|
on Computational Economics |
| By: | Mostapha Benhenda (LAGA) |
| Abstract: | This paper presents a novel risk-sensitive trading agent combining reinforcement learning and large language models (LLMs). We extend the Conditional Value-at-Risk Proximal Policy Optimization (CPPO) algorithm, by adding risk assessment and trading recommendation signals generated by a LLM from financial news. Our approach is backtested on the Nasdaq-100 index benchmark, using financial news data from the FNSPID dataset and the DeepSeek V3, Qwen 2.5 and Llama 3.3 language models. The code, data, and trading agents are available at: https://github.com/benstaf/FinRL_DeepSee k |
| Date: | 2025–02 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2502.07393 |
| By: | Tianzuo Hu |
| Abstract: | This paper proposes a financial fraud detection system based on improved Random Forest (RF) and Gradient Boosting Machine (GBM). Specifically, the system introduces a novel model architecture called GBM-SSRF (Gradient Boosting Machine with Simplified and Strengthened Random Forest), which cleverly combines the powerful optimization capabilities of the gradient boosting machine (GBM) with improved randomization. The computational efficiency and feature extraction capabilities of the Simplified and Strengthened Random Forest (SSRF) forest significantly improve the performance of financial fraud detection. Although the traditional random forest model has good classification capabilities, it has high computational complexity when faced with large-scale data and has certain limitations in feature selection. As a commonly used ensemble learning method, the GBM model has significant advantages in optimizing performance and handling nonlinear problems. However, GBM takes a long time to train and is prone to overfitting problems when data samples are unbalanced. In response to these limitations, this paper optimizes the random forest based on the structure, reducing the computational complexity and improving the feature selection ability through the structural simplification and enhancement of the random forest. In addition, the optimized random forest is embedded into the GBM framework, and the model can maintain efficiency and stability with the help of GBM's gradient optimization capability. Experiments show that the GBM-SSRF model not only has good performance, but also has good robustness and generalization capabilities, providing an efficient and reliable solution for financial fraud detection. |
| Date: | 2025–02 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2502.15822 |
| By: | Alicia Vidler; Toby Walsh |
| Abstract: | Bilateral markets, such as those for government bonds, involve decentralized and opaque transactions between market makers (MMs) and clients, posing significant challenges for traditional modeling approaches. To address these complexities, we introduce TRIBE an agent-based model augmented with a large language model (LLM) to simulate human-like decision-making in trading environments. TRIBE leverages publicly available data and stylized facts to capture realistic trading dynamics, integrating human biases like risk aversion and ambiguity sensitivity into the decision-making processes of agents. Our research yields three key contributions: first, we demonstrate that integrating LLMs into agent-based models to enhance client agency is feasible and enriches the simulation of agent behaviors in complex markets; second, we find that even slight trade aversion encoded within the LLM leads to a complete cessation of trading activity, highlighting the sensitivity of market dynamics to agents' risk profiles; third, we show that incorporating human-like variability shifts power dynamics towards clients and can disproportionately affect the entire system, often resulting in systemic agent collapse across simulations. These findings underscore the emergent properties that arise when introducing stochastic, human-like decision processes, revealing new system behaviors that enhance the realism and complexity of artificial societies. |
| Date: | 2025–02 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2503.00320 |
| By: | Rath Minati; Date Hema |
| Abstract: | The integration of Quantum Deep Learning (QDL) techniques into the landscape of financial risk analysis presents a promising avenue for innovation. This study introduces a framework for credit risk assessment in the banking sector, combining quantum deep learning techniques with adaptive modeling for Row-Type Dependent Predictive Analysis (RTDPA). By leveraging RTDPA, the proposed approach tailors predictive models to different loan categories, aiming to enhance the accuracy and efficiency of credit risk evaluation. While this work explores the potential of integrating quantum methods with classical deep learning for risk assessment, it focuses on the feasibility and performance of this hybrid framework rather than claiming transformative industry-wide impacts. The findings offer insights into how quantum techniques can complement traditional financial analysis, paving the way for further advancements in predictive modeling for credit risk. |
| Date: | 2025–02 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2502.07806 |
| By: | Yanhao (Max); Wei; Zhenling Jiang |
| Abstract: | We study an alternative use of machine learning. We train neural nets to provide the parameter estimate of a given (structural) econometric model, for example, discrete choice or consumer search. Training examples consist of datasets generated by the econometric model under a range of parameter values. The neural net takes the moments of a dataset as input and tries to recognize the parameter value underlying that dataset. Besides the point estimate, the neural net can also output statistical accuracy. This neural net estimator (NNE) tends to limited-information Bayesian posterior as the number of training datasets increases. We apply NNE to a consumer search model. It gives more accurate estimates at lighter computational costs than the prevailing approach. NNE is also robust to redundant moment inputs. In general, NNE offers the most benefits in applications where other estimation approaches require very heavy simulation costs. We provide code at: https://nnehome.github.io. |
| Date: | 2025–02 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2502.04945 |
| By: | Jaskaran Singh Walia; Aarush Sinha; Srinitish Srinivasan; Srihari Unnikrishnan |
| Abstract: | Financial bond yield forecasting is challenging due to data scarcity, nonlinear macroeconomic dependencies, and evolving market conditions. In this paper, we propose a novel framework that leverages Causal Generative Adversarial Networks (CausalGANs) and Soft Actor-Critic (SAC) reinforcement learning (RL) to generate high-fidelity synthetic bond yield data for four major bond categories (AAA, BAA, US10Y, Junk). By incorporating 12 key macroeconomic variables, we ensure statistical fidelity by preserving essential market properties. To transform this market dependent synthetic data into actionable insights, we employ a finetuned Large Language Model (LLM) Qwen2.5-7B that generates trading signals (BUY/HOLD/SELL), risk assessments, and volatility projections. We use automated, human and LLM evaluations, all of which demonstrate that our framework improves forecasting performance over existing methods, with statistical validation via predictive accuracy, MAE evaluation(0.103%), profit/loss evaluation (60% profit rate), LLM evaluation (3.37/5) and expert assessments scoring 4.67 out of 5. The reinforcement learning-enhanced synthetic data generation achieves the least Mean Absolute Error of 0.103, demonstrating its effectiveness in replicating real-world bond market dynamics. We not only enhance data-driven trading strategies but also provides a scalable, high-fidelity synthetic financial data pipeline for risk & volatility management and investment decision-making. This work establishes a bridge between synthetic data generation, LLM driven financial forecasting, and language model evaluation, contributing to AI-driven financial decision-making. |
| Date: | 2025–02 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2502.17011 |
| By: | Yuan Liao; Xinjie Ma; Andreas Neuhierl; Linda Schilling |
| Abstract: | Machine learning in asset pricing typically predicts expected returns as point estimates, ignoring uncertainty. We develop new methods to construct forecast confidence intervals for expected returns obtained from neural networks. We show that neural network forecasts of expected returns share the same asymptotic distribution as classic nonparametric methods, enabling a closed-form expression for their standard errors. We also propose a computationally feasible bootstrap to obtain the asymptotic distribution. We incorporate these forecast confidence intervals into an uncertainty-averse investment framework. This provides an economic rationale for shrinkage implementations of portfolio selection. Empirically, our methods improve out-of-sample performance. |
| Date: | 2025–03 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2503.00549 |
| By: | Pierre Beaucoral |
| Abstract: | Analyzing development projects is crucial for understanding donors aid strategies, recipients priorities, and to assess development finance capacity to adress development issues by on-the-ground actions. In this area, the Organisation for Economic Co-operation and Developments (OECD) Creditor Reporting System (CRS) dataset is a reference data source. This dataset provides a vast collection of project narratives from various sectors (approximately 5 million projects). While the OECD CRS provides a rich source of information on development strategies, it falls short in informing project purposes due to its reporting process based on donors self-declared main objectives and pre-defined industrial sectors. This research employs a novel approach that combines Machine Learning (ML) techniques, specifically Natural Language Processing (NLP), an innovative Python topic modeling technique called BERTopic, to categorise (cluster) and label development projects based on their narrative descriptions. By revealing existing yet hidden topics of development finance, this application of artificial intelligence enables a better understanding of donor priorities and overall development funding and provides methods to analyse public and private projects narratives. |
| Date: | 2025–02 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2502.09495 |
| By: | Eric Hitz; Mingmin Feng; Radu Tanase; Ren\'e Algesheimer; Manuel S. Mariani |
| Abstract: | Recent advances in artificial intelligence have led to the proliferation of artificial agents in social contexts, ranging from education to online social media and financial markets, among many others. The increasing rate at which artificial and human agents interact makes it urgent to understand the consequences of human-machine interactions for the propagation of new ideas, products, and behaviors in society. Across two distinct empirical contexts, we find here that artificial agents lead to significantly faster and wider social contagion. To this end, we replicate a choice experiment previously conducted with human subjects by using artificial agents powered by large language models (LLMs). We use the experiment's results to measure the adoption thresholds of artificial agents and their impact on the spread of social contagion. We find that artificial agents tend to exhibit lower adoption thresholds than humans, which leads to wider network-based social contagions. Our findings suggest that the increased presence of artificial agents in real-world networks may accelerate behavioral shifts, potentially in unforeseen ways. |
| Date: | 2025–02 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2502.21037 |
| By: | Pedro Reis; Ana Paula Serra; Jo\~ao Gama |
| Abstract: | This review systematically examines deep learning applications in financial asset management. Unlike prior reviews, this study focuses on identifying emerging trends, such as the integration of explainable artificial intelligence (XAI) and deep reinforcement learning (DRL), and their transformative potential. It highlights new developments, including hybrid models (e.g., transformer-based architectures) and the growing use of alternative data sources such as ESG indicators and sentiment analysis. These advancements challenge traditional financial paradigms and set the stage for a deeper understanding of the evolving landscape. We use the Scopus database to select the most relevant articles published from 2018 to 2023. The inclusion criteria encompassed articles that explicitly apply deep learning models within financial asset management. We excluded studies focused on physical assets. This review also outlines our methodology for evaluating the relevance and impact of the included studies, including data sources and analytical methods. Our search identified 934 articles, with 612 meeting the inclusion criteria based on their focus and methodology. The synthesis of results from these articles provides insights into the effectiveness of deep learning models in improving portfolio performance and price forecasting accuracy. The review highlights the broad applicability and potential enhancements deep learning offers to financial asset management. Despite some limitations due to the scope of model application and variation in methodological rigour, the overall evidence supports deep learning as a valuable tool in this field. Our systematic review underscores the progressive integration of deep learning in financial asset management, suggesting a trajectory towards more sophisticated and impactful applications. |
| Date: | 2025–03 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2503.01591 |
| By: | Yung, Vincent (Northwestern University); Colyvas, Jeannette |
| Abstract: | Data wrangling is typically treated as an obligatory, codified, and ideally automated step in the machine learning pipeline. In contrast, we suggest that archival data wrangling is a theory-driven process best understood as a practical craft. Drawing on empirical examples from contemporary computational social science, we identify nine core modes of data wrangling. Although these modes can be seen as a sequence, we emphasize how they are iterative and nonlinear in practice. Moreover, we discuss how data wrangling can address issues of coded bias. Although machine learning emphasizes architectural engineering, we assert that to properly engage with machine learning is to properly engage with data wrangling. |
| Date: | 2023–08–18 |
| URL: | https://d.repec.org/n?u=RePEc:osf:socarx:2dve6_v1 |
| By: | Moustapha Pemy; Na Zhang |
| Abstract: | This paper studies the ubiquitous problem of liquidating large quantities of highly correlated stocks, a task frequently encountered by institutional investors and proprietary trading firms. Traditional methods in this setting suffer from the curse of dimensionality, making them impractical for high-dimensional problems. In this work, we propose a novel method based on stochastic optimal control to optimally tackle this complex multidimensional problem. The proposed method minimizes the overall execution shortfall of highly correlated stocks using a reinforcement learning approach. We rigorously establish the convergence of our optimal trading strategy and present an implementation of our algorithm using intra-day market data. |
| Date: | 2025–02 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2502.07868 |
| By: | Merfeld, Joshua David; Newhouse, David Locke |
| Abstract: | Reliable estimates of economic welfare for small areas are valuable inputs into the design and evaluation of development policies. This paper compares the accuracy of point estimates and confidence intervals for small area estimates of wealth and poverty derived from four different prediction methods: linear mixed models, Cubist regression, extreme gradient boosting, and boosted regression forests. The evaluation draws samples from unit-level household census data from four developing countries, combines them with publicly and globally available geospatial indicators to generate small area estimates, and evaluates these estimates against aggregates calculated using the full census. Predictions of wealth are evaluated in four countries and poverty in one. All three machine learning methods outperform the traditional linear mixed model, with extreme gradient boosting and boosted regression forests generally outperforming the other alternatives. The proposed residual bootstrap procedure reliably estimates confidence intervals for the machine learning estimators, with estimated coverage rates across simulations falling between 94 and 97 percent. These results demonstrate that predictions obtained using tree-based gradient boosting with a random effect block bootstrap generate more accurate point and uncertainty estimates than prevailing methods for generating small area welfare estimates. |
| Date: | 2023–03–08 |
| URL: | https://d.repec.org/n?u=RePEc:wbk:wbrwps:10348 |
| By: | Gerion Spielberger; Florian Artinger; Jochen Reb; Rudolf Kerschreiter |
| Abstract: | Analyzing textual data is the cornerstone of qualitative research. While traditional methods such as grounded theory and content analysis are widely used, they are labor-intensive and time-consuming. Topic modeling offers an automated complement. Yet, existing approaches, including LLM-based topic modeling, still struggle with issues such as high data preprocessing requirements, interpretability, and reliability. This paper introduces Agentic Retrieval-Augmented Generation (Agentic RAG) as a method for topic modeling with LLMs. It integrates three key components: (1) retrieval, enabling automatized access to external data beyond an LLM's pre-trained knowledge; (2) generation, leveraging LLM capabilities for text synthesis; and (3) agent-driven learning, iteratively refining retrieval and query formulation processes. To empirically validate Agentic RAG for topic modeling, we reanalyze a Twitter/X dataset, previously examined by Mu et al. (2024a). Our findings demonstrate that the approach is more efficient, interpretable and at the same time achieves higher reliability and validity in comparison to the standard machine learning approach but also in comparison to LLM prompting for topic modeling. These results highlight Agentic RAG's ability to generate semantically relevant and reproducible topics, positioning it as a robust, scalable, and transparent alternative for AI-driven qualitative research in leadership, managerial, and organizational research. |
| Date: | 2025–02 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2502.20963 |
| By: | Tianmi Ma; Jiawei Du; Wenxin Huang; Wenjie Wang; Liang Xie; Xian Zhong; Joey Tianyi Zhou |
| Abstract: | Recent advancements in large language models (LLMs) have significantly improved performance in natural language processing tasks. However, their ability to generalize to dynamic, unseen tasks, particularly in numerical reasoning, remains a challenge. Existing benchmarks mainly evaluate LLMs on problems with predefined optimal solutions, which may not align with real-world scenarios where clear answers are absent. To bridge this gap, we design the Agent Trading Arena, a virtual numerical game simulating complex economic systems through zero-sum games, where agents invest in stock portfolios. Our experiments reveal that LLMs, including GPT-4o, struggle with algebraic reasoning when dealing with plain-text stock data, often focusing on local details rather than global trends. In contrast, LLMs perform significantly better with geometric reasoning when presented with visual data, such as scatter plots or K-line charts, suggesting that visual representations enhance numerical reasoning. This capability is further improved by incorporating the reflection module, which aids in the analysis and interpretation of complex data. We validate our findings on NASDAQ Stock dataset, where LLMs demonstrate stronger reasoning with visual data compared to text. Our code and data are publicly available at https://github.com/wekjsdvnm/Agent-Tradi ng-Arena.git. |
| Date: | 2025–02 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2502.17967 |
| By: | Lett, Elle; La Cava, William |
| Abstract: | Machine learning (ML)-derived tools are rapidly being deployed as an additional input in the clinical decision-making process to optimize health interventions. However, ML models also risk propagating societal discrimination and exacerbating existing health inequities. The field of ML fairness has focused on developing approaches to mitigate bias in ML models. To date, the focus has been on the model fitting process, simplifying the processes of structural discrimination to definitions of model bias based on performance metrics. Here, we reframe the ML task through the lens of intersectionality, a Black feminist theoretical framework that contextualizes individuals in interacting systems of power and oppression, linking inquiry into measuring fairness to the pursuit of health justice. In doing so, we present intersectional ML fairness as a paradigm shift that moves from an emphasis on model metrics to an approach for ML that is centered around achieving more equitable health outcomes. |
| Date: | 2023–02–27 |
| URL: | https://d.repec.org/n?u=RePEc:osf:socarx:gu7yh_v1 |
| By: | Morande, Swapnil; Arshi, Tahseen; Gul, Kanwal; Amini, Mitra |
| Abstract: | This pioneering study employs machine learning to predict startup success, addressing the long-standing challenge of deciphering entrepreneurial outcomes amidst uncertainty. Integrating the multidimensional SECURE framework for holistic opportunity evaluation with AI's pattern recognition prowess, the research puts forth a novel analytics-enabled approach to illuminate success determinants. Rigorously constructed predictive models demonstrate remarkable accuracy in forecasting success likelihood, validated through comprehensive statistical analysis. The findings reveal AI’s immense potential in bringing evidence-based objectivity to the complex process of opportunity assessment. On the theoretical front, the research enriches entrepreneurship literature by bridging the knowledge gap at the intersection of structured evaluation tools and data science. On the practical front, it empowers entrepreneurs with an analytical compass for decision-making and helps investors make prudent funding choices. The study also informs policymakers to optimize conditions for entrepreneurship. Overall, it lays the foundation for a new frontier of AI-enabled, data-driven entrepreneurship research and practice. However, acknowledging AI’s limitations, the synthesis underscores the persistent relevance of human creativity alongside data-backed insights. With high predictive performance and multifaceted implications, the SECURE-AI model represents a significant stride toward an analytics-empowered paradigm in entrepreneurship management. |
| Date: | 2023–08–29 |
| URL: | https://d.repec.org/n?u=RePEc:osf:socarx:p3gyb_v1 |
| By: | Zhu, Jin; Wan, Runzhe; Qi, Zhengling; Luo, Shikai; Shi, Chengchun |
| Abstract: | This paper endeavors to augment the robustness of offline reinforcement learning (RL) in scenarios laden with heavy-tailed rewards, a prevalent circumstance in real-world applications. We propose two algorithmic frameworks, ROAM and ROOM, for robust off-policy evaluation and offline policy optimization (OPO), respectively. Central to our frameworks is the strategic incorporation of the median-of-means method with offline RL, enabling straightforward uncertainty estimation for the value function estimator. This not only adheres to the principle of pessimism in OPO but also adeptly manages heavytailed rewards. Theoretical results and extensive experiments demonstrate that our two frameworks outperform existing methods on the logged dataset exhibits heavytailed reward distributions. The implementation of the proposal is available at https://github.com/Mamba413/ROOM. |
| Keywords: | Rights Retention |
| JEL: | C1 |
| Date: | 2024–05–02 |
| URL: | https://d.repec.org/n?u=RePEc:ehl:lserod:122740 |
| By: | Verhagen, Mark D. |
| Abstract: | There is lively discussion regarding the potential and pitfalls of artificial intelligence (AI) and machine learning (ML) for public policy. This debate tends to focus on replacing human decision-making with (semi-)automated processes and the unique challenges such applications pose for policymakers and society more generally. As this paper argues, particularly ML could be used in a more direct and less controversial way: to improve policy analysis and inform evidence-based policymaking. ML methods can be used to identify sub-groups in a population that differ in their policy effect in a data-driven way, which might otherwise be missed in standard policy analysis. In doing so, a more complete picture of a policy’s impact on a population can be obtained. I illustrate how ML can complement our understanding of policy interventions by studying the nationwide 2015 decentralisation of the social domain in The Netherlands. This policy intervention delegated responsibilities to administer social care from the national to the municipal level. Using ML methods on entire population data in The Netherlands, I find the policy induced strongly heterogeneous effects that include evidence of local capture and strong urban/rural divides. Findings that are crucial for policymakers to assess whether the policy had the desired outcome. |
| Date: | 2023–03–16 |
| URL: | https://d.repec.org/n?u=RePEc:osf:socarx:qzm7y_v1 |
| By: | Daniel Brunstein (LISA - Laboratoire « Lieux, Identités, eSpaces, Activités » (UMR CNRS 6240 LISA) - CNRS - Centre National de la Recherche Scientifique - Università di Corsica Pasquale Paoli [Université de Corse Pascal Paoli]); Georges Casamatta (LISA - Laboratoire « Lieux, Identités, eSpaces, Activités » (UMR CNRS 6240 LISA) - CNRS - Centre National de la Recherche Scientifique - Università di Corsica Pasquale Paoli [Université de Corse Pascal Paoli]); Sauveur Giannoni (Università di Corsica Pasquale Paoli [Université de Corse Pascal Paoli], LISA - Laboratoire « Lieux, Identités, eSpaces, Activités » (UMR CNRS 6240 LISA) - CNRS - Centre National de la Recherche Scientifique - Università di Corsica Pasquale Paoli [Université de Corse Pascal Paoli]) |
| Abstract: | This study investigates the influence of Airbnb on property prices in Corsica. Leveraging machine learning techniques, we obtain more robust results than those achieved with conventional methods and uncover heterogeneous effects of Airbnb on property values. Our analysis reveals that a 1% increase in Airbnb listings leads to an average 0.21% rise in house prices. Interestingly, this effect is more pronounced in economically less developed regions, such as inland municipalities and remote seaside resorts, compared to traditionally popular tourist destinations and urban areas. |
| Keywords: | Short-term rental, Housing market, Machine learning, Heterogeneous effects |
| Date: | 2025 |
| URL: | https://d.repec.org/n?u=RePEc:hal:journl:hal-04934630 |
| By: | Iman Modarressi; Jann Spiess; Amar Venugopal |
| Abstract: | We propose a machine-learning tool that yields causal inference on text in randomized trials. Based on a simple econometric framework in which text may capture outcomes of interest, our procedure addresses three questions: First, is the text affected by the treatment? Second, which outcomes is the effect on? And third, how complete is our description of causal effects? To answer all three questions, our approach uses large language models (LLMs) that suggest systematic differences across two groups of text documents and then provides valid inference based on costly validation. Specifically, we highlight the need for sample splitting to allow for statistical validation of LLM outputs, as well as the need for human labeling to validate substantive claims about how documents differ across groups. We illustrate the tool in a proof-of-concept application using abstracts of academic manuscripts. |
| Date: | 2025–03 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2503.00725 |
| By: | Dirk Bergemann; Alessandro Bonatti; Alex Smolin |
| Abstract: | We develop an economic framework to analyze the optimal pricing and product design of Large Language Models (LLM). Our framework captures several key features of LLMs: variable operational costs of processing input and output tokens; the ability to customize models through fine-tuning; and high-dimensional user heterogeneity in terms of task requirements and error sensitivity. In our model, a monopolistic seller offers multiple versions of LLMs through a menu of products. The optimal pricing structure depends on whether token allocation across tasks is contractible and whether users face scale constraints. Users with similar aggregate value-scale characteristics choose similar levels of fine-tuning and token consumption. The optimal mechanism can be implemented through menus of two-part tariffs, with higher markups for more intensive users. Our results rationalize observed industry practices such as tiered pricing based on model customization and usage levels. |
| Date: | 2025–02 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2502.07736 |
| By: | Songrun He; Linying Lv; Asaf Manela; Jimmy Wu |
| Abstract: | Large language models are increasingly used in social sciences, but their training data can introduce lookahead bias and training leakage. A good chronologically consistent language model requires efficient use of training data to maintain accuracy despite time-restricted data. Here, we overcome this challenge by training chronologically consistent large language models timestamped with the availability date of their training data, yet accurate enough that their performance is comparable to state-of-the-art open-weight models. Lookahead bias is model and application-specific because even if a chronologically consistent language model has poorer language comprehension, a regression or prediction model applied on top of the language model can compensate. In an asset pricing application, we compare the performance of news-based portfolio strategies that rely on chronologically consistent versus biased language models and estimate a modest lookahead bias. |
| Date: | 2025–02 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2502.21206 |
| By: | Ruoyu Guo; Haochen Qiu |
| Abstract: | Making consistently profitable financial decisions in a continuously evolving and volatile stock market has always been a difficult task. Professionals from different disciplines have developed foundational theories to anticipate price movement and evaluate securities such as the famed Capital Asset Pricing Model (CAPM). In recent years, the role of artificial intelligence (AI) in asset pricing has been growing. Although the black-box nature of deep learning models lacks interpretability, they have continued to solidify their position in the financial industry. We aim to further enhance AI's potential and utility by introducing a return-weighted loss function that will drive top growth while providing the ML models a limited amount of information. Using only publicly accessible stock data (open/close/high/low, trading volume, sector information) and several technical indicators constructed from them, we propose an efficient daily trading system that detects top growth opportunities. Our best models achieve 61.73% annual return on daily rebalancing with an annualized Sharpe Ratio of 1.18 over 1340 testing days from 2019 to 2024, and 37.61% annual return with an annualized Sharpe Ratio of 0.97 over 1360 testing days from 2005 to 2010. The main drivers for success, especially independent of any domain knowledge, are the novel return-weighted loss function, the integration of categorical and continuous data, and the ML model architecture. We also demonstrate the superiority of our novel loss function over traditional loss functions via several performance metrics and statistical evidence. |
| Date: | 2025–02 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2502.17493 |
| By: | Hamid Moradi-Kamali; Mohammad-Hossein Rajabi-Ghozlou; Mahdi Ghazavi; Ali Soltani; Amirreza Sattarzadeh; Reza Entezari-Maleki |
| Abstract: | Financial Sentiment Analysis (FSA) traditionally relies on human-annotated sentiment labels to infer investor sentiment and forecast market movements. However, inferring the potential market impact of words based on their human-perceived intentions is inherently challenging. We hypothesize that the historical market reactions to words, offer a more reliable indicator of their potential impact on markets than subjective sentiment interpretations by human annotators. To test this hypothesis, a market-derived labeling approach is proposed to assign tweet labels based on ensuing short-term price trends, enabling the language model to capture the relationship between textual signals and market dynamics directly. A domain-specific language model was fine-tuned on these labels, achieving up to an 11% improvement in short-term trend prediction accuracy over traditional sentiment-based benchmarks. Moreover, by incorporating market and temporal context through prompt-tuning, the proposed context-aware language model demonstrated an accuracy of 89.6% on a curated dataset of 227 impactful Bitcoin-related news events with significant market impacts. Aggregating daily tweet predictions into trading signals, our method outperformed traditional fusion models (which combine sentiment-based and price-based predictions). It challenged the assumption that sentiment-based signals are inferior to price-based predictions in forecasting market movements. Backtesting these signals across three distinct market regimes yielded robust Sharpe ratios of up to 5.07 in trending markets and 3.73 in neutral markets. Our findings demonstrate that language models can serve as effective short-term market predictors. This paradigm shift underscores the untapped capabilities of language models in financial decision-making and opens new avenues for market prediction applications. |
| Date: | 2025–02 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2502.14897 |
| By: | Tanay Panat; Rohitash Chandra |
| Abstract: | The drastic changes in the global economy, geopolitical conditions, and disruptions such as the COVID-19 pandemic have impacted the cost of living and quality of life. It is important to understand the long-term nature of the cost of living and quality of life in major economies. A transparent and comprehensive living index must include multiple dimensions of living conditions. In this study, we present an approach to quantifying the quality of life through the Global Ease of Living Index that combines various socio-economic and infrastructural factors into a single composite score. Our index utilises economic indicators that define living standards, which could help in targeted interventions to improve specific areas. We present a machine learning framework for addressing the problem of missing data for some of the economic indicators for specific countries. We then curate and update the data and use a dimensionality reduction approach (principal component analysis) to create the Ease of Living Index for major economies since 1970. Our work significantly adds to the literature by offering a practical tool for policymakers to identify areas needing improvement, such as healthcare systems, employment opportunities, and public safety. Our approach with open data and code can be easily reproduced and applied to various contexts. This transparency and accessibility make our work a valuable resource for ongoing research and policy development in quality-of-life assessment. |
| Date: | 2025–02 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2502.06866 |
| By: | Shang Liu; Hanzhao Wang; Zhongyao Ma; Xiaocheng Li |
| Abstract: | Human-annotated preference data play an important role in aligning large language models (LLMs). In this paper, we investigate the questions of assessing the performance of human annotators and incentivizing them to provide high-quality annotations. The quality assessment of language/text annotation faces two challenges: (i) the intrinsic heterogeneity among annotators, which prevents the classic methods that assume the underlying existence of a true label; and (ii) the unclear relationship between the annotation quality and the performance of downstream tasks, which excludes the possibility of inferring the annotators' behavior based on the model performance trained from the annotation data. Then we formulate a principal-agent model to characterize the behaviors of and the interactions between the company and the human annotators. The model rationalizes a practical mechanism of a bonus scheme to incentivize annotators which benefits both parties and it underscores the importance of the joint presence of an assessment system and a proper contract scheme. From a technical perspective, our analysis extends the existing literature on the principal-agent model by considering a continuous action space for the agent. We show the gap between the first-best and the second-best solutions (under the continuous action space) is of $\Theta(1/\sqrt{n \log n})$ for the binary contracts and $\Theta(1/n)$ for the linear contracts, where $n$ is the number of samples used for performance assessment; this contrasts with the known result of $\exp(-\Theta(n))$ for the binary contracts when the action space is discrete. Throughout the paper, we use real preference annotation data to accompany our discussions. |
| Date: | 2025–02 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2502.06387 |
| By: | Leonardo Berti; Gjergji Kasneci |
| Abstract: | Stock Price Trend Prediction (SPTP) based on Limit Order Book (LOB) data is a fundamental challenge in financial markets. Despite advances in deep learning, existing models fail to generalize across different market conditions and struggle to reliably predict short-term trends. Surprisingly, by adapting a simple MLP-based architecture to LOB, we show that we surpass SoTA performance; thus, challenging the necessity of complex architectures. Unlike past work that shows robustness issues, we propose TLOB, a transformer-based model that uses a dual attention mechanism to capture spatial and temporal dependencies in LOB data. This allows it to adaptively focus on the market microstructure, making it particularly effective for longer-horizon predictions and volatile market conditions. We also introduce a new labeling method that improves on previous ones, removing the horizon bias. We evaluate TLOB's effectiveness using the established FI-2010 benchmark, which exceeds the state-of-the-art by an average of 3.7 F1-score(\%). Additionally, TLOB shows improvements on Tesla and Intel with a 1.3 and 7.7 increase in F1-score(\%), respectively. Additionally, we empirically show how stock price predictability has declined over time (-6.68 absolute points in F1-score(\%)), highlighting the growing market efficiencies. Predictability must be considered in relation to transaction costs, so we experimented with defining trends using an average spread, reflecting the primary transaction cost. The resulting performance deterioration underscores the complexity of translating trend classification into profitable trading strategies. We argue that our work provides new insights into the evolving landscape of stock price trend prediction and sets a strong foundation for future advancements in financial AI. We release the code at https://github.com/LeonardoBerti00/TLOB. |
| Date: | 2025–02 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2502.15757 |
| By: | Arandjelović, Ognjen |
| Abstract: | Purpose: The remarkable increase of sophistication of artificial intelligence in recent years has already led to its widespread use in martial applications, the potential of so-called ‘killer robots’ ceasing to be a subject of fiction. Approach: Virtually without exception, this potential has generated fear, as evidenced by a mounting number of academic articles calling for the ban on the development and deployment of lethal autonomous robots (LARs). In the present paper I start with an analysis of the existing ethical objections to LARs. Findings: My analysis shows the contemporary thought to be deficient in philosophical rigour, these deficiencies leading to an alternative thesis. Value: I advance a thesis that LARs can in fact be a force for peace, leading to fewer and less deadly wars. |
| Date: | 2023–03–23 |
| URL: | https://d.repec.org/n?u=RePEc:osf:socarx:9kja8_v1 |
| By: | Mahony, Christopher Brian; Manning, Matthew; Wong, Gabriel |
| Abstract: | Can the impact of justice processes be enhanced with the inclusion of a heterogeneous component into an existing cost-benefit analysis app that demonstrates how benefactors and beneficiaries are affected Such a component requires (i) moving beyond the traditional cost-benefit conceptual framework of utilizing averages, (ii) identification of social group or population-specific variation, (iii) identification of how justice processes differ across groups/populations, (iv) distribution of costs and benefits according to the identified variations, and (v) utilization of empirically informed statistical techniques to gain new insights from data and maximize the impact for beneficiaries. This paper outlines a method for capturing heterogeneity. The paper tests the method and the cost-benefit analysis online app that was developed using primary data collected from a developmental crime prevention intervention in Australia. The paper identifies how subgroups in the intervention display different behavioral adjustments across the reference period, revealing the heterogeneous distribution of costs and benefits. Finally, the paper discusses the next version of the cost-benefit analysis app, which incorporates an artificial intelligence-driven component that reintegrates individual cost-benefit analysis projects using machine learning and other modern data science techniques. The paper argues that the app enhances cost-benefit analysis, development outcomes, and policy making efficiency for optimal prioritization of criminal justice resources. Further, the app advances the policy accessibility of enhanced, social group-specific data, illuminating optimal policy orientation for more inclusive, just, and resilient societal outcomes—an approach with potential across broader public policy. |
| Date: | 2023–05–18 |
| URL: | https://d.repec.org/n?u=RePEc:wbk:wbrwps:10449 |
| By: | Hsin-Min Lu; Yu-Tai Chien; Huan-Hsun Yen; Yen-Hsiu Chen |
| Abstract: | Extracting specific items from 10-K reports remains challenging due to variations in document formats and item presentation. Traditional rule-based item segmentation approaches often yield suboptimal results. This study introduces two advanced item segmentation methods leveraging language models: (1) GPT4ItemSeg, using a novel line-ID-based prompting mechanism to utilize GPT4 for item segmentation, and (2) BERT4ItemSeg, combining BERT embeddings with a Bi-LSTM model in a hierarchical structure to overcome context window constraints. Trained and evaluated on 3, 737 annotated 10-K reports, BERT4ItemSeg achieved a macro-F1 of 0.9825, surpassing GPT4ItemSeg (0.9567), conditional random field (0.9818), and rule-based methods (0.9048) for core items (1, 1A, 3, and 7). These approaches enhance item segmentation performance, improving text analytics in accounting and finance. BERT4ItemSeg offers satisfactory item segmentation performance, while GPT4ItemSeg can easily adapt to regulatory changes. Together, they offer practical benefits for researchers and practitioners, enabling reliable empirical studies and automated 10-K item segmentation functionality. |
| Date: | 2025–02 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2502.08875 |
| By: | Montoya Munoz, Kelly Yelitza; Olivieri, Sergio Daniel; Silveira Braga, Cicero Augusto |
| Abstract: | Economists have long been interested in measuring the poverty and distributional impacts of macroeconomic projections and shocks. In this sense, microsimulation models have been widely used to estimate the distributional effects since they allow accounting for several transmission channels through which macroeconomic forecasts could impact individuals and households. This paper innovates previous microsimulation methodology by introducing more flexibility in labor earnings, considering intra-sectoral variation according to the formality status, and assessing its effect on forecasting country-level poverty, inequality, and other distributive indicators. The results indicate that the proposed methodology accurately estimates the intensity of poverty in the most immediate years indistinctively of how labor income is simulated. However, allowing for more intra-sectoral variation in labor income leads to more accurate projections in poverty and across the income distribution, with gains in performance in the middle term, especially in atypical years such as 2020. |
| Date: | 2023–06–22 |
| URL: | https://d.repec.org/n?u=RePEc:wbk:wbrwps:10497 |