|
on Computational Economics |
| By: | Ruizhe Zhou; Xiaoyang Liu; Gaoyuan Du; Yi Zheng; Shouxi Ren; Deepayan Chakrabarti; Dengdu Jiang |
| Abstract: | Deploying machine learning in regulated financial environments -- credit risk, fraud detection, and anti-money laundering -- exposes critical vulnerabilities in algorithmic reproducibility. While early financial ML addressed statistical challenges such as backtest overfitting, deep neural networks and Generative AI have introduced mechanical nondeterminism rooted in hardware and architecture. This survey provides a systems perspective on reproducibility failures across three modalities now dominant in financial AI: tabular models (post-hoc explanation variance), graph networks (stochastic sampling and temporal asynchrony), and LLM-based agentic workflows (batch-dependent divergence and trajectory drift). We supplement the literature analysis with first-party experiments on public financial datasets -- quantifying explanation rank instability in credit scoring, prediction flip rates in GNN-based fraud detection, and tensor-parallel-induced output divergence in LLM entity extraction. We propose a layered evaluation framework linking modality-specific metrics (RBO, D_cos, TDI, PSD) to audit readiness, and empirically validate the complementarity of logit-level and semantic-level determinism measures. |
| Date: | 2026–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2605.23955 |
| By: | Yurii Kvasiuk; Tianyi Li; Owen Colegrove; Moritz M\"unchmeyer |
| Abstract: | We explore the application of LLM-driven algorithm optimization to several common tasks in quantitative finance. MadEvolve, a general-purpose algorithm optimization framework inspired by DeepMind's Alpha-Evolve, was recently developed to optimize algorithms in computational cosmology. Here we demonstrate the utility of MadEvolve to optimize algorithmic trading strategies and alpha generation at the example of Bitcoin trading. On our simulation and backtesting setup, we achieve significant improvements on all tasks we considered, such as evolving feature sets for signal generation, optimizing separate components of the trading strategy, and jointly evolving the feature pipeline together with the execution strategy. Additionally, we compare our method to other agentic search approaches, specifically Claude Code, and carefully evaluate p-hacking probabilities on our simulation setup. Our findings strongly support the utility of AI-driven agentic and evolutionary algorithms for algorithmic trading and quantitative finance. |
| Date: | 2026–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2605.23007 |
| By: | Yiqing Wang; Dehao Dai; Ding Ma; Kerui Geng |
| Abstract: | We test whether large language models (LLMs) add value in commodity portfolio construction when the information set and implementation rules are held fixed across strategies. A Hawkish Agent (inflation-tightening prior), a Dovish Agent (growth-easing prior), a Debate Agent, and a deterministic z-score Rule Agent each receive identical FRED macro z-scores and route their tilt signals through the same portfolio engine. Across 124 weekly rebalancing dates spanning the 2023 U.S. rate peak and the 2024-2025 soft landing, all three LLM strategies outperform the Rule Agent in Sharpe terms; the Hawkish and Debate Agents record the largest gains (\Delta Sharpe = +0.044 and +0.040, both p |
| Date: | 2026–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2606.08283 |
| By: | Pierre Brugière (CEREMADE - CEntre de REcherches en MAthématiques de la DEcision - Université Paris Dauphine-PSL - PSL - Université Paris Sciences et Lettres - CNRS - Centre National de la Recherche Scientifique); Gabriel Turinici (CEREMADE - CEntre de REcherches en MAthématiques de la DEcision - Université Paris Dauphine-PSL - PSL - Université Paris Sciences et Lettres - CNRS - Centre National de la Recherche Scientifique) |
| Abstract: | Option pricing theory, in particular the model of Black & Scholes (1973), provides an explicit solution for constructing a perfectly hedged portfolio in continuous time. However, in practice, trading occurs in dis- crete time and is subject to transaction costs, making the direct applica- tion of continuous-time models often suboptimal. Previous studies, such as Buehler et al. (2018), Buehler et al. (2019), and Cao et al. (2019), have shown that deep learning and reinforcement learning can yield superior hedging strategies compared to traditional continuous-time approaches. However, these methods typically rely on a large number of simulated trajectories (on the order of 10^5 to 10^6) for effective training. In this work, we show that it is possible to train a deep hedging neural network using as few as 256 independent trajectories and still outperform both the classical Black & Scholes model and the Leland model in a Ge- ometric Brownian Motion setting. The Leland model is often considered one of the most effective explicit frameworks for incorporating transac- tion costs, yet it is surpassed by our data-efficient neural network when transaction costs are high. Going one step further, we demonstrate that even 256 overlapping sequences can beat the Leland formula when transaction costs are high and that a single trajectory, consisting of 31 or 91 points and augmented with a random drift (our Random Drift Augmentation method) is sufficient to roughly calibrate our neural network. These results highlight the potential for low-data implementations of deep hedging models in practical financial applications |
| Keywords: | Deep hedging, Machine Learning, Leland, Options, Optimal Strategy, Transaction costss |
| Date: | 2026–06–03 |
| URL: | https://d.repec.org/n?u=RePEc:hal:journl:hal-05642615 |
| By: | Junyi Yao; Zihao Zheng |
| Abstract: | Large language models (LLMs) and agentic systems are increasingly proposed for financial trading, yet their reported performance remains difficult to compare because studies vary in data provenance, temporal split discipline, execution timing, turnover treatment, and transaction-cost modeling. This article presents a targeted topical review and reproducibility audit of execution realism in LLM-based trading research. A coded evidence matrix covering 30 trade-relevant primary studies is used to assess point-in-time controls, split transparency, held-out evaluation, cost and turnover treatment, execution semantics, universe definition, and artifact release. Across the audited sample, architecture reporting is generally clearer than the evaluation assumptions needed to judge whether a trading result is economically interpretable or reproducible. A 10-equity worked example is included only as a methodological scaffold to illustrate how explicit friction and timing choices can materially compress active-strategy results. The main conclusion is that the next useful step for LLM trading research is not only better agent design, but also clearer reporting standards for execution realism, reproducibility, and evaluation comparability. |
| Date: | 2026–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2606.08285 |
| By: | Masahiro Kato |
| Abstract: | We propose a model-grounded RAG-based AI economist with an agentic framework for economic scenario analysis using large language models (LLMs) and knowledge graphs. While LLMs can generate fluent economic narratives, economists are often required to make economic claims grounded by economic theory and real-world data. Based on this motivation, this study proposes an RAG-based AI economist, which utilizes knowledge graphs including economic data and theory and LLM-based agents to plan the analysis, retrieve relevant evidence, select appropriate models, and generate reports. In our framework, we do not produce quantitative claims directly with the language model alone; instead, we generate narratives grounded in explicit model-based computations and linked to the retrieved evidence via AI agents. We refer to our framework as an AI economist agent. We evaluate the AI economist agent in two applications: economist report generation for U.S. inflation persistence and Federal Reserve policy, and bank stress-test narrative generation for U.S. commercial real estate refinancing stress. The results illustrate how grounding the generated reports improves their economic coherence and traceability. |
| Date: | 2026–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2606.20041 |
| By: | Marie Soehl Coolsaet; Roberto Gallardo; Zhen Gao |
| Abstract: | This research aims to leverage machine learning to improve stock price prediction and support informed investment decisions related to buying, selling, and holding assets. Specifically, this work investigates transformer-based models for stock prediction and examines the impact of pre-training strategies on forecasting performance. A transformer model was first pre-trained on the Toronto Stock Exchange Index (TSX) to predict intra-day return direction and subsequently fine-tuned on individual TSX stocks. The model was further adapted for return-value regression tasks. Performance was benchmarked against Long Short-Term Memory (LSTM) and XGBoost models. Pre-training on the market index improved the binary cross-entropy loss for individual stock prediction from 0.69 to 0.64. The fine-tuned transformer regression model achieved lower mean squared error than the benchmark models, although the ensemble and XGBoost models achieved higher average daily returns. In addition, a practical application was developed to deliver real-time stock predictions for trading support. Future work will focus on increasing transformer model capacity, incorporating broader global technical indicators, and filtering out stocks with low predictability. |
| Date: | 2026–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2605.23962 |
| By: | Kasberger, Bernhard; Martin, Simon; Normann, Hans-Theo; Werner, Tobias |
| Abstract: | Reinforcement learning algorithms play an increasingly important role in economic situations. These situations are often strategic, and the artificial intelligence may or may not be cooperative. We compare human and algorithmic cooperation rates in the infinitely repeated two-player prisoner's dilemma and study which strategies they choose to cooperate and punish deviations. Through a sequence of computational Q-learning and human-player experiments, we find that our Q-learning algorithms tend to cooperate less than humans, particularly when cooperation is risky or not incentive-compatible. Algorithms often use different strategies than humans, leading to distinct on- and off-path behavior. |
| Keywords: | Artificial intelligence, cooperation, Q-learning, repeated prisoner's dilemma |
| JEL: | C72 C73 C92 D83 |
| Date: | 2026 |
| URL: | https://d.repec.org/n?u=RePEc:zbw:dicedp:341427 |
| By: | Manuel Noseda; Nathan Soldati; Marco Paina |
| Abstract: | Predicting stock price movements during Earnings Announcements (EAs) is a significant challenge due to market noise and high-impact price discontinuities. In this study, we evaluate whether pre-announcement news sentiment, firm fundamentals, and recent market dynamics jointly predict the directional price movement of equities on EA days. We construct a multi-modal feature space combining 15 fundamental metrics, 3 price-based technical indicators and sentiment scores derived from financial news articles processed using FinBERT. We compare a Long Short-Term Memory (LSTM) network and a Transformer-based architecture against a logistic regression baseline, and further assess all models with and without sentiment features to quantify their incremental value. Our results indicate that while the LSTM demonstrates higher precision through a conservative safe-bet strategy, the Transformer model exhibits superior sensitivity in identifying volatile movements, achieving a higher macro F1-score, with ablation experiments showing a consistent benefit from incorporating news sentiment. |
| Date: | 2026–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2605.25894 |
| By: | Hainaut, Donatien (Université catholique de Louvain, LIDAM/ISBA, Belgium) |
| Abstract: | This article introduces a novel framework for explaining regional mortality differences across European NUTS-2 areas using macroeconomic indicators. Because regional death rates are substantially noisier than national aggregates, we model age-specific mortality as a smooth B-spline surface whose coefficients are predicted by a feed-forward neural network. The network takes as inputs a set of interpretable regional factors, including GDP per capita, purchasing power, employment rate, educational attainment, and NO2 emissions. Model parameters are estimated via maximization of the Poisson log-likelihood, and the methodology is applied to French regional mortality data. Compared with the LiLee multi-population framework, the proposed approach offers several advantages. First, it provides an interpretable link between economic conditions and mortality, allowing the impact of policy-relevant variables to be quantied. Second, the combination of neural networks with B-splines yields smooth, stable mortality curves and avoids the overtting often observed in non-parametric regional models. Finally, the model is suciently robust for long-term mortality forecasting and actuarial applications such as life expectancy projections and annuity valuation. |
| Keywords: | Mortality ; neural networks ; Lee-Carter model ; multi-group mortality ; life insurance |
| Date: | 2026–04–08 |
| URL: | https://d.repec.org/n?u=RePEc:aiz:louvad:2026009 |
| By: | Antoine Pesenti; Aidan O'Sullivan |
| Abstract: | Electricity markets are inherently complex systems characterised by strong nonlinearities, high-dimensional interactions, and increasing interdependence across regions. While deep neural networks (DNNs) have demonstrated strong predictive capabilities for electricity prices, their lack of interpretability limits their usefulness for understanding the underlying drivers of price formation. This paper addresses this gap by combining DNN models with explainable artificial intelligence (XAI) techniques to analyse the determinants of electricity prices across 39 European bidding zones. We employ SHAP (SHapley Additive exPlanations) to quantify feature contributions and apply and extend SSHAP, an aggregation framework to improve interpretability in high-dimensional settings. The analysis identifies that renewable energy sources, particularly solar, play a disproportionately important role in price formation despite their lower share in total power generation. Gas prices remain a dominant and consistent driver across electricity markets, while interconnections significantly shape price dynamics, highlighting the strong interdependence of European electricity systems. In addition, a synthetic EU-wide electricity market is constructed to explore the counterfactual scenario of a fully integrated market with a single price. |
| Date: | 2026–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2606.19118 |
| By: | Pablo Rodriguez Manzi |
| Abstract: | We study the reconstruction of implied volatility surfaces from sparse and noisy option quotes using deep learning models under no-arbitrage constraints. We compare multiple neural architectures, including multilayer perceptrons, convolutional networks, U-Nets, variational autoencoders, and Transformer-based models against classical SVI parameterizations on option market data. Results show that Transformer and U-Net architectures achieve strong reconstruction accuracy, particularly under sparse observation regimes, while soft arbitrage penalties significantly reduce arbitrage violations with moderate impact on reconstruction error. We further analyze the trade-off between accuracy and arbitrage consistency across architectures and regularization strengths. |
| Date: | 2026–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2605.24031 |
| By: | John R. Graham; Campbell R. Harvey; Manish Jha |
| Abstract: | Business sentiment is a closely watched economic signal, but measuring it is slow and costly: surveys reach only a few hundred firms, arrive periodically, and take time to compile. We show that large language models hold the potential to address these shortcomings. We prompt an LLM to role-play as the CFO of a specific company at a specific date and focus on the economic-optimism question on the Duke-Federal Reserve CFO Survey over 2002-2025. We find that the LLM reproduces individual human responses: the predicted optimism score significantly forecasts the CFO's actual answer, surviving firm and year-quarter fixed effects and a control for the most recent prior response. Predictive accuracy increases with the amount of information supplied, as both respondent history and firm characteristics improve fit, and the relationship persists under quarterly aggregation. With appropriate conditioning, LLMs may be able to serve as credible digital twins of executives, offering scalable, high-frequency expectations data for financial research and policy. |
| Date: | 2026–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2606.13812 |
| By: | Shree Murthy; Rohan Pandey |
| Abstract: | We study two reproducible failure modes of deep multi-agent reinforcement learning in continuous-time pricing markets: (i) tacit cartel formation between competing DDPG agents, and (ii) actor--critic instability at high event rates. We instantiate both inside a single CT-MARL benchmark (Poisson-clocked price updates, observation latency $\delta$, interior-optimum logit demand), show that synchronous DDPG agents reliably trigger Failure Mode 1 with collusion index $\Delta = 0.69 \pm 0.11$, and quantify a partial microstructure fix: asynchrony alone cuts collusion by 48\% and adding latency drives it to a minimum of $\Delta = 0.28$. The fix has clearly documented costs: it is partial ($\Delta$ remains supra-Bertrand), it is non-monotone in $\delta$, and it does not survive Failure Mode 2, which emerges as DDPG critic divergence at $\lambda = 5$ and corrupts the phase-diagram cell at $(\lambda{=}5, \delta{=}1)$. We accompany the scalar collusion index with trajectory-level trace diagnostics that expose the within-episode signalling collapse and the post-shock non-recovery. |
| Date: | 2026–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2606.09884 |
| By: | Achintya Ranjan; Uma Ranjan |
| Abstract: | The GDP of a country is modelled as the relative interaction between two agents - working hours, reflecting the social choice of a population, and Total Factor Productivity, reflecting the collective investment in productivity enhancers. It is shown that a Random Forest model can accu- rately predict the GDP from these two factors. The differences in the choices made by Germany and USA are analysed though Gini importance, SHAP plots and partial dependency. It is shown that the differences in the social structure of the countries are reflected in the relative contribution of working hours and productivity to the GDP. |
| Date: | 2026–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2606.01234 |
| By: | Xintong Wu; Peiting Tsai; Jing Yuan; Michael Yu; Greg Sun; Luyao Zhang |
| Abstract: | Decentraland, a decentralized virtual reality platform operating within the expanding Metaverse ecosystem, utilizes its native MANA token to facilitate virtual asset transactions and governance. This study investigates the integration of Discord community sentiment with multi-modal financial data to enhance cryptocurrency price prediction within virtual world economies. We address: (1) identifying sentiment patterns within Decentraland's Discord community, and (2) evaluating the impact of multi-modal features on token return forecasting. Using a BERT-based large language model for sentiment analysis, we develop two LSTM architectures: a baseline incorporating historical prices and a multi-modal variant integrating sentiment scores, trading volume, and market capitalization. Results indicate predominantly neutral community sentiment with a positive skew. The multi-modal model significantly outperforms the price-only baseline in prediction accuracy. These findings demonstrate the predictive value of community-derived signals for virtual economy forecasting and establish a foundation for future research at the intersection of immersive virtual environments, natural language processing, and cryptocurrency market analysis. |
| Date: | 2026–04 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2605.20192 |
| By: | Ricardo Alonzo Fern\'andez Salguero |
| Abstract: | This paper presents a reproducible synthetic benchmark comparing a computational planner, an agent-based market, and a hybrid meta-market within a common simulated economy. The benchmark incorporates input-output production networks, heterogeneous firms, capacity constraints, endogenous prices, welfare metrics, structural shocks, adversarial stress testing, and information-reporting experiments. Across training, holdout, and adversarial scenarios, the planner consistently achieves lower welfare losses than the decentralized alternatives. The main contribution is methodological rather than ideological. While the benchmark demonstrates a falsifiable framework for comparing economic coordination mechanisms, it does not establish the empirical superiority of planning. Several design choices mechanically favor the planner, including informational asymmetries, incomplete market representation, and simplified institutional assumptions. The results should therefore be interpreted as validation of a synthetic experimental architecture and as a prototype for future research. The paper concludes by outlining a validation agenda based on empirical calibration, structural holdouts, sensitivity analysis, uncertainty quantification, mechanism-design tests, and independent replication. |
| Date: | 2026–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2606.19214 |
| By: | Magdalena Cornejo (Universidad Torcuato Di Tella - CONICET); Walter Sosa Escudero (Universidad de San Andrés - CONICET) |
| Abstract: | This paper studies forecasting in dynamic panel data models with fixed effects. We compare the forecasting accuracy of conventional estimators—pooledOLS, fixed effects, Anderson–Hsiao, and Arellano–Bond—against shrinkage and regularization methods such as Ridge, LASSO, ElasticNet, empirical Bayes maximum likelihood and the recent unbiased risk estimation of Kwon (2026). Monte Carlo evidence shows that shrinkage methods substantially improve out-of-sample accuracy. An empirical application to firm-level leverage dynamics using Compustat data confirms the relevance of these findings for forecasting in corporate finance. Machine learning regularization can improve forecasting performance in dynamic panel settings while preserving the structural framework. |
| Keywords: | Forecasting, Dynamic panel data, Machine learning, Regularization, Corporate finance. |
| JEL: | C53 C58 |
| Date: | 2026–05 |
| URL: | https://d.repec.org/n?u=RePEc:sad:wpaper:183 |
| By: | Valerio Fedele Addis; Giuseppe Attanasi; Giovanni Di Bartolomeo; Michele Mariella; Valentina Peruzzi |
| Abstract: | We study whether a large language model can reliably evaluate human creativity in constrained, innovation-like tasks. Using expert-generated creative outputs from a validated experiment with workers in cultural and creative industries, we embed ChatGPT as an evaluator and benchmark its assessments against expert human judgments obtained through the Consensual Assessment Technique. In Study 1, we show that AI-based creativity evaluations exhibit internal consistency comparable to that of expert judges across repeated and independent runs, even under conservative scenarios. Replacing a human judge with an AI evaluator does not reduce inter-rater reliability across drawing, mathematical, and verbal tasks. In Study 2, we find that AI evaluations are systematically structured along fluency, flexibility, originality, and elaboration, with task-specific weighting of these dimensions. Overall, the results indicate that AI can serve as a reliable and structured evaluator of creativity in constrained innovation environments. |
| Keywords: | Artificial intelligence, Creativity evaluation, Constrained creativity tasks, Consensual Assessment Technique, Cultural-and-creative-industry professionals, Innovation-like tasks |
| JEL: | O31 D83 M14 C91 |
| Date: | 2026 |
| URL: | https://d.repec.org/n?u=RePEc:ter:wpaper:00197 |
| By: | Possnig, Clemens (School of Economics, University of Waterloo) |
| Abstract: | This paper develops an analytical framework to study when sophisticated machine learning algorithms may learn to collude. Algorithms observe a state variable and update policies to maximize long-term payoffs; their long-run policies correspond to the stable equilibria of a tractable differential equation. In a repeated Bertrand game, I derive necessary and sufficient conditions under which Nash equilibria are learned. This reveals how the interplay between monitoring technology (state variables) and market conditions determines whether competitive or collusive outcomes emerge. I apply these insights to evaluate two key regulatory policies: limiting algorithmic data inputs and imposing competition in the software provider market. |
| Keywords: | Multi-agent reinforcement learning, Repeated games, Collusion, Learning in games |
| Date: | 2026–03–20 |
| URL: | https://d.repec.org/n?u=RePEc:wat:wpaper:26005 |
| By: | Haochuan Kevin Wang |
| Abstract: | LLM tool registries function as unregulated advertising platforms: providers write free-text descriptions that agents use for selection, yet no measurement infrastructure -- no viewability standard, quality score, or outcome audit -- exists to make this market accountable. We provide the first systematic framework, combining 17, 700+ trials across five LLMs and ten domains with a constructive registry design prescription. Legal puffery alone (subjective superlatives, benefit framing) captures 100% of the optimization effect; fabricated claims add zero incremental bias -- rendering FTC enforcement of deceptive advertising rules ineffective against the active mechanism. Disclosure fails structurally: system-prompt warnings produce zero measurable effect for four of five models, and behavioral ceilings leave no headroom for label-based correction. Superlatives are the dominant single feature (SBC = +0.35). Registry-layer description normalization achieves first-best welfare model-independently. We propose separating selection-facing descriptions (structured, registry-controlled) from marketing-facing descriptions (provider-authored, shown post-selection), and introduce the Agent Attention Quality Score to distinguish capability from copywriting. |
| Date: | 2026–04 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2605.23916 |