters numerous difficulties in the effort to build a good model. The main source of this is the huge difference between noisy real market data and ideal data which is very common in all types of tutorials on machine learning. This paper covers all stages of modeling: the collection of initial data, identification of outliers, the search and analysis of patterns in the data, the formation and final choice of price factors, the building of the model, and the evaluation of its efficiency. For each stage, we highlight potential issues and describe sound methods for overcoming emerging difficulties on actual examples. We show that the combination of classical linear regression with interpolation methods of geostatistics allows to build an effective model for land parcels. For flats, when many objects are attributed to one spatial point the application of geostatistical methods is difficult. Therefore we suggest linear regression with automatic generation and selection of additional rules on the base of decision trees, so called the RuleFit method. Thus we show, that despite such a strong restriction as the requirement of interpretability which is important in practical aspects, for example, legal matters, it is still possible to build effective models of real property markets. |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2506.15723 |
| By: | Kai-Robin Lange; Tobias Schmidt; Matthias Reccius; Henrik M\"uller; Michael Roos; Carsten Jentsch |
| Abstract: | With rapidly evolving media narratives, it has become increasingly critical to not just extract narratives from a given corpus but rather investigate, how they develop over time. While popular narrative extraction methods such as Large Language Models do well in capturing typical narrative elements or even the complex structure of a narrative, applying them to an entire corpus comes with obstacles, such as a high financial or computational cost. We propose a combination of the language understanding capabilities of Large Language Models with the large scale applicability of topic models to dynamically model narrative shifts across time using the Narrative Policy Framework. We apply a topic model and a corresponding change point detection method to find changes that concern a specific topic of interest. Using this model, we filter our corpus for documents that are particularly representative of that change and feed them into a Large Language Model that interprets the change that happened in an automated fashion and distinguishes between content and narrative shifts. We employ our pipeline on a corpus of The Wall Street Journal news paper articles from 2009 to 2023. Our findings indicate that a Large Language Model can efficiently extract a narrative shift if one exists at a given point in time, but does not perform as well when having to decide whether a shift in content or a narrative shift took place. |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2506.20269 |
| By: | Sedigheh Mahdavi (Kristin); Jiating (Kristin); Chen; Pradeep Kumar Joshi; Lina Huertas Guativa; Upmanyu Singh |
| Abstract: | Large Language Models (LLMs) have been employed in financial decision making, enhancing analytical capabilities for investment strategies. Traditional investment strategies often utilize quantitative models, fundamental analysis, and technical indicators. However, LLMs have introduced new capabilities to process and analyze large volumes of structured and unstructured data, extract meaningful insights, and enhance decision-making in real-time. This survey provides a structured overview of recent research on LLMs within the financial domain, categorizing research contributions into four main frameworks: LLM-based Frameworks and Pipelines, Hybrid Integration Methods, Fine-Tuning and Adaptation Approaches, and Agent-Based Architectures. This study provides a structured review of recent LLMs research on applications in stock selection, risk assessment, sentiment analysis, trading, and financial forecasting. By reviewing the existing literature, this study highlights the capabilities, challenges, and potential directions of LLMs in financial markets. |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2507.01990 |
| By: | Ho Ming Lee; Katrien Antonio; Benjamin Avanzi; Lorenzo Marchi; Rui Zhou |
| Abstract: | Ensuring equitable treatment (fairness) across protected attributes (such as gender or ethnicity) is a critical issue in machine learning. Most existing literature focuses on binary classification, but achieving fairness in regression tasks-such as insurance pricing or hiring score assessments-is equally important. Moreover, anti-discrimination laws also apply to continuous attributes, such as age, for which many existing methods are not applicable. In practice, multiple protected attributes can exist simultaneously; however, methods targeting fairness across several attributes often overlook so-called "fairness gerrymandering", thereby ignoring disparities among intersectional subgroups (e.g., African-American women or Hispanic men). In this paper, we propose a distance covariance regularisation framework that mitigates the association between model predictions and protected attributes, in line with the fairness definition of demographic parity, and that captures both linear and nonlinear dependencies. To enhance applicability in the presence of multiple protected attributes, we extend our framework by incorporating two multivariate dependence measures based on distance covariance: the previously proposed joint distance covariance (JdCov) and our novel concatenated distance covariance (CCdCov), which effectively address fairness gerrymandering in both regression and classification tasks involving protected attributes of various types. We discuss and illustrate how to calibrate regularisation strength, including a method based on Jensen-Shannon divergence, which quantifies dissimilarities in prediction distributions across groups. We apply our framework to the COMPAS recidivism dataset and a large motor insurance claims dataset. |
| Date: | 2025–09 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2509.08163 |
| By: | Paloma Mar\'in; Sergio Ardanza-Trevijano; Javier Sabio |
| Abstract: | The digitalization of financial markets has shifted trading from voice to electronic channels, with Multi-Dealer-to-Client (MD2C) platforms now enabling clients to request quotes (RfQs) for financial instruments like bonds from multiple dealers simultaneously. In this competitive landscape, dealers cannot see each other's prices, making a rigorous analysis of the negotiation process crucial to ensure their profitability. This article introduces a novel general framework for analyzing the RfQ process using probabilistic graphical models and causal inference. Within this framework, we explore different inferential questions that are relevant for dealers participating in MD2C platforms, such as the computation of optimal prices, estimating potential revenues and the identification of clients that might be interested in trading the dealer's axes. We then move into analyzing two different approaches for model specification: a generative model built on the work of (Fermanian, Gu\'eant & Pu, 2017); and discriminative models utilizing machine learning techniques. We evaluate these methodologies using predictive metrics designed to assess their effectiveness in the context of optimal pricing, highlighting the relative benefits of using models that take into account the internal mechanisms of the negotiation process. |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2506.18147 |
| By: | Muhammad Bilal Zafar |
| Abstract: | The proliferation of artificial intelligence (AI) in financial services has prompted growing demand for tools that can systematically detect AI-related disclosures in corporate filings. While prior approaches often rely on keyword expansion or document-level classification, they fall short in granularity, interpretability, and robustness. This study introduces FinAI-BERT, a domain-adapted transformer-based language model designed to classify AI-related content at the sentence level within financial texts. The model was fine-tuned on a manually curated and balanced dataset of 1, 586 sentences drawn from 669 annual reports of U.S. banks (2015 to 2023). FinAI-BERT achieved near-perfect classification performance (accuracy of 99.37 percent, F1 score of 0.993), outperforming traditional baselines such as Logistic Regression, Naive Bayes, Random Forest, and XGBoost. Interpretability was ensured through SHAP-based token attribution, while bias analysis and robustness checks confirmed the model's stability across sentence lengths, adversarial inputs, and temporal samples. Theoretically, the study advances financial NLP by operationalizing fine-grained, theme-specific classification using transformer architectures. Practically, it offers a scalable, transparent solution for analysts, regulators, and scholars seeking to monitor the diffusion and framing of AI across financial institutions. |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2507.01991 |
| By: | Pesce, Simone; Errico, Marco; Pollio, Luigi |
| Abstract: | Firms respond heterogeneously to aggregate fluctuations, yet standard linear models impose restrictive assumptions on firm sensitivities. Applying the Generalized Random Forest to U.S. firm-level data, we document strong nonlinearities in how firm characteristics shape responses to macroeconomic shocks. We show that nonlinearities significantly lower aggregate esponses, leading linear models to overestimate the economy’s sensitivity to shocks by up to 1.7 percentage points. We also find that larger firms, which carry disproportionate economic weight, exhibit lower sensitivities, leading to a median reduction in aggregate economic sensitivity of 52%. Our results highlight the importance of accounting for nonlinearities and firm heterogeneity when analyzing macroeconomic fluctuations and the transmission of aggregate shocks. JEL Classification: D22, E32, C14, E5 |
| Keywords: | business cycle, firm sensitivity, monetary policy, oil shock, uncertainty |
| Date: | 2025–09 |
| URL: | https://d.repec.org/n?u=RePEc:ecb:ecbwps:20253107 |
| By: | Shrenik Jadhav; Birva Sevak; Srijita Das; Akhtar Hussain; Wencong Su; Van-Hai Bui |
| Abstract: | Peer-to-peer (P2P) trading is increasingly recognized as a key mechanism for decentralized market regulation, yet existing approaches often lack robust frameworks to ensure fairness. This paper presents FairMarket-RL, a novel hybrid framework that combines Large Language Models (LLMs) with Reinforcement Learning (RL) to enable fairness-aware trading agents. In a simulated P2P microgrid with multiple sellers and buyers, the LLM acts as a real-time fairness critic, evaluating each trading episode using two metrics: Fairness-To-Buyer (FTB) and Fairness-Between-Sellers (FBS). These fairness scores are integrated into agent rewards through scheduled {\lambda}-coefficients, forming an adaptive LLM-guided reward shaping loop that replaces brittle, rule-based fairness constraints. Agents are trained using Independent Proximal Policy Optimization (IPPO) and achieve equitable outcomes, fulfilling over 90% of buyer demand, maintaining fair seller margins, and consistently reaching FTB and FBS scores above 0.80. The training process demonstrates that fairness feedback improves convergence, reduces buyer shortfalls, and narrows profit disparities between sellers. With its language-based critic, the framework scales naturally, and its extension to a large power distribution system with household prosumers illustrates its practical applicability. FairMarket-RL thus offers a scalable, equity-driven solution for autonomous trading in decentralized energy systems. |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2506.22708 |
| By: | Alessio Brini; David A. Hsieh; Patrick Kuiper; Sean Moushegian; David Ye |
| Abstract: | The key objective of this paper is to develop an empirical model for pricing SPX options that can be simulated over future paths of the SPX. To accomplish this, we formulate and rigorously evaluate several statistical models, including neural network, random forest, and linear regression. These models use the observed characteristics of the options as inputs -- their price, moneyness and time-to-maturity, as well as a small set of external inputs, such as the SPX and its past history, dividend yield, and the risk-free rate. Model evaluation is performed on historical options data, spanning 30 years of daily observations. Significant effort is given to understanding the data and ensuring explainability for the neural network. A neural network model with two hidden layers and four neurons per layer, trained with minimal hyperparameter tuning, performs well against the theoretical Black-Scholes-Merton model for European options, as well as two other empirical models based on the random forest and the linear regression. It delivers arbitrage-free option prices without requiring these conditions to be imposed. |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2506.17511 |
| By: | Giorgos Demosthenous; Chryssis Georgiou; Eliada Polydorou |
| Abstract: | This study investigates the impact of data source diversity on the performance of cryptocurrency forecasting models by integrating various data categories, including technical indicators, on-chain metrics, sentiment and interest metrics, traditional market indices, and macroeconomic indicators. We introduce the Crypto100 index, representing the top 100 cryptocurrencies by market capitalization, and propose a novel feature reduction algorithm to identify the most impactful and resilient features from diverse data sources. Our comprehensive experiments demonstrate that data source diversity significantly enhances the predictive performance of forecasting models across different time horizons. Key findings include the paramount importance of on-chain metrics for both short-term and long-term predictions, the growing relevance of traditional market indices and macroeconomic indicators for longer-term forecasts, and substantial improvements in model accuracy when diverse data sources are utilized. These insights help demystify the short-term and long-term driving factors of the cryptocurrency market and lay the groundwork for developing more accurate and resilient forecasting models. |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2506.21246 |
| By: | Yanlong Wang; Jian Xu; Fei Ma; Hongkang Zhang; Hang Yu; Tiantian Gao; Yu Wang; Haochen You; Shao-Lun Huang; Danny Dongning Sun; Xiao-Ping Zhang |
| Abstract: | Financial time series forecasting is both highly significant and challenging. Previous approaches typically standardized time series data before feeding it into forecasting models, but this encoding process inherently leads to a loss of important information. Moreover, past time series models generally require fixed numbers of variables or lookback window lengths, which further limits the scalability of time series forecasting. Besides, the interpretability and the uncertainty in forecasting remain areas requiring further research, as these factors directly impact the reliability and practical value of predictions. To address these issues, we first construct a diverse financial image-text dataset (FVLDB) and develop the Uncertainty-adjusted Group Relative Policy Optimization (UARPO) method to enable the model not only output predictions but also analyze the uncertainty of those predictions. We then proposed FinZero, a multimodal pre-trained model finetuned by UARPO to perform reasoning, prediction, and analytical understanding on the FVLDB financial time series. Extensive experiments validate that FinZero exhibits strong adaptability and scalability. After fine-tuning with UARPO, FinZero achieves an approximate 13.48\% improvement in prediction accuracy over GPT-4o in the high-confidence group, demonstrating the effectiveness of reinforcement learning fine-tuning in multimodal large model, including in financial time series forecasting tasks. |
| Date: | 2025–09 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2509.08742 |
| By: | Chi-Sheng Chen; Xinyu Zhang; Ya-Chuan Chen |
| Abstract: | We propose a hybrid quantum-classical reinforcement learning framework for sector rotation in the Taiwan stock market. Our system employs Proximal Policy Optimization (PPO) as the backbone algorithm and integrates both classical architectures (LSTM, Transformer) and quantum-enhanced models (QNN, QRWKV, QASA) as policy and value networks. An automated feature engineering pipeline extracts financial indicators from capital share data to ensure consistent model input across all configurations. Empirical backtesting reveals a key finding: although quantum-enhanced models consistently achieve higher training rewards, they underperform classical models in real-world investment metrics such as cumulative return and Sharpe ratio. This discrepancy highlights a core challenge in applying reinforcement learning to financial domains -- namely, the mismatch between proxy reward signals and true investment objectives. Our analysis suggests that current reward designs may incentivize overfitting to short-term volatility rather than optimizing risk-adjusted returns. This issue is compounded by the inherent expressiveness and optimization instability of quantum circuits under Noisy Intermediate-Scale Quantum (NISQ) constraints. We discuss the implications of this reward-performance gap and propose directions for future improvement, including reward shaping, model regularization, and validation-based early stopping. Our work offers a reproducible benchmark and critical insights into the practical challenges of deploying quantum reinforcement learning in real-world finance. |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2506.20930 |
| By: | Sebastien Gallet; Julja Prodani |
| Abstract: | This paper builds on existing literature on federated learning to introduce an innovative framework, which we call federated modelling. Federated modelling enables collaborative modelling by a group of participants while bypassing the need for disclosing participants’ underlying private data, which are restricted due to legal or institutional requirements. While the uses of this framework can be numerous, the paper presents a proof of concept for a system-wide, granular financial stress test that enables effective cooperation among central banks without the need to disclose the underlying private data and models of the participating central banks or their reporting entities (banks and insurers). Our findings confirm that by leveraging machine learning techniques and using readily available computational tools, the framework allows participants to contribute to the development of shared models whose results are comparable to those using full granular data centralization. This has profound implications for regulatory cooperation and financial stability monitoring across jurisdictions. |
| Date: | 2025–08 |
| URL: | https://d.repec.org/n?u=RePEc:dnb:dnbocs:2503 |
| By: | Kerstin Bernoth |
| Abstract: | This paper investigates the effectiveness of the European Central Bank’s (ECB) communication in shaping market expectations and real economic outcomes. Using a transformer-based large language model (LLM) fine-tuned to ECB communication, the tone of monetary policy statements from 2003 to 2025 is classified, constructing a novel ECB Communication Stance Indicator. This indicator contains forward-looking information beyond standard macro-financial variables. Identified communication shocks are distinct from monetary policy and central bank information shocks. A structural Bayesian VAR reveals that hawkish communication signals favorable economic prospects, raising output, equity prices, and inflation, but also increases bond market stress. These findings highlight communication as an independent and effective tool of monetary policy, while also underscoring the importance of carefully calibrating tone to balance market expectations, and financial stability. |
| Keywords: | Monetary Policy, Central Bank Communication, Text Sentiment, Transformerbased Large Language Model, Bayesian Vector Autoregression, Local Projections |
| JEL: | C32 E43 E47 E52 E58 |
| Date: | 2025 |
| URL: | https://d.repec.org/n?u=RePEc:diw:diwwpp:dp2137 |
| By: | Umberto Collodel |
| Abstract: | This paper develops a novel method to simulate financial market reactions to European Central Bank (ECB) press conferences using a Large Language Model (LLM). We create a behavioral, agent-based simulation of 30 synthetic traders, each with distinct risk preferences, cognitive biases, and interpretive styles. These agents forecast Euro interest rate swap levels at 3-month, 2-year, and 10-year maturities, with the variation across forecasts serving as a measure of market uncertainty or disagreement. We evaluate three prompting strategies, naive, few-shot (enriched with historical data), and an advanced iterative 'LLM-as-a-Judge' framework, to assess the effect of prompt design on predictive performance. Even the naive approach generates a strong correlation (roughly 0.5) between synthetic disagreement and actual market outcomes, particularly for longer-term maturities. The LLM-as-a-Judge framework further improves accuracy at the first iteration. These results demonstrate that LLM-driven simulations can capture interpretive uncertainty beyond traditional measures, providing central banks with a practical tool to anticipate market reactions, refine communication strategies, and enhance financial stability. |
| Date: | 2025–08 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2508.13635 |
| By: | Ziyao Wang; Svetlozar T Rachev |
| Abstract: | Financial returns are known to exhibit heavy tails, volatility clustering and abrupt jumps that are poorly captured by classical diffusion models. Advances in machine learning have enabled highly flexible functional forms for conditional means and volatilities, yet few models deliver interpretable state--dependent tail risk, capture multiple forecast horizons and yield distributions amenable to backtesting and execution. This paper proposes a neural L\'evy jump--diffusion framework that jointly learns, as functions of observable state variables, the conditional drift, diffusion, jump intensity and jump size distribution. We show how a single shared encoder yields multiple forecasting heads corresponding to distinct horizons (daily, weekly, etc.), facilitating multi--horizon density forecasts and risk measures. The state vector includes conventional price and volume features as well as novel complexity measures such as permutation entropy and recurrence quantification analysis determinism, which quantify predictability in the underlying process. Estimation is based on a quasi--maximum likelihood approach that separates diffusion and jump contributions via bipower variation weights and incorporates monotonicity and smoothness regularisation to ensure identifiability. A cost--aware portfolio optimiser translates the model's conditional densities into implementable trading strategies under leverage, turnover and no--trade--band constraints. Extensive empirical analyses on cross--sectional equity data demonstrate improved calibration, sharper tail control and economically significant risk reduction relative to baseline diffusive and GARCH benchmarks. The proposed framework is therefore an interpretable, testable and practically deployable method for state--dependent risk and density forecasting. |
| Date: | 2025–08 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2509.01041 |