|
on Computational Economics |
| By: | Andrea Macr\`i; Sebastian Jaimungal; Fabrizio Lillo |
| Abstract: | Reinforcement Learning (RL) applied to financial problems has been the subject of a lively area of research. The use of RL for optimal trading strategies that exploit latent information in the market is, to the best of our knowledge, not widely tackled. In this paper we study an optimal trading problem, where a trading signal follows an Ornstein-Uhlenbeck process with regime-switching dynamics. We employ a blend of RL and Recurrent Neural Networks (RNN) in order to make the most at extracting underlying information from the trading signal with latent parameters. The latent parameters driving mean reversion, speed, and volatility are filtered from observations of the signal, and trading strategies are derived via RL. To address this problem, we propose three Deep Deterministic Policy Gradient (DDPG)-based algorithms that integrate Gated Recurrent Unit (GRU) networks to capture temporal dependencies in the signal. The first, a one -step approach (hid-DDPG), directly encodes hidden states from the GRU into the RL trader. The second and third are two-step methods: one (prob-DDPG) makes use of posterior regime probability estimates, while the other (reg-DDPG) relies on forecasts of the next signal value. Through extensive simulations with increasingly complex Markovian regime dynamics for the trading signal's parameters, as well as an empirical application to equity pair trading, we find that prob-DDPG achieves superior cumulative rewards and exhibits more interpretable strategies. By contrast, reg-DDPG provides limited benefits, while hid-DDPG offers intermediate performance with less interpretable strategies. Our results show that the quality and structure of the information supplied to the agent are crucial: embedding probabilistic insights into latent regimes substantially improves both profitability and robustness of reinforcement learning-based trading strategies. |
| Date: | 2025–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2511.00190 |
| By: | Lampe, Max; Adalid, Ramón |
| Abstract: | Monetary aggregates provide valuable information about the monetary policy transmission and the business cycle. This paper applies machine learning methods, namely Learning Vector Quantisation (LVQ) and its distinction-sensitive extension (DSLVQ), to identify turning points in euro area M1 and M3. We benchmark performance against the Bry–Boschan algorithm and standard classifiers. Our results show that LVQ detects M1 turning points with only a three-month delay, halving the six-month confirmation lag of Bry–Boschan dating. DSLVQ delivers comparable accuracy while offering interpretability: it assigns weights to the sources of broad money growth, showing that lending to households and firms, as well as Eurosystem asset purchases when present, are the main drivers of turning points in M3. The findings are robust across parameter choices, bootstrap designs, alternative performance metrics, and comparator models. These results demonstrate that machine learning can yield more timely and interpretable signals from monetary aggregates. For policymakers, this approach enhances the information set available for assessing near-term economic dynamics and understanding the transmission of monetary policy. JEL Classification: E32, E51, C63 |
| Keywords: | machine learning, monetary aggregates, turning points |
| Date: | 2025–11 |
| URL: | https://d.repec.org/n?u=RePEc:ecb:ecbwps:20253148 |
| By: | Nikolas Anic (Swiss Finance Institute - University of Zurich; Finreon); Andrea Barbon (University of St. Gallen; University of St.Gallen); Ralf Seiz (University of St.Gallen; Finreon); Carlo Zarattini (Concretum Group) |
| Abstract: | This paper investigates whether large language models (LLMs) can improve cross-sectional momentum strategies by extracting predictive signals from firm-specific news. We combine daily U.S. equity returns for S&P 500 constituents with high-frequency news data and use prompt-engineered queries to ChatGPT that inform the model when a stock is about to enter a momentum portfolio. The LLM evaluates whether recent news supports a continuation of past returns, producing scores that condition both stock selection and portfolio weights. An LLM-enhanced momentum strategy outperforms a standard longonly momentum benchmark, delivering higher Sharpe and Sortino ratios both in-sample and in a truly out-of-sample period after the model's pre-training cutoff. These gains are robust to transaction costs, prompt design, and portfolio constraints, and are strongest for concentrated, high-conviction portfolios. The results suggest that LLMs can serve as effective real-time interpreters of financial news, adding incremental value to established factor-based investment strategies. |
| Keywords: | Large Language Models, Momentum Investing, Textual Analysis, News Sentiment, Artificial Intelligence |
| Date: | 2025–10 |
| URL: | https://d.repec.org/n?u=RePEc:chf:rpseri:rp2594 |
| By: | Haofei Yu; Fenghai Li; Jiaxuan You |
| Abstract: | Large language models (LLMs) achieve strong performance across benchmarks--from knowledge quizzes and math reasoning to web-agent tasks--but these tests occur in static settings, lacking real dynamics and uncertainty. Consequently, they evaluate isolated reasoning or problem-solving rather than decision-making under uncertainty. To address this, we introduce LiveTradeBench, a live trading environment for evaluating LLM agents in realistic and evolving markets. LiveTradeBench follows three design principles: (i) Live data streaming of market prices and news, eliminating dependence on offline backtesting and preventing information leakage while capturing real-time uncertainty; (ii) a portfolio-management abstraction that extends control from single-asset actions to multi-asset allocation, integrating risk management and cross-asset reasoning; and (iii) multi-market evaluation across structurally distinct environments--U.S. stocks and Polymarket prediction markets--differing in volatility, liquidity, and information flow. At each step, an agent observes prices, news, and its portfolio, then outputs percentage allocations that balance risk and return. Using LiveTradeBench, we run 50-day live evaluations of 21 LLMs across families. Results show that (1) high LMArena scores do not imply superior trading outcomes; (2) models display distinct portfolio styles reflecting risk appetite and reasoning dynamics; and (3) some LLMs effectively leverage live signals to adapt decisions. These findings expose a gap between static evaluation and real-world competence, motivating benchmarks that test sequential decision making and consistency under live uncertainty. |
| Date: | 2025–11 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2511.03628 |
| By: | Felipe Valencia-Clavijo |
| Abstract: | Large language models (LLMs) are increasingly examined as both behavioral subjects and decision systems, yet it remains unclear whether observed cognitive biases reflect surface imitation or deeper probability shifts. Anchoring bias, a classic human judgment bias, offers a critical test case. While prior work shows LLMs exhibit anchoring, most evidence relies on surface-level outputs, leaving internal mechanisms and attributional contributions unexplored. This paper advances the study of anchoring in LLMs through three contributions: (1) a log-probability-based behavioral analysis showing that anchors shift entire output distributions, with controls for training-data contamination; (2) exact Shapley-value attribution over structured prompt fields to quantify anchor influence on model log-probabilities; and (3) a unified Anchoring Bias Sensitivity Score integrating behavioral and attributional evidence across six open-source models. Results reveal robust anchoring effects in Gemma-2B, Phi-2, and Llama-2-7B, with attribution signaling that the anchors influence reweighting. Smaller models such as GPT-2, Falcon-RW-1B, and GPT-Neo-125M show variability, suggesting scale may modulate sensitivity. Attributional effects, however, vary across prompt designs, underscoring fragility in treating LLMs as human substitutes. The findings demonstrate that anchoring bias in LLMs is robust, measurable, and interpretable, while highlighting risks in applied domains. More broadly, the framework bridges behavioral science, LLM safety, and interpretability, offering a reproducible path for evaluating other cognitive biases in LLMs. |
| Date: | 2025–11 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2511.05766 |
| By: | John Armstrong; Cristin Buescu; James Dalby; Rohan Hobbs |
| Abstract: | We use a neural network to identify the optimal solution to a family of optimal investment problems, where the parameters determining an investor's risk and consumption preferences are given as inputs to the neural network in addition to economic variables. This is used to develop a practical tool that can be used to explore how pension outcomes vary with preference parameters. We use a Black-Scholes economic model so that we may validate the accuracy of network using a classical and provably convergent numerical method developed using the duality approach. |
| Date: | 2025–11 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2511.07045 |
| By: | Singhal, Mohit |
| Abstract: | Background: The U.S. opioid epidemic imposes a persistent and disproportionate economic burden on payers and communities, driven by complex interactions among clinical utilization, pharmacy benefit management (PBM) policies, and social determinants of health (SDOH). Despite extensive research on overdose and prescribing risk, few studies have quantified the cost burden of opioid use or examined how policy and community-level factors jointly shape it. Objective: This study develops an interpretable, machine-learning framework integrating PBM cost levers and SDOH indicators to predict and explain county-level variation in opioid-related spending from 2013–2023. The goal is to identify structural drivers of cost, simulate potential savings under policy and social interventions, and support data-driven resource allocation. Methods: Using CMS Medicare Part D data linked with County Health Rankings and U.S. Census indicators, a Random Forest regression model was trained on ten years of county-level data (≈3, 000 counties, 2013–2023). Key predictors included unemployment, income ratio, obesity, smoking, provider density, and PBM variables such as cost per claim and opioid prescribing rate. Model interpretability was achieved through SHAP (SHapley Additive exPlanations) analysis and policy simulations testing both PBM and SDOH interventions. Results: The model achieved high predictive accuracy (R² ≈ 0.97), explaining nearly all observed variation in opioid cost per capita. SHAP analysis revealed unemployment, mental-health-provider density, and income inequality as dominant drivers, while provider access and preventive-care variables exerted cost-mitigating effects. Simulated PBM levers (e.g., formulary tightening, utilization management) reduced predicted costs by 4–6%, while integrated SDOH improvements (e.g., +20% behavioral-health access, +10% primary care) achieved up to 17% savings—equivalent to approximately $23 billion nationally. The combined model demonstrated both statistical robustness and policy relevance. Conclusion: This study reframes the opioid crisis through an economic and structural lens, demonstrating that predictive modeling can translate public-health and PBM data into actionable fiscal insights. The proposed PBM–SDOH integration provides a scalable, transparent framework for targeting interventions in high-burden counties, optimizing healthcare spending, and informing evidence-based opioid policy. Keywords: Opioid costs, pharmacy benefit management, social determinants of health, Medicare Part D, machine learning, SHAP, predictive modeling, public health economics, health policy |
| Date: | 2025–10–28 |
| URL: | https://d.repec.org/n?u=RePEc:osf:socarx:c7rvx_v1 |
| By: | Panagiotis G. Papaioannou; Athanassios N. Yannacopoulos |
| Abstract: | We introduce a Geometry Informed Model for financial forecasting by embedding high dimensional market data onto constant curvature 2manifolds. Guided by the uniformization theorem, we model market dynamics as Brownian motion on spherical S2, Euclidean R2, and hyperbolic H2 geometries. We further include the torus T, a compact, flat manifold admissible as a quotient space of the Euclidean plane anticipating its relevance for capturing cyclical dynamics. Manifold learning techniques infer the latent curvature from financial data, revealing the torus as the best performing geometry. We interpret this result through a macroeconomic lens, the torus circular dimensions align with endogenous cycles in output, interest rates, and inflation described by IS LM theory. Our findings demonstrate the value of integrating differential geometry with data-driven inference for financial modeling. |
| Date: | 2025–11 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2511.05030 |
| By: | Sofía Balladares (Universitat de Barcelona & IEB); Esteban García-Miralles (Banco de España) |
| Abstract: | Fiscal drag arises when nominal tax parameters remain unchanged despite nominal income growth, thereby increasing effective tax rates and revenue. We use Spanish administrative tax records and a detailed microsimulation model to examine fiscal drag in personal income taxation through two complementary approaches. First, we estimate tax-to-base elasticities to assess the progressivity of the tax system and potential fiscal drag under homogeneous income growth. We uncover significant heterogeneity in elasticities across income sources, across the individual income distribution and in the underlying mechanisms. Second, we conduct counterfactual simulations to quantify the actual impact of fiscal drag from 2019 to 2023, finding it accounts for about a third of revenue growth. Our findings offer insights for public finance modelling, revenue forecasting, and tax policy design. |
| Keywords: | Inflation, taxes, progressivity, indexation, bracket creep |
| JEL: | D31 E62 H24 |
| Date: | 2025 |
| URL: | https://d.repec.org/n?u=RePEc:ieb:wpaper:doc2025-08 |
| By: | Jian'an Zhang |
| Abstract: | We propose ARBITER, a risk-neutral neural operator for learning joint SPX-VIX term structures under no-arbitrage constraints. ARBITER maps market states to an operator that outputs implied volatility and variance curves while enforcing static arbitrage (calendar, vertical, butterfly), Lipschitz bounds, and monotonicity. The model couples operator learning with constrained decoders and is trained with extragradient-style updates plus projection. We introduce evaluation metrics for derivatives term structures (NAS, CNAS, NI, Dual-Gap, Stability Rate) and show gains over Fourier Neural Operator, DeepONet, and state-space sequence models on historical SPX and VIX data. Ablation studies indicate that tying the SPX and VIX legs reduces Dual-Gap and improves NI, Lipschitz projection stabilizes calibration, and selective state updates improve long-horizon generalization. We provide identifiability and approximation results and describe practical recipes for arbitrage-free interpolation and extrapolation across maturities and strikes. |
| Date: | 2025–11 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2511.06451 |
| By: | Bryan T. Kelly (Yale SOM; AQR Capital Management, LLC; National Bureau of Economic Research (NBER)); Semyon Malamud (Ecole Polytechnique Federale de Lausanne; Centre for Economic Policy Research (CEPR); Swiss Finance Institute) |
| Abstract: | Recent papers have challenged certain aspects of the "virtue of complexity" described by Kelly et al. (2024b) (KMZ) and related work. These challenges ultimately have little bearing on the theoretical arguments or empirical findings of KMZ. They do, however, provide a valuable opportunity to better understand the nuanced behavior of complex models. In addition to responding to recent challenges, we provide detailed discussions of how complex models learn in small samples, the roles of "nominal" and "effective" complexity, the unique effects of implicit regularization, and the importance of limits to learning. We then present new empirical and theoretical analyses that expand on KMZ. Finally, we introduce and demonstrate the virtue of ensemble complexity. |
| Keywords: | Portfolio choice, machine learning, random matrix theory, benign overfit |
| JEL: | C58 C61 G11 G12 G14 |
| Date: | 2025–07 |
| URL: | https://d.repec.org/n?u=RePEc:chf:rpseri:rp2596 |
| By: | Ding, Liangping; Lawson, Cornelia; Shapira, Philip (The University of Manchester) |
| Abstract: | Artificial intelligence (AI) promises to transform science by accelerating knowledge discovery, automating processes, and introducing new paradigms for research. However, there remains a limited understanding of how AI is being utilized in scientific research. In this paper, we develop a framework based on GPT-4 and SciBERT to identify AI’s role in scientific papers, differentiating between Foundational, Adaptation, Tool and Discussion modes of AI research. This allows us to capture AI’s diverse contributions, from theoretical advances to practical applications and critical analysis. We examine AI’s trajectory across these modes by analyzing time series, field-specific, and country trends. This approach expands on search-term based identification of AI contributions and offers insights into how AI is being deployed in science. |
| Date: | 2025–11–02 |
| URL: | https://d.repec.org/n?u=RePEc:osf:socarx:7ed2b_v1 |
| By: | Mahdi Goldani |
| Abstract: | The policy environment of countries changes rapidly, influencing macro-level indicators such as the Energy Security Index. However, this index is only reported annually, limiting its responsiveness to short-term fluctuations. To address this gap, the present study introduces a daily proxy for the Energy Security Index and applies it to forecast energy security at a daily frequency.The study employs a two stage approach first, a suitable daily proxy for the annual Energy Security Index is identified by applying six time series similarity measures to key energy related variables. Second, the selected proxy is modeled using the XGBoost algorithm to generate 15 day ahead forecasts, enabling high frequency monitoring of energy security dynamics.As the result of proxy choosing, Volume Brent consistently emerged as the most suitable proxy across the majority of methods. The model demonstrated strong performance, with an R squared of 0.981 on the training set and 0.945 on the test set, and acceptable error metrics . The 15 day forecast of Brent volume indicates short term fluctuations, with a peak around day 4, a decline until day 8, a rise near day 10, and a downward trend toward day 15, accompanied by prediction intervals.By integrating time series similarity measures with machine learning based forecasting, this study provides a novel framework for converting low frequency macroeconomic indicators into high frequency, actionable signals. The approach enables real time monitoring of the Energy Security Index, offering policymakers and analysts a scalable and practical tool to respond more rapidly to fast changing policy and market conditions, especially in data scarce environments. |
| Date: | 2025–11 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2511.05556 |
| By: | Erhan Bayraktar; Qi Feng; Zecheng Zhang; Zhaoyu Zhang |
| Abstract: | We propose a deep neural-operator framework for a general class of probability models. Under global Lipschitz conditions on the operator over the entire Euclidean space-and for a broad class of probabilistic models-we establish a universal approximation theorem with explicit network-size bounds for the proposed architecture. The underlying stochastic processes are required only to satisfy integrability and general tail-probability conditions. We verify these assumptions for both European and American option-pricing problems within the forward-backward SDE (FBSDE) framework, which in turn covers a broad class of operators arising from parabolic PDEs, with or without free boundaries. Finally, we present a numerical example for a basket of American options, demonstrating that the learned model produces optimal stopping boundaries for new strike prices without retraining. |
| Date: | 2025–11 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2511.07235 |
| By: | Cansu Isler |
| Abstract: | Accurate forecasting of downside risks to economic growth is critically important for policymakers and financial institutions, particularly in the wake of recent economic crises. This paper extends the Growth-at-Risk (GaR) approach by introducing a novel daily sentiment indicator derived from textual analysis of mandatory corporate disclosures (SEC 10-K and 10-Q reports) to forecast downside risks to economic growth. Using the Loughran--McDonald dictionary and a word-count methodology, I compute firm-level tone growth as the year-over-year difference between positive and negative sentiment expressed in corporate filings. These firm-specific sentiment metrics are aggregated into a weekly tone index, weighted by firms' market capitalizations to capture broader, economy-wide sentiment dynamics. Integrated into a mixed-data sampling (MIDAS) quantile regression framework, this sentiment-based indicator enhances the prediction of GDP growth downturns, outperforming traditional financial market indicators such as the National Financial Conditions Index (NFCI). The findings underscore corporate textual data as a powerful and timely resource for macroeconomic risk assessment and informed policymaking. |
| Date: | 2025–11 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2511.04935 |