|
on Computational Economics |
| By: | Xiaohong Chen (Yale University); Luis Hoderlein (Yale University); Jonas Lieber (Imperial College London) |
| Abstract: | The "deep learning revolution" has led to remarkable success of neural networks in applications across a wide range of fields, such as computer vision, speech recognition, natural language processing, code generation, protein structure prediction, image and video generation, and dynamic control. This review introduces neural networks to economists. Recent advances and challenges in approximation theory, neural network architecture, computation, econometric theory and practice are presented. Finally, we survey the rapidly evolving applications of modern neural networks and Large Language Models in economic research. |
| Date: | 2026–06–01 |
| URL: | https://d.repec.org/n?u=RePEc:cwl:cwldpp:2539 |
| By: | Fernández-Villaverde, Jesús; Nuño, Galo; Perla, Jesse |
| Abstract: | We argue that deep learning provides a promising avenue for taming the curse of dimensionality in quantitative economics. We begin by exploring the unique challenges posed by solving dynamic equilibrium models, especially the feedback loop between individual agents' decisions and the aggregate consistency conditions required by equilibrium. Following this, we introduce deep neural networks and demonstrate their application by solving the stochastic neoclassical growth model. Next, we compare deep neural networks with traditional solution methods in quantitative economics. We conclude with a survey of neural network applications in quantitative economics and offer reasons for cautious optimism. |
| Keywords: | Deep learning |
| JEL: | C61 C63 E27 |
| Date: | 2024–11 |
| URL: | https://d.repec.org/n?u=RePEc:cpr:ceprdp:19636 |
| By: | Alice Treesa M; Dr. Arpita Choudhary (Assistant Professor, Madras School of Economics, Chennai, India.) |
| Abstract: | Reliable energy consumption forecasting in the short term is essential for improving building operations efficiency and creating sustainable energy consumption plans. The authors of this study evaluate the forecasting performance of machine learning and deep learning methods which use climate data and time data to predict energy usage at hourly intervals. The study used Linear Regression, Decision Trees, Random Forest, XGBoost and Long Short-Term Memory as comparison methods to assess performance in the same context. The study demonstrated that energy consumption forecasting accuracy depends more on selected features than on the model's complexity. The study found that LSTM model learning capacity remained stable while Random Forest model performance showed superior results in dealing with non-linear features that had temporal attributes. |
| Keywords: | Energy Consumption Prediction, Machine Learning, Ensemble Models, LSTM Model, Feature Engineering, Sustainable Energy Managementsemantics, Neural architectures |
| JEL: | Q47 C53 C45 C38 L94 Q41 |
| Date: | 2026–05 |
| URL: | https://d.repec.org/n?u=RePEc:mad:wpaper:2026-301 |
| By: | Ramit Das (Cadence); Purbita Jana (Assistant Professor and Chair of M.Sc. Data Science Programme, Madras School of Economics, Chennai, India.) |
| Abstract: | Neural networks achieve strong empirical performance, yet their architectural semantics and compositional structure remain difficult to analyse formally. This paper develops a logical–topological framework for reasoning about neural network architectures independently of learning dynamics. Focusing on the ART/LAPART family as a canonical testbed in which bidirectional interaction and stability are ex-plicit, we provide a semantic interpretation of excitation relations using geometric logic and topological systems. We extend the classical setting to fuzzy and frame-valued semantics in order to capture graded and potentially incomparable activation strengths. With this extension we show that we express SHAP - a Neural Network Explainability methodology. The contribution is foundational: it clarifies how ar-chitectural causal structure can be represented, compared, and composed. While the technical development centres on ART and LAPART, the framework isolates structural principles—compositionality, graded influence, and continuity—that can be extend to modern deep neural network architectures. |
| Keywords: | Geometric logic, Topological systems, Neural network semantics, Adaptive Resonance Theory, LAPART, Fuzzy topology, Explainable AI, SHAP values, Frame-valued semantics, Neural architectures |
| JEL: | C02 C45 C63 C65 D83 |
| Date: | 2026–05 |
| URL: | https://d.repec.org/n?u=RePEc:mad:wpaper:2026-300 |
| By: | Domenico Delli Gatti; Andrea Coletta; Aldo Glielmo; Filippo Gusella; Enrico Maria Turco; Alessia Lo Turco |
| Abstract: | In canonical macroeconomic agent-based model (ABM), firms pursue behavioural (non-optimal) price and quantity strategies, that take the form of heuristics. In this paper we incorporate reinforcement learning (RL) into an otherwise standard ABM by replacing a fraction of heuristic-using firms with RL agents that learn profitmaximizing strategies through repeated interaction with the economic environment. When RL agents adopt a shared Q-function, they endogenously converge to one of three distinct strategic regimes – market power, predatory pricing, or quasi-perfect competition – with the prevailing equilibrium depending on the degree of market competition and the share of RL agents. Under independent Q-functions, agents spontaneously segregate into heterogeneous strategies, yielding higher aggregate market power and producer surplus without explicit coordination. The prevalence of RL agents shapes aggregate output and volatility in a non-monotonic way. To rationalize these findings, we develop a stylized theoretical framework that links the competition intensity between RL and non-RL agents with the prevailing optimal pricing strategies. |
| Keywords: | macroeconomics, agent-based modelling, reinforcement learning |
| JEL: | C63 D21 E37 L13 |
| Date: | 2026 |
| URL: | https://d.repec.org/n?u=RePEc:ces:ceswps:_12862 |
| By: | Geofrey Ntale |
| Abstract: | Large Language Models (LLMs) have emerged as powerful tools for processing the heterogeneous information environments of modern financial markets. This paper presents a systematic, comparative evaluation of five prominent LLMs: GPT-4 Turbo, Claude 3 Opus, Gemini 1.5 Pro, Llama 3 70B, and the domain-specialized FinGPT, with respect to their capacity for technical market analysis. The evaluation spans four structured tasks: candlestick pattern recognition from OHLCV data, directional signal generation (BUY/SELL/HOLD), backtesting of signal quality through a simulated execution pipeline, and financial report comprehension. Our experimental framework employs rigorous quantitative metrics, including Sharpe ratio, maximum drawdown, Sortino ratio, information coefficient, F1-score, and BLEU score. Findings from simulated backtesting indicate that GPT-4 Turbo achieves the highest annualized return and Sharpe ratio among general-purpose models, while FinGPT demonstrates competitive risk-adjusted performance due to domain-specific fine-tuning. Both models outperform a passive S&P 500 benchmark under the tested conditions. The study identifies persistent failure modes across all evaluated models, including numerical hallucination, context-window limitations, and inconsistent performance in sideways market regimes. We conclude that while LLMs hold genuine promise within AI trading systems, robust deployment requires careful task decomposition, rigorous backtesting protocols, and domain-aware fine-tuning strategies. |
| Date: | 2026–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2607.15414 |
| By: | Abdukakhkhor Abdurakhmonov (Central Bank of Uzbekistan) |
| Abstract: | This paper provides the first systematic assessment of machine learning methods for macroeconomic forecasting in Uzbekistan. Using a comprehensive dataset of more than 170 indicators, we forecast CPI inflation and GDP growth with nine machine learning models and compare them against three traditional benchmarks (ARIMA, VAR, and BVAR). For both targets, the relative performance of machine learning improves as the forecast horizon increases. For inflation, machine learning provides clear and growing gains as the horizon increases, and a simple equal-weighted ensemble of the machine learning models is the most accurate approach overall, achieving the lowest forecast error at nearly every horizon. For GDP growth, by contrast, the traditional benchmarks (ARIMA in particular) remain the most accurate across most horizons, although regularized linear and dimension-reduction machine learning methods are competitive at short horizons. Tree-based models struggle to forecast GDP when growth exceeds the range observed during training because they cannot extrapolate beyond the training data. This limitation is particularly relevant in Uzbekistan's rapidly changing economy, where rapid economic growth in 2024-2025 pushed the level of GDP beyond the range observed in the training sample. We show that forecasting stationary transformations of the target largely removes this weakness. Overall, the findings suggest that machine learning is best used to complement rather than replace the existing forecasting toolkit. It improves the accuracy of medium-term inflation forecasts, whereas traditional models remain more accurate for forecasting GDP. |
| Keywords: | Machine Learning; Macroeconomic Forecasting; Ination; GDP Growth; Model Evaluation and Selection; Uzbekistan |
| JEL: | C22 C45 C53 E31 E37 E52 |
| Date: | 2026–08–03 |
| URL: | https://d.repec.org/n?u=RePEc:gii:giihei:heidwp19-2026 |
| By: | Andrew Ellis; Michele Piccione; Shengxing Zhang |
| Abstract: | We introduce a framework for studying the equilibrium effects of machine learning. Agents process information using a Chow and Liu (1968) tree, a widely-used machine learning procedure that admits a closed-form solution. We apply the model to an asset market with dispersed information based on Hellwig (1980). The price mechanism fails to aggregate the information extracted by the algorithm, even approximately. While there are partial equilibrium benefits from access to algorithms, the equilibrium price aggregates less information than the rational equilibrium. Equilibrium typically features diverse world-models, demands, and utilities, even with ex ante identical agents. |
| Date: | 2026–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2607.13670 |
| By: | Junyu Chen; Tom Boot; Lingwei Kong; Weining Wang |
| Abstract: | Conditional Value-at-Risk (CoVaR) quantifies systemic financial risk by measuring the loss quantile of one asset, conditional on another asset experiencing distress. We develop a Transformer-based methodology that integrates financial news articles directly with market data to improve CoVaR estimates. Unlike approaches that use predefined sentiment scores, our method incorporates raw text embeddings generated by a large language model (LLM). We prove explicit error bounds for our Transformer CoVaR estimator, showing that accurate CoVaR learning is possible even with small datasets. Using U.S. market returns and Reuters news items from 2006–2013, our out-of-sample results show that textual information impacts the CoVaR forecasts. With better predictive performance, we identify a pronounced negative dip during market stress periods across several equity assets when comparing the Transformer-based CoVaR to both the CoVaR without text and the CoVaR using traditional sentiment measures. Our results show that textual data can be used to effectively model systemic risk without requiring prohibitively large data sets. |
| Date: | 2026–01–30 |
| URL: | https://d.repec.org/n?u=RePEc:bri:uobdis:26/840 |
| By: | Minyu Shen; Weihua Gu; Junqi Ma; Boqian Song; Li Zhen; Gang Kou |
| Abstract: | Improving boarding efficiency reduces airplane turnaround time and improves passenger experience. Airlines typically assign passengers to a few sequential boarding groups using static seat-based rules. Yet arrivals, seat choices, and luggage are sequential and random, and a static rule ignores the seats earlier passengers have already taken. We propose the first dynamic formulation of boarding group assignment. As each passenger checks in, we observe earlier passengers' seats and groups, the current passenger's seat, and optional luggage information, then assign a group while keeping companions together. We formulate dynamic group assignment as a Markov decision process and solve it with reinforcement learning (RL). The policy uses a convolutional neural network to encode the checked-in seat-assignment state and is trained by proximal policy optimization. The reward balances total boarding time and average individual boarding time. We benchmark the proposed RL policy against three companion-compatible static policies (back-to-front, modified Steffen, and alternating block) in an in-house simulator covering six single- and double-aisle layouts. Back-to-front with optimized group sizes achieves the shortest total boarding time and average individual boarding time among the static benchmarks across all layouts. The dynamic RL policy further outperforms it on both metrics in every layout. On a representative case, the RL policy outperforms the optimal back-to-front by up to 9.8\% in total boarding time and 22.8\% in average individual time. Sweeping the reward weight yields an approximate Pareto frontier for operator choice. Trained policies remain robust under out-of-distribution operating conditions, including varying load factors, companion sizes, and luggage loads. |
| Date: | 2026–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2607.21512 |
| By: | Prashanth BS; Manoj Kumar; Ariful Hoque; Nasser Al Muraqab; Immanuel Azaad Moonesar; Udo Christian Braendle; Ananth Rao |
| Abstract: | The development of online banking has brought about an increase in fraudulent operations, which is a major problem for banks. This study delves into the urgent requirement for interpretable, scalable, and top-notch fraud detection systems by using TabNet, an adaptable deep learning framework, on a Kaggle dataset consisting of actual bank transactions in India. Maximizing operational risk management by improving the accuracy of transaction anomaly detection and ensuring regulatory compliance through transparent models is the goal. We utilize a supervised learning pipeline that incorporates the Synthetic Minority Oversampling Technique (SMOTE) to ensure that classes are balanced. Subsequently, we conduct thorough exploratory data analysis (EDA) to identify patterns of fraud, both during specific times and across behaviors. On this dataset, five different deep learning architectures are tested: DNN, GRU, LSTM, CNN1D, and TabNet. Assessment of predictive performance was carried out using a 3-fold cross-validation framework. With a ROC-AUC of 0.9739 and an accuracy of 97.39 %, TabNet considerably outperformed the competition. The method of sparse feature selection used improved interpretability, generalized better on tabular data, and produced fewer false positives and negatives. Critical insights for operational fraud detection systems and a contribution to the broader literature on explainable AI (XAI) in financial decision-making are offered by the findings. Goals 8 and 16 of the Sustainable Development Agenda are supported by this study, which promotes inclusive economic growth and institutional transparency. Supporting strong, policy-compliant, and interpretable decision-support systems, it also offers practical use for real-time implementation in banking infrastructure. |
| Date: | 2026–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2607.18616 |
| By: | Rauh, C. |
| Abstract: | This paper proposes a methodology to extract information about regional economic conditions from newspaper text in real time. The approach relies on large-scale collections of news articles that are summarized using unsupervised machine learning to generate topics capturing recurring themes in economic reporting. Because the method uses the full corpus of regional news and avoids restrictive keyword selection, it minimizes human judgment and allows the data to reveal economically relevant patterns in news coverage. I apply the methodology to Canada, a large and economically diverse country, and show that the resulting topics contain information about fluctuations in economic indicators such as manufacturing activity and unemployment at both the national and provincial levels. The results are robust to alternative choices of the number of topics. A composite index constructed from the topic measures provides a summary indicator of economic information contained in the news. While some topics display similar associations with economic outcomes across provinces, others capture region-specific developments, highlighting the ability of the approach to uncover geographically heterogeneous economic signals in news data. |
| Keywords: | Machine Learning, Latent Dirichlet Allocation, Newspaper Text, Economic Uncertainty, Topic Model, Canada |
| JEL: | D80 E66 C55 |
| Date: | 2026–06–26 |
| URL: | https://d.repec.org/n?u=RePEc:cam:camdae:2657 |
| By: | Luc Hazenoot; Zhaochun Ren; Amirhossein Zohrehvand |
| Abstract: | Existing measures of how much a text is about a concept read the surface of the text: dictionary word shares, topic proportions, embedding similarities. They score the words a text uses, not the judgment a reader forms about it. Recent work has shown that a gap exists in what Large Language Models (LLMs) know internally versus what they express in their response. This paper asks whether that internal knowledge, read by monitoring the activations of frozen, out-of-the-box LLMs, can stand in for task-specific fine-tuning when measuring concept content, and which extraction method reads it best. We extract such measures via the Recursive Feature Machine (RFM) algorithm and via linear probing, and compare these against an embedding baseline, surface baselines, and the same model's own answer to the question. We demonstrate the approach on financial text, a domain studied extensively and served by established annotated resources, using a human-annotated Environmental, Social and Governance (ESG) dataset. The best linear probe comes within 0.6 percentage points of a fine-tuned domain classifier's accuracy without any task-specific fine-tuning, and outscores the same model's own answer to the question in eleven of twelve comparisons, so the activations carry concept content the response does not report. The simple probe consistently beats the RFM concept vectors, which in turn provide what classification alone does not: a continuous score intended to reflect how strongly a concept is present in a text, whose validation awaits graded labels. |
| Date: | 2026–08 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2608.07208 |
| By: | Lönn, Gabriel Elias (University of Oslo); Schutte, Sebastian |
| Abstract: | Text-as-data methods aim to extract quantitative information from natural language. Traditionally, this was accomplished by using separate steps in each analysis, such as part-of-speech tagging, sentiment analysis, and named entity recognition. Modern Large Language Models (LLMs) hold the promise of drastically simplifying this process, as they can be flexibly instructed to extract specific information. However, transferring data to LLM providers at scale and receiving directly usable data back has previously required application-specific programming. In contrast, the rapidcodeR package offers a highly flexible approach to coding quantitative data from text at maximum speed and minimal cost. Here, we present an example of using the package to visualize international relations, directly coded from Russian UN speeches between 1946 and 2024. The results correspond well to formal alliance structures. Similar use cases can involve coding of archival information, researching social media discourse, and extracting event data from news sources. |
| Date: | 2026–07–22 |
| URL: | https://d.repec.org/n?u=RePEc:osf:socarx:q4zd8_v1 |
| By: | Ma, Zhenyao; Liang, Yue; Li, Dongxu |
| Abstract: | Inspired by behavioral science, we propose Behavior Learning (BL), a novel general-purpose machine learning framework that learns interpretable and identifiable optimization structures from data, ranging from single optimization problems to hierarchical compositions. It unifies predictive performance, intrinsic interpretability, and identifiability, with broad applicability to scientific domains involving optimization. BL parameterizes a compositional utility function built from intrinsically interpretable modular blocks, which induces a data distribution for prediction and generation. Each block represents and can be written in symbolic form as a utility maximization problem (UMP), a foundational paradigm in behavioral science and a universal framework of optimization. BL supports architectures ranging from a single UMP to hierarchical compositions, the latter modeling hierarchical optimization structures that offer both expressiveness and structural transparency. Its smooth and monotone variant (IBL) guarantees identifiability under mild conditions. Theoretically, we establish the universal approximation property of both BL and IBL, and analyze the M-estimation properties of IBL. Empirically, BL demonstrates strong predictive performance, intrinsic interpretability and scalability to high-dimensional data. Code: https://github.com/MoonYLiang/Behavior-Learning; installable via pip install blnetwork. |
| Keywords: | Behavioral Modeling, Inverse Optimization, Interpretable Machine Learning, Identifiability, Utility Maximization, Energy-Based Models (EBMs) |
| JEL: | A1 C1 C45 D03 |
| Date: | 2025–09–20 |
| URL: | https://d.repec.org/n?u=RePEc:pra:mprapa:128277 |
| By: | Kellner, Domenic; Lang, Jan Hannes; Rusnák, Marek; Nagy, Lukas Joseph |
| Abstract: | Financial stability risks consist of two distinct components: vulnerabilities and possible trigger events. While there has been considerable progress regarding the measurement of vulnerabilities, the assessment of possible trigger events remains largely qualitative. To fill this gap, we employ Large Language Models to extract information about the Severity and Probability Of potential Trigger events (SPOT) from a large dataset of financial news articles over the period2005 – 2026. The SPOT indicator increases ahead of major historical trigger events, correctly identifies trigger sources, and helps to improve forward looking model estimates of downside risks to the economy. The results indicate that the use of AI-based signal extraction from text can be a promising avenue to improve the monitoring of financial stability risks. JEL Classification: C55, C88, E32, E44, G01 |
| Keywords: | artificial intelligence, crisis indicators, financial stability, growth-at-risk |
| Date: | 2026–07 |
| URL: | https://d.repec.org/n?u=RePEc:ecb:ecbwps:20263262 |
| By: | Jin-Chuan Duan; Mr. Dimitrios Laliotis; Ms. Wei Sun |
| Abstract: | This paper examines macrofinancial linkages between property developers, financial institutions, and macroeconomic outcomes in China. Using a parsimonious vector autoregressive (VAR) model enabled by a machine learning algorithm, it quantifies how idiosyncratic shocks can propagate and be amplified across sectors, with potential implications for financial stability. Stress originating from privately owned developers and regionally focused financial institutions—though relatively limited in scale—can generate persistent spillovers through lending relationships, common exposures, shared markets, and changes in market sentiment. A decline in property prices may undermine investment, weaken consumer confidence, and adversely affect the health of both the property and financial sectors, thereby disrupting financial intermediation and weighing on broader economic growth. Policy considerations should take into account these feedback loops. Market- and exposure-based tools can be helpful for monitoring macrofinancial linkages and assessing the transmission of shocks. |
| Keywords: | Macrofinancial linkage; property development; financial system; machine learning; model selection |
| Date: | 2026–06–26 |
| URL: | https://d.repec.org/n?u=RePEc:imf:imfwpa:2026/134 |
| By: | Ibhar C. Beramendi Illanes (Universidad Privada Boliviana (UPB)); Ivette Illanes Fajardo (Escuela Militar de Ingeniería) |
| Abstract: | Este estudio analiza los determinantes del empleo informal en Bolivia mediante una combinación de técnicas econométricas tradicionales, métodos de machine learning y enfoques híbridos. Utilizando datos de las Encuestas de Ho-gares 2022 y 2023, se identifican los factores individuales y del hogar que influyen en la probabilidad de pertenecer al empleo informal. Los resultados muestran que variables como la edad, el nivel educativo, el ingreso del hogar y el género son deter-minantes clave. El Random Forest destaca el papel central de los ingresos laborales, usualmente excluidos por problemas de endogeneidad. El Adaptive Lasso permite identificar relaciones no lineales e interacciones complejas, como las asociadas al gé-nero, la pertenencia a grupos originarios y la presencia de niños pequeños en el hogar. Se concluye que el fenómeno del empleo informal responde a dinámicas multidimensionales que requieren enfoques analíticos integradores para el diseño de políticas públicas más efectivas y focalizadas. |
| Keywords: | Empleo Informal, Probit, Machine Learning, Adaptive Lasso |
| JEL: | J46 C20 C45 |
| Date: | 2025 |
| URL: | https://d.repec.org/n?u=RePEc:iad:wpaper:1125 |
| By: | Ulimwengu, John M. |
| Abstract: | Large language models (LLM) are increasingly used in applied economics to convert unstructured text into structured empirical measures. This paper examines their use as measurement instruments through a 10-country public-discourse panel on food and nutrition security in Africa from 2010 to 2025. The panel covers Somalia, South Sudan, Sudan, Democratic Republic of the Congo, Nigeria, Ethiopia, Kenya, Niger, Mali, and Burkina Faso, and contains 206 document-level records drawn from public early-warning, humanitarian, government, and technical sources. Each record is organized by country, date, source type, geography, benchmark type, benchmark phase where available, leakage risk, and a set of generated coding variables describing food-security dimension, text severity, narrative frame, tone, attribution, and evidence type. The paper treats LLM-coded outputs not as ground truth, but as generated variables subject to measurement error, source-selection bias, benchmark leakage, and uncertainty arising from incomplete or uneven source text. A conservative validation sample is limited to records with completed source-grounded excerpts, while an exploratory validation sample uses the broader metadata-supported corpus to examine phase coverage across benchmark categories. The results illustrate both the promise and the limits of LLM-assisted public-discourse measurement. Public documents can be transformed into transparent, auditable indicators of food-security stress, but their validity depends on document sampling, excerpt quality, benchmark independence, source diversity, and careful distinction between technical classifications and independent discourse. The paper contributes to the emerging literature on LLMs in economics by shifting attention from general productivity uses toward the practical conditions under which LLM-assisted text measurement can support applied research and policy analysis. A reproducibility package accompanies the study and includes the coded data, validation samples, codebook, data dictionary, AI-use disclosure, leakage documentation, and scripts for reproducing the descriptive results. |
| Keywords: | large language models; food security; economics; measurement; Somalia; South Sudan; Sudan; Congo, Democratic Republic of; Nigeria; Ethiopia; Kenya; Niger; Mali; Burkina Faso; Africa; Sub-Saharan Africa |
| Date: | 2026–06–30 |
| URL: | https://d.repec.org/n?u=RePEc:fpr:ifprid:183571 |
| By: | Lagakos, David; Michalopoulos, Stelios; Voth, Hans-Joachim |
| Abstract: | What does it take to live a meaningful life? We exploit a unique corpus of over 1, 400 life narratives of older Americans collected by a team of writers during the 1930s. We combine detailed human readings with large language models (LLMs) to extract systematic information on critical junctures, sources of meaning, and overall life satisfaction. Under specific conditions, LLMs can provide responses to complex questions that are indistinguishable from those of human readers, effectively passing a version of the Turing Test. We find that sources of life meaning are more varied than previous research suggested, underlining the importance of work and community contributions in addition to family and close relationships (emphasized by earlier work). The narratives also highlight gendered disparities, with women disproportionately citing adverse family events, such as the loss of a parent, underscoring their role as keepers of the kin. Our research expands our understanding of human flourishing during a transformative period in American history and establishes a robust and scalable framework for exploring subjective well-being across diverse historical and cultural contexts. |
| Keywords: | Text analysis; Narratives; Life satisfaction |
| JEL: | I00 I31 N32 |
| Date: | 2025–01 |
| URL: | https://d.repec.org/n?u=RePEc:cpr:ceprdp:19885 |
| By: | Dana Golden; Brett Indelicato; Lav R. Varshney; Carlos D. Messina; Suzanne Thornsbury |
| Abstract: | Rigorous economic models can take months to construct, yet energy crises demand decisions from policymakers within days or even hours. Any disruption in energy markets is not isolated but rapidly disseminates through interlinked global systems. Off-the-shelf models that already exist typically focus only on limited aspects of the system and are distributed across research groups, programming languages, software architectures not designed for model integration, and incompatible formats. Integrating these models manually can take longer than the crisis itself, forcing analysts to rely on whichever models are easiest to connect and leaving consequential scenarios unexplored. Policymakers must make rapid decisions with obstructed and limited information. We show that large language models can perform the critical integration directly. The system constructs internally consistent scenarios, translates assumptions into model-specific inputs, executes existing economic and physical models in dependency order, and synthesizes outputs tailored to policymakers. The language model generates no quantitative results: every reported value is reproduced directly from an underlying model run, remains traceable to its source and is subject to analyst approval at each stage. We develop a LLM framework that coordinates 16 models of oil, natural gas, shipping, water, helium, fertilizer and macroeconomic equilibrium. The framework is applied across five scenarios to assess the 2026 closure of the Strait of Hormuz and refreshed weekly for eight weeks as events on the ground continued to unfold. By linking models that already exist and reading them as a suite rather than in isolation, this architecture mobilizes distributed scientific models rapidly during energy and geopolitical disruptions while keeping any single model's assumptions from driving the conclusion. |
| Date: | 2026–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2607.23313 |
| By: | Alessio Emanuele Biondo; Mauro Gallegati |
| Abstract: | We develop an agent-based model in which inflation emerges from decentralized price-setting and credit-financed production in an endogenous-money economy. Firms operate under working-capital constraints, form market-based price expectations through heterogeneous adaptive learning, and set prices via cost-plus rules with endogenous mark-ups. Bank lending simultaneously creates deposits, while heterogeneous lending rates and credit rationing shape firms' financing costs and, through unit costs, their pricing decisions. The economy features interacting production and credit networks: intermediate-input linkages propagate cost shocks across supply chains, while bank--firm relationships transmit financial conditions across firms. The interaction of network-based pass-through, state-dependent pricing incentives, and evolving credit conditions generates inflationary regimes, including episodes driven by pricing cascades and feedback loops. |
| Date: | 2026–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2607.07864 |