Actuaries rely primarily on structured numerical data for reserving and ratemaking, while valuable predictive information in unstructured text including medical records, adjuster notes, and call transcripts remains largely unused. Manual processing of these documents is time-consuming, inconsistent across reviewers, and unscalable. We present a proof-of-concept framework using large language models (LLMs) to extract structured actuarial variables from unstructured claims data. We implement a two-stage processing architecture separating document-level extraction (Stage 1) from claim-level synthesis (Stage 2). A modular four-script Python pipeline processes synthetic FHIR-based claims data and real claims documents, extracting 36 actuarial variables across reserving, ratemaking, and claims management categories. We validate 14 core variables using two independent clinical expert reviewers scoring 20 synthetic claims on a five-point Likert rubric, achieving mean scores above 4.0 and a weighted kappa of 0.53. Integration with chain ladder reserving demonstrates practical actuarial value: severity-segmented analysis reduced reserve estimation error from 6.5% to 4.0%. The open-source implementation includes audit trails and confidence scoring, providing a replicable foundation for LLM-based actuarial variable extraction in property-casualty insurance.

We study the division of a heterogeneous good between two agents into contiguous bundles, each defined by a starting location and a quantity, in a purely ordinal framework that does not rely on cardinal valuations. We introduce a general class of monotonic preferences representable by indifference curves. We show that an allocation is Pareto efficient and envy-free if and only if it lies in a specific ``balanced region'', implying that an equal split is fair only when it belongs to this region. We further show that no rule can simultaneously satisfy Pareto efficiency, envy-freeness, and strategy-proofness.

We study forecasting of the realized covariation in electricity markets. The realized covariation in this context is a matrix-valued representation of the latent infinite-dimensional covariance operator and a parsimonious matrix-HAR type model is constructed to facilitate estimation. We test the model on one-week ahead forecasts of the weekly realized covariation and find that the inclusion of longer time horizons and renewable generation information adds important predictive power. We also investigate the prediction of risk premia in electricity forward markets and find that our variance forecasts provide substantially improved forecasts of spread risk premia compared to standard methods relying on backward looking volatility.

Turning a promising economic idea into a credible empirical finding is, in practice, an expensive undertaking: it demands a great deal of specialised computation, and the results are seldom released in a form that others can check or build upon. Econstellar is our response. It is an open, publicly served research engine that runs publication-grade financial econometrics from an ordinary web browser and explains what the results mean, so that a reader does not merely read a finding but can re-run it, vary its inputs, and trace exactly how it was produced. Three choices give the system its character. The heavy computation is placed on the processor that suits it, rather than forced onto hardware ill-matched to the task, which is much of the reason analysis of this kind is so rarely served to the public. An artificial-intelligence assistant selects and interprets the analyses but never originates a number, so every quantity it reports is a real computation the reader can reproduce. And the engine a visitor exercises is the same code that produced the figures in our published research. We expose seventeen econometric methods, each reported with a verified live value and reproducible at the public endpoint, computed under a single discipline: prices are treated as non-stationary and all methods are applied to returns. The system also regenerates, on demand, the headline result of an accompanying study of financial contagion, from the package that generated it. The platform is the working core of an active research programme spanning three software releases and three preprints, and it is available now, free and open-source, at a live public address. Our aim is a simple one: to shorten the distance between a research claim and the moment another person can independently verify it.

The ratio of voting power between a permanent member and a non-permanent member of the United Nations Security Council varies substantially across indices: approximately 100 to 1 according to the Shapley-Shubik index, 10 to 1 according to the Banzhaf index, and 2.5 to 1 according to the Deegan-Packel index. Such comparisons depend on the choice of power index and are meaningful only in settings where players are divided into two types. To address these limitations, this paper proposes and characterizes a function that measures the level of power concentration in monotonic approval voting games. The proposed measure assigns a single value to each voting game, reflecting the extent to which voting power is unevenly distributed among players. The proposed measure is proportional to the sum of squared Deegan-Packel power indices and can also be interpreted as the degree of overlap among minimal winning coalitions. An application to the United Nations Security Council is also provided.

Market stress rarely harms investors through one channel alone. Losses, volatility spikes, and deteriorating tradability often arrive together. We examine whether ESG is associated with lower exposure to clustered fragility in equity markets. Using monthly data on S&P 500 constituents from 2014 to 2025, we study downside returns, volatility, illiquidity, and a cofragility state that captures their joint occurrence within the same firm month. The evidence supports a stress-amplified resilience interpretation rather than an unconditional ESG return premium. In the return channel, the ESG association is concentrated in the extreme downside tail during stress months. In the volatility channel, higher ESG is associated with smaller risk spikes when aggregate conditions are weak. In the illiquidity channel, the association is more persistent, suggesting a liquidity-quality component whose relevance increases when market-wide trading conditions deteriorate. The central evidence comes from the joint analysis: a one-standard-deviation increase in ESG lowers the stress-period probability of severe cofragility by 0.92 percentage points, about 9% relative to the baseline. Double Machine Learning shows a similar negative ESG association after flexible adjustment for observable firm characteristics. Pillar evidence suggests stronger baseline resilience for Environmental scores and clearer stress amplification for Social scores. Overall, the findings characterize ESG as a multi-channel fragility signal for tail-risk monitoring, stress analysis, and pillar-level ESG assessment.

The weighted center of imputations (CIS) value allocates the surplus of the grand coalition equally after granting each player a fixed proportion of his individual worth. This paper provides three axiomatic characterizations of this value by generalizing the individual rationality and subgame order preservation axioms. The first characterization employs individual rationality with respect to the weights together with the equal surplus increment property. The second relies on efficiency, additivity, symmetry adjusted by the weights, and a dummifying player property adapted to the weights. The third builds on efficiency and a weak subgame order preservation axiom that incorporates the weights. These results unify and extend recent findings, covering both the equal division and the standard CIS values as special cases.

We provide a theorem on the role of risk and risk attitudes in macroeconomic models that clarifies and extends the Tallarini (2000) separation result. Under (1) separation of intertemporal and risk preferences, (2) separation of drivers of first and higher moments in the model primitives, and (3) approximate linearity of constraints, risk aversion and time-varying risk are irrelevant for the elasticity of any endogenous variable with respect to state variables that don't drive variation in higher moments. We discuss how models generate a more prominent role for risk by ``breaking'' or ``adapting'' to the assumptions in the theorem.

Agentic artificial intelligence (AI) systems are transforming the risk landscape by extending beyond information generation to autonomous planning, tool invocation, decision execution, and persistent modification of digital and physical environments. These capabilities introduce novel exposures that do not fit neatly within traditional insurance categories such as cyber, professional liability, product liability, or directors and officers coverage. This paper examines the emerging insurance market for agentic AI and develops a framework for understanding its underwriting, pricing, reinsurance, and product-design implications. We characterize agentic AI as a continuum of autonomy and delegated authority, emphasizing the distinction between informational outputs and systems capable of independently generating insured events through external actions. We analyze major risk pathways, including hallucinations, prompt-injection attacks, autonomous decision errors, model drift, dependency failures, and cyber-physical harms, and evaluate how existing insurance products are adapting to address these exposures. The paper further proposes an actuarial framework based on exposure assessment, scenario analysis, dependency mapping, and accumulation-risk management, drawing parallels to the evolution of cyber insurance. Finally, we present a coordinated insurance architecture that integrates cyber, technology errors and omissions, product liability, performance-warranty, and affirmative AI-liability coverages through explicit allocation mechanisms and dedicated AI aggregates. The analysis suggests that the future of agentic-AI insurance lies not in a single monoline product but in a layered ecosystem of complementary coverages supported by improved governance, transparency, telemetry, and regulatory clarity.

Can artificial intelligence (AI) refute economic theory? I document experiments in which I asked several AI models (Gemini, Refine, Claude, and ChatGPT) to check the correctness of four published papers in economic theory, each containing an error that I helped identify or correct. ChatGPT Pro performed best, occasionally constructing counterexamples and corrected proofs, while other models fared worse. However, no model located a true error without substantial human guidance, and data contamination complicates interpretation. I argue that a competent human paired with a frontier model can outperform current peer review, but AI cannot yet refute economic theory on its own.

Norway's electricity market is heavily dominated by hydropower, but the 2021-2022 energy crisis and stronger integration with Continental Europe have fundamentally altered price formation, reducing the reliability of forecasting models calibrated on historical data. Despite the critical need for updated models, a unified benchmark evaluating feature contributions across all structurally diverse Norwegian bidding zones remains lacking. Here we present a comprehensive evaluation of one-step-ahead forecasting of the Nord Pool market across all five Norwegian bidding zones. We constructed a multimodal hourly dataset spanning 2019-2025 and evaluated eight forecasting model families, including Light Gradient Boosting Machine (LightGBM), autoregressive models with exogenous variables, and advanced deep learning architectures, using a strictly causal test set. We implemented robust rolling-origin backtesting, leave-one-group-out feature ablation, and conditional regime analysis to dissect model performance and feature utility. Our results show that LightGBM achieves the best performance in every zone, with mean absolute error ranging from 1.60 to 5.58 euros per megawatt-hour, while a ridge-regularized autoregressive model with exogenous variables remains a highly competitive linear benchmark in northern zones. Feature ablation reveals that models relying solely on lagged prices and calendar variables achieve high accuracy and often match or closely approach the performance of the full multimodal model. However, conditional regime analysis demonstrates that external features like reservoir levels and gas prices remain crucial to stratify forecast errors, which consistently increase under stressed market regimes. This highlights the practical value of model interpretability and regime awareness for decision makers facing structural changes in market dynamics.

Interactive fixed effects are routinely controlled for in linear panel models. While an analogous fixed effects (FE) estimator for nonlinear models has been available in the literature (Chen, Fernandez-Val and Weidner, 2021), it sees much more limited use in applied research because its implementation involves solving a high-dimensional non-convex problem. In this paper, we complement the theoretical analysis of Chen, Fernandez-Val and Weidner (2021) by providing a new computationally efficient estimator that is asymptotically equivalent to their estimator. Unlike the previously proposed FE estimator, our estimator avoids solving a high-dimensional non-convex optimization problem and can be feasibly computed in large nonlinear panels. Our proposed method involves two steps. In the first step, we convexify the optimization problem using nuclear norm regularization (NNR) and obtain preliminary NNR estimators of the parameters, including the fixed effects. Then, we find the global solution of the original optimization problem using a standard gradient descent method initialized at these preliminary estimates. To make our method readily applicable in practice, we also propose specific numerical algorithms for solving the involved optimization problems, establish their convergence, and provide their efficient implementation in our R package NNRPanel.

If AI displaces human workers faster than the economy can reabsorb them, it risks eroding the very consumer demand firms depend on. We show that knowing this is not enough for firms to stop it. In a competitive task-based model of a transitioning economy, each firm captures the full cost saving from automation but bears only a fraction of the demand loss it creates in the product market; the rest falls on rivals. This demand externality traps rational firms in an automation arms race, displacing workers well beyond what is collectively optimal. The resulting loss harms both workers and firm owners. More competition and ``better'' AI amplify the excess; wage adjustments and free entry cannot eliminate it. Neither can capital income taxes, worker equity, universal basic income, upskilling, or Coasean bargaining. A Pigouvian automation tax can. The results suggest that policy should address not only the aftermath of AI labor displacement but also the competitive incentives that drive it.

In many choice settings the decision maker (DM) adopts a criterion which is a mediation between her preference, and its opposite. According to such compromise, the first i alternatives on top of the DM's taste are moved, in reverse order, to the bottom. This pattern allows to define the compromise-based degree of irrationality, which quantifies the extent of the mediation embraced by the DM in her choice. Necessary and sufficient conditions characterizing this index are singled out. I investigate non rationalizable choices that display the lowest degree of irrationality, and I fully identify the preferences that explain the DM's picks by a minimal mediation between opposite judgments. These datasets account for some well known selection biases, such as second-best procedures, and the handicapped avoidance. I offer a simple characterization of the choice behavior that exhibits the most severe compromise, and I show that this subclass comprises almost all choices. Finally, some alternative measures of compromise are characterized, and compared with the score previously determined.

Recursive decision trees are widely used to estimate heterogeneous causal treatment effects in experimental and observational studies. These methods are typically implemented using CART-type recursive partitioning, with splitting criteria designed to identify variation in treatment effects across covariate-defined subgroups. We study causal tree estimators based on adaptive recursive partitioning and establish lower bounds on their estimation accuracy. The class we analyze includes versions with and without sample splitting, based on common treatment effect and squared-error splitting criteria. Even in a constant-effect benchmark with randomized treatment assignment, causal trees constructed via standard CART-type splitting rules can have uniform-norm errors that decrease more slowly than any power of the sample size. The underlying mechanism is that greedy recursive partitioning selects highly imbalanced splits with nonvanishing probability, producing terminal nodes containing very few observations and leading to large estimation variance. We further show that sample splitting, often called ``honesty,'' does not remove this limitation. As a consequence, causal tree estimators may converge arbitrarily slowly uniformly over the covariate space. At the same time, these estimators can have small integrated mean squared error, showing that average accuracy can mask local inaccuracy. Our results also clarify the role of balanced partition assumptions in existing theoretical guarantees for causal forests and related ensemble methods.

We study the problem of estimating Dynamic Discrete Choice (DDC) models, also known as offline Maximum Entropy-Regularized Inverse Reinforcement Learning (offline MaxEnt-IRL) in machine learning. The objective is to recover reward or $Q^*$ functions that govern agent behavior from offline behavior data. In this paper, we propose a globally convergent gradient-based method for solving these problems without the restrictive assumption of linearly parameterized rewards. The novelty of our approach lies in introducing the Empirical Risk Minimization (ERM) based IRL/DDC framework, which circumvents the need for explicit state transition probability estimation in the Bellman equation. Furthermore, our method is compatible with non-parametric estimation techniques such as neural networks. Therefore, the proposed method has the potential to be scaled to high-dimensional, infinite state spaces. A key theoretical insight underlying our approach is that the Bellman residual satisfies the Polyak-Lojasiewicz (PL) condition -- a property that, while weaker than strong convexity, is sufficient to ensure fast global convergence guarantees. Through a series of synthetic experiments, we demonstrate that our approach consistently outperforms benchmark methods and state-of-the-art alternatives.

I introduce heterogeneity into the analysis of peer effects arising from conformity by allowing peer-effect parameters to vary across agents' actions. Using a structural model based on a simultaneous network game with incomplete information, I derive conditions that guarantee the uniqueness of the equilibrium and the identification of heterogeneous peer-effect parameters. Applying the model to data on smoking and alcohol consumption among secondary school students, and conducting policy simulations, I show that assuming a homogeneous preference for conformity leads to biased estimates of peer effects and ex ante policy evaluations.

We introduce a general integral framework for computing fractional, complex, absolute, and logarithmic moments from the moment-generating function (MGF) under explicit regularity conditions. By evaluating a complex extension of the MGF along a vertical contour, we obtain exact integral expressions that bypass the need for explicit probability densities and high-order derivatives. We establish conditions for negative fractional moments using the symmetric Cauchy principal value, including the requirement that the distribution have no point mass at the centering point. We demonstrate the theoretical scope and computational practicality of the framework through applications to the normal-inverse Gaussian distribution and a semicontinuous compound Poisson-Gamma distribution. In the latter case, the framework handles point masses at the boundary by evaluating conditional fractional moments.

Many of the world's renewable resources are in decline. Optimal harvests with smooth recruitment is well studied but in recent years, ecologists have concluded that tipping points in recruitment are common. Recruitment with a tipping point has low-fecundity below the tipping point and high-fecundity above. When the discounted value of high-fecundity is sufficiently high, there is a high-fecundity steady-state. This steady-state is stable but in some cases, small perturbations may result in large, temporary reductions in recruitment and harvests. Below the tipping point, a low-fecundity steady-state need not exist. When a low-fecundity steady-state does exist, there is an endogenous tipping (Skiba) point: below, harvests converge to the low-fecundity steady-state and above, an austere harvest policy transitions the renewable resource to high-fecundity recruitment. If there is hysteresis in recruitment, the high steady-state may not be stable. Moreover, if the high-/low-fecundity differential is large then following a downward perturbation, fecundity optimally remains low.

We propose confidence regions for the parameters of incomplete models with exact coverage of the true parameter in finite samples. Our confidence region inverts a test, which generalizes Monte Carlo tests to incomplete models. The test statistic is a discrete analogue of a new optimal-transport formulation of the structural model. Both test statistic and critical values rely on simulation draws from the distribution of latent variables and are computed using solutions to discrete optimal transport, hence linear programming problems. We also propose a fast preliminary search in the parameter space with an alternative, more conservative yet consistent test, based on a parameter-free critical value. We compare size and power of our procedure with competing proposals in simulations based on a regression with interval valued regressors. Finally, we apply our methodology to the model of airline entry and price competition in Ciliberto et al. [2021].

This study investigates the pre-trained RNN attention models with the mainstream attention mechanisms, such as additive attention, Luong's three attentions, global self-attention and sliding window sparse attention, for the empirical asset pricing research on the top 420 large-cap US stocks. This is the first paper on the large-scale state-of-the-art (SOTA) attention mechanisms applied in the asset pricing context. They overcome the limitations of the traditional machine learning-based asset pricing, such as mis-capturing the temporal dependency and short memory. Moreover, the enforced causal masks in the attention mechanisms address the future data leaking issue ignored by the more advanced attention-based models, such as the classic Transformer. The proposed attention models also consider the temporal sparsity characteristic of asset pricing data and mitigate potential overfitting issues by deploying the simplified model structures. This provides some insights for future empirical economic research. All models are examined in three periods, which cover pre-COVID-19, COVID-19 and one year post-COVID-19, for testing the stability of these models under extreme market conditions. The study finds that in value-weighted portfolio back testing, the global self-attention model and the sliding window sparse attention model exhibit excellent capabilities in deriving the absolute returns and hedging downside risks, while they achieve an annualized Sortino ratio of 2.0 and 1.80 respectively in the period with COVID-19 in the static transaction cost scenario. Moreover, the sliding window sparse attention model performs more stably than the global self-attention model from the perspective of absolute portfolio returns with respect to the size of stocks' market capitalization.

This paper studies semiparametric Bayesian inference for the average treatment effect on the treated (ATT) within the difference-in-differences (DiD) research design. We propose two new Bayesian methods with frequentist validity. The first one is the semiparametric Bayesian outcome regression, where we place a Gaussian process prior on the conditional mean function of the control group. The second method is a doubly robust Bayesian procedure that adjusts the prior distribution of the conditional mean function and subsequently corrects the posterior distribution of the resulting ATT. We prove new semiparametric Bernstein-von Mises (BvM) theorems for both proposals. Monte Carlo simulations and an empirical application demonstrate that the proposed Bayesian DiD methods exhibit strong finite-sample performance. We also present extensions of the canonical DiD approach, incorporating clustered data and staggered entry with multiple periods.

Can wasteful money burning improve strategic communication? We show that it can, but only with intermediate commitment. In mediated communication with report-contingent burning, the mediator can use costly messages to discipline deviations and make persuasive messages credible. Under transparent motives, increasing the burning budget strictly raises the Sender's payoff once the budget is large enough, unless mediated communication with money burning collapses to cheap talk. With an unbounded budget, the value equals a robust Bayesian persuasion payoff, or equivalently the payoff of a cautious Sender. The framework clarifies commitment through smart contracts and Web 3.0 mediation.