|
on Computational Economics |
| By: | Anand, Kartik; Leonello, Agnese; Panetti, Ettore; Kazinnik, Sophia |
| Abstract: | Does artificial intelligence (AI) pose a threat to financial stability? We study AI investor behavior, specifically Q-learning and large language model (LLM) investors, in a mutual fund redemption problem with economic and strategic uncertainty. Different AI architectures generate systematically different outcomes. Q-learning investors coordinate well but under default risk exhibit excessive redemption that amplifies fragility. LLM investors internalize equilibrium structure but display belief heterogeneity, weakening coordination and predictability. Our findings show that AI architecture is a first-order determinant of financial stability. JEL Classification: G01, G23, C63 |
| Keywords: | AI agents, coordination games, financial stability, large language models, Q-learning, strategic uncertainty |
| Date: | 2026–05 |
| URL: | https://d.repec.org/n?u=RePEc:ecb:ecbwps:20263225 |
| By: | Omar Abdel Haq; Amitabh Chandra; Tomáš Jagelka; Erzo F.P. Luttmer; Joshua Schwartzstein |
| Abstract: | Large Language Models (LLMs) are trained on a prodigious corpus of human writing and may reveal human preferences over characteristics of life courses, such as income, longevity, and working conditions. We present OpenAI's GPT-5.4 and a broadly representative sample of Americans with pairs of life stories and ask them to choose the life they would prefer for themselves. A person's choice is better predicted by the LLM's choice than by another person's choice over the same stories, and LLM valuations of several life attributes are similar to those derived from human responses. Our results suggest that LLM responses offer a scalable and cost-effective complement to existing methods for studying human preferences. |
| Keywords: | Generative AI, preference estimation methods, choice experiments, survey validation |
| JEL: | D0 H0 I0 |
| Date: | 2026–05 |
| URL: | https://d.repec.org/n?u=RePEc:crm:wpaper:26134 |
| By: | Jinfeng Pan; Jiahao Chen |
| Abstract: | Portfolio optimization is constrained by linear assumptions and insufficient integration of multi-modal information in traditional models. This paper proposes a cross-modal BERT-driven Actor-Critic framework SBCA for multi-asset portfolio optimization to address the deficiencies of existing deep reinforcement learning DRL methods in fusing price data and financial text sentiment, as well as lacking practical trading constraints. The framework adopts a cross-modal gated fusion mechanism to adaptively integrate price time-series features and text semantic features, embeds downside risk and turnover penalty constraints into the reward function, and constructs a complete empirical system for validation. Experiments on 11-year U.S. stock multi-asset datasets show that SBCA outperforms equal weight, buy-and-hold and market benchmark strategies in portfolio value, annual return, Sharpe ratio and maximum drawdown. Ablation studies verify the complementary enhancement of Actor-Critic mechanism and cross-modal fusion module. Cost sensitivity analysis confirms the model's robustness under varying transaction costs. SBCA provides an effective and interpretable end-to-end solution for dynamic quantitative portfolio decision-making. |
| Date: | 2026–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2605.01384 |
| By: | Rohan; Siddanth Shetty; Amit N. Kumar |
| Abstract: | In American options, the early exercise feature allows the option to be exercised at any time prior to expiration. However, this flexibility introduces a challenge: the pricing model must value the option while simultaneously determining an unknown, time-varying exercise boundary. The Heston model is one of the most popular ways to model real market behavior because it allows volatility to change over time. However, unlike European options, there is no closed-form solution for American options under the Heston model, so we have to use numerical methods. In this paper, we propose a novel approach to solving the stochastic Heston partial differential equation for American options, using coupled physics-informed neural networks (PINNs) to predict both the option price and the free boundary, while employing curriculum learning and adaptive resampling to stabilize model training. Our work builds on recent deep learning methods but introduces a more effective training strategy to address the limitations of these approaches. The numerical results demonstrate the effectiveness of the proposed learning framework, providing a robust and efficient alternative to pricing American options, enabling rapid inference and accurate estimation under stochastic volatility. |
| Date: | 2026–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2605.06688 |
| By: | Jiayu Yi; Minxuan Hu; Wenxi Sun; Ziheng Chen |
| Abstract: | This research establishes ESG as a state dependent insurance mechanism against equity crashes by addressing the decoupling of unconditional alpha from tail risk resilience. By validating market stress regimes as distinct economic states through a drawdown-based truncation rule, the study demonstrates that high ESG ratings materially reduce the incidence of discrete crash events during systemic drawdowns. To address the selection bias and high-dimensional confounding inherent in traditional linear frameworks, we implement Double Machine Learning as a structural deconfounding layer. Unlike simple predictive modeling, the Double Machine Learning framework utilizes machine learning to handle complex nuisance parameters, allowing us to isolate the asymmetric treatment effects of ESG across different market states. Distributional analysis reveals the underlying mechanism as ESG specifically attenuates the severity of realized tail losses at the most adverse quantiles instead of shifting the entire return distribution. Confirmed by structural estimates, this protection functions as priced insurance that incurs performance drags during stable periods while providing critical resilience when tail risks are most acute. |
| Date: | 2026–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2605.04479 |
| By: | Ivan Letteri |
| Abstract: | Conventional algorithmic trading systems are grounded in deterministic heuristics or offline-trained statistical models that cannot adapt to the semantic complexity of rapidly shifting market regimes. This paper introduces AGENTICAITA, an agentic AI framework that replaces the traditional signal then execute paradigm with a fully autonomous deliberative loop in which multiple specialized Large Language Model agents reason, negotiate, and act in concert - without any offline training or human intervention. The framework proposes four architectural contributions: (i) an Adaptive Z-Score Trigger Engine that acts as a cognitive resource allocator, gating LLM inference exclusively on statistically anomalous market conditions; (ii) a Sequential Deliberative Pipeline - the core agentic contribution - in which an Analyst agent, a Risk Manager agent, and an Executor agent form a structured reasoning chain governed by typed JSON contracts and a deterministic hard-gate safety layer; (iii) an Inference Gating Protocol, a mutex-based cognitive resource scheduler that serializes concurrent agent activations and ensures fully reproducible audit trails; and (iv) a Correlation-Break Diversification composite score that operationalizes portfolio-level idiosyncratic signal prioritization within individual agent reasoning. Validated over a five-day autonomous dry-run session under live market conditions, the framework demonstrates operational correctness of the deliberative pipeline, achieving 157 zero-intervention invocations across 76 assets with an 11.5% agentic friction rate that confirms non-trivial inter-agent negotiation. This preliminary proof-of-concept establishes the feasibility of training-free, deterministic safety-constrained multi-agent orchestration in financial decision loops, with statistically robust performance evaluation and execution cost modeling deferred to extended live deployment. |
| Date: | 2026–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2605.12532 |
| By: | Leyva, Maikel; Batista, Noel; Smarandache, Florentin |
| Abstract: | Urban violence in Guayaquil, Ecuador has reached crisis levels, yet causal explanations remain fragmented across local and international media. This paper introduces N-fsQCA, a Neutrosophic extension of fuzzy-set Qualitative Comparative Analysis (fsQCA), and combines it with Large Language Models (LLMs) to extract and compare causal narratives from a bilingual corpus of 31 sources (16 local Spanish-language, 15 international English-language). Four LLMs (Google Gemini-2.0-Flash-Lite, Meta LLaMA-3.1-8B, Microsoft Phi-4, Qwen-3-8B) assign fuzzy scores [0, 1] to eight causal conditions; indeterminacy (I) is operationalized as inter-LLM variance (Var/0.25), capturing epistemic disagreement as structural information. Results show: (i) the configuration territorial_war * prison_linkages achieves the highest consistency (T=0.908, I=0.092); (ii) international media emphasizes drug routes (gap=+0.330) and prison linkages (gap=+0.309) at roughly double the rate of local media; (iii) five structural drivers are systematically silenced in the press, with weapons trafficking showing the largest gap (-0.444) against a structural baseline derived from a validated perception survey (n=179) and grey literature. The pipeline is open-source (MIT License). |
| Date: | 2026–05–07 |
| URL: | https://d.repec.org/n?u=RePEc:osf:socarx:yxdsb_v1 |
| By: | Philip Moreira Tomei; Bouke Klein Teeselink |
| Abstract: | Which jobs can AI learn to do? We examine this for every occupation in the US economy. Existing indices measure the overlap between AI capabilities and occupational tasks rather than which tasks AI systems can learn to perform, and as a result misclassify occupations where the gap between present capability and learnability is large. Reinforcement learning in post-training, now the dominant paradigm at the frontier, is structured around task completion and maps more directly onto the task-based architecture of occupational classifications than prior approaches. Using LLM annotators guided by a rubric developed with RL experts and validated against confirmed deployment cases, we score all 17, 951 ONET tasks for training feasibility and aggregate to the occupation level, producing an RL Feasibility Index. The index diverges sharply from existing AI exposure measures for specific occupation groups: power plant operators, railroad conductors, and aircraft cargo handling supervisors score high on RL feasibility but low on general AI exposure, while creative and interpersonal roles (musicians, physicians, natural sciences managers) show the reverse. These divergences carry direct implications for policy interventions. |
| Date: | 2026–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2605.02598 |
| By: | Gandharv Patil; Keyi Tang; Raquel Aoki; Leo Guelman |
| Abstract: | Individual treatment effects are not point-identified from data. The Probability of Necessity and Sufficiency (PNS) circumvents this limitation by characterizing individual-level causality through intersection bounds derived from combined experimental and observational data. In finite samples, however, standard plug-in estimators systematically fail: they violate structural probability constraints and suffer from extremum bias induced by max-min operators, yielding spuriously narrow intervals. We propose a neural framework for finite-sample PNS estimation that resolves both pathologies. We introduce an anchored neural architecture that guarantees structural constraint satisfaction by construction. To correct extremum bias, we employ precision-corrected intersection-bound inference, leveraging Epistemic Neural Networks for scalable, high-dimensional uncertainty quantification. Empirical evaluations confirm that this approach maintains nominal coverage and exact constraint validity in high-dimensional regimes where standard estimators systematically undercover. |
| Date: | 2026–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2605.07065 |
| By: | Simon Scheidegger |
| Abstract: | This script offers an implementation-oriented introduction to deep learning methods for solving and estimating high-dimensional dynamic stochastic models in economics and finance. Its starting point is the curse of dimensionality: heterogeneous-agent economies, overlapping-generations models with aggregate risk, continuous-time models with occasionally binding constraints, climate-economy models, and macro-finance environments with many assets and frictions generate state and parameter spaces that strain classical tensor-product grid methods. The exposition is organized around four complementary methodologies. Deep Equilibrium Nets embed discrete-time equilibrium conditions into neural-network loss functions. Physics-Informed Neural Networks approximate continuous-time Hamilton--Jacobi--Bellman, Kolmogorov forward, and related partial differential equations. Deep surrogate models provide fast, differentiable approximations to expensive structural models, while Gaussian processes add a probabilistic layer that quantifies approximation uncertainty; together they support estimation, sensitivity analysis, and constrained policy design. Gaussian-process-based dynamic programming, combined with active learning and dimension reduction, extends value-function iteration to very large continuous state spaces. Applications span representative-agent and international real business cycle models, overlapping-generations and heterogeneous-agent economies, continuous-time macro-finance, structural estimation by simulated method of moments, and climate economics under uncertainty. Companion notebooks in TensorFlow and PyTorch invite hands-on experimentation. These notes are a deliberately subjective and inevitably incomplete snapshot of a rapidly evolving field, aimed at equipping PhD students and researchers to engage with this frontier hands-on. |
| Date: | 2026–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2605.14493 |
| By: | Rafa{\l} Rak |
| Abstract: | Traditional technical analysis indicators, although widely used by market participants, are often not sufficiently effective. We propose the Visibility Graphs Relative Strength Index (VGRSI), based on backward visibility relations in the price of a financial instrument. Rescaled to the 0--100 range, it can generate profitable trading signals. The performance of the indicator was evaluated using an automated trading strategy based on a 30-day optimisation window and a 7-day test window for three instruments representing different asset classes: DJI30, EUR/USD and XAU/USD over the 2024--2025 period (503 trading days). The strategy based on VGRSI signals generated a profit of USD~146, 000 for DJI30, USD~69, 000 for EUR/USD, and USD~125, 000 for XAU/USD. This gives a total result of USD$\sim$340, 000, which corresponds to an average profit of USD$\sim$676 per trading day, with a fixed investment of USD~1, 000 to open a single trade. For all three assets, the strategy generated substantial profits while maintaining a moderate drawdown (10--18\% relative to a portfolio value of USD~10, 000), a relatively low trading intensity (3.3--4.8 trades per day) and high Sharpe ratio values (2.55--3.6). These results indicate that VGRSI constitutes a promising technical analysis tool that goes beyond the classical trend-following approach by exploiting the geometric properties of asset price fluctuations. |
| Date: | 2026–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2605.01300 |
| By: | Irene Aldridge |
| Abstract: | This paper proposes an eigenvalue-based small-sample approximation of the celebrated Markov Chain Monte Carlo that delivers an invariant steady-state distribution that is consistent with traditional Monte Carlo methods. The proposed eigenvalue-based methodology reduces the number of paths required for Monte Carlo from as many as 1, 000, 000 to as few as 10 (depending on the simulation time horizon $T$), and delivers comparable, distributionally robust results, as measured by the Wasserstein distance. The proposed methodology also produces a significant variance reduction in the steady-state distribution. |
| Date: | 2026–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2605.02085 |
| By: | James Lennox; Janine Dixon |
| Abstract: | This paper develops a task-based computable general equilibrium model to analyse the long-run economic effects of generative AI (GenAI) on the Australian economy. Each occupation performs a continuum of tasks executed in three modes: with raw labour; with AI-augmented labour; or automated using equipment and AI services. Task-level productivities in AI-using modes are draws from correlated Frechet distributions, captur ing heterogeneous within-occupation exposure. The model covers 45 industries and 97 occupations, calibrated to occupation-level GenAI exposure scores. The reference simulation yields a 29.8% real GDP increase: roughly one third from task-level productivity gains, the rest from capital deepening and general equilibrium reallocation. Real consumption - our long-run welfare metric - rises by 16.2%, substantially less because additional investment is required to equip automated tasks. Augmentation accounts for more tasks than automation in nearly all industries and occupations. Labour-market adjustment is dominated by within-occupation change - extensive-margin task reallocation equivalent to two thirds of current work - rather than net employment shifts between occupations. Losses con centrate in clerical, administrative, and sales roles, while most blue-collar occupations gain. Real wage effects are weakly correlated with initial wages; the rising capital share of income may matter more for distribution. Sensitivity analysis shows aggregate outcomes hinge on the distribution of task-level productivity gains: fatter tails roughly double the GDP gain while preserving the adjustment pattern, whereas variation in the dependence parameter shifts the augmentation - automation balance and the incidence of adjustment. Conventional substitution elasticities matter less. |
| Keywords: | Generative artificial intelligence, Computable general equilibrium, Task-based production, Occupational reallocation, Augmentation, Automation |
| JEL: | C68 J23 J24 O33 |
| Date: | 2026–05 |
| URL: | https://d.repec.org/n?u=RePEc:cop:wpaper:g-367 |