Institutional crossing platforms face a hidden-information problem: investors value trades as portfolios, but liquidity discovery is typically organized around individual securities. We model portfolio crossing as limited-communication preference elicitation over signed portfolio trades. The platform first uses price-directed demand queries to search the portfolio space and then verifies selected packages through value queries; an incumbent verification query records the demand-discovered allocation before further exploration. Final allocations are chosen from elicited reports, so the learning model guides queries but does not determine welfare. The analysis shows why search and verification are complementary. Demand queries locate high-value regions of a nonseparable portfolio space, but they provide only conservative welfare evidence unless selected packages are verified. Value queries provide exact welfare comparisons, but they are ineffective when applied to poorly targeted packages. Market-calibrated experiments using equity panels from the United States, Korea, Japan, and Germany show that demand-only and value-only designs recover only about half of full-information welfare under a limited query budget, whereas the hybrid procedure recovers 88\% and approaches 95\% as communication expands. We then compare exact security-level packages with factor-completed basket packages within the same allocation rule. Security-level packages are the unadjusted-efficiency mode when exact-securities disclosure is inexpensive. Factor-completed baskets become preferable when pretrade message informativeness is costly. The results characterize portfolio crossing as a selective verification problem and identify disclosure-sensitive package representation as a core design choice for hidden liquidity platforms.

The US housing market exhibits pronounced seasonal cycles: prices and sales rise through spring, peak in summer, and decline through autumn and winter. Since 2021, this pattern has shifted earlier in the calendar year, with spring strengthening at the expense of the traditional summer peak. A leading explanation for housing market seasonality is the search-and-matching model of Ngai and Tenreyro (2014), which links these cycles to household mobility through a thick-market mechanism. In this framework, periods with higher mobility generate thicker markets and higher prices and transaction volumes. Viewed through this lens, a shift in the seasonal cycle of prices and sales raises the question of whether the timing of household moves has changed. Did residential mobility shift earlier in the calendar year after 2021? We find that it did. Using SIPP data, and corroborating evidence from Google Trends indicators, we document a post-2021 shift in mobility toward spring. We extend the model to a monthly frequency, prove the existence and uniqueness of the equilibrium, and calibrate it to the observed mobility patterns. The calibrated model reproduces the spring shift in both prices and transaction volumes, consistent with the view that a change in the timing of household mobility alone can account for the recent shift in housing market seasonality.

Frontier AI Safety Policies concentrate on prevention: capability evaluations, deployment gates, and usage constraints, while neglecting the capacity to coordinate responses when prevention fails. We argue this coordination gap is structural: investments in ecosystem robustness yield diffuse benefits but concentrated costs, generating systematic underinvestment. Drawing on risk regimes in nuclear safety, pandemic preparedness, and critical infrastructure, we propose that similar mechanisms (precommitment, shared protocols, standing coordination venues) could be adapted to frontier AI governance. Closing the gap requires cross-actor "note-exchange" of ex ante if-then response logic, exposing not only triggers but the decision processes that convert signals into actions. Without such architecture, institutions cannot learn from failures at the pace of relevance.

Large language models show promise for financial decision-making, yet deploying them as autonomous trading agents raises fundamental challenges: how to adapt instructions when rewards arrive late and obscured by market noise, how to synthesize heterogeneous information streams into coherent decisions, and how to bridge the gap between model outputs and executable market actions. We present ATLAS (Adaptive Trading with LLM AgentS), a unified multi-agent framework that integrates structured information from markets, news, and corporate fundamentals to support robust trading decisions. Within ATLAS, the central trading agent operates in an order-aware action space, ensuring that outputs correspond to executable market orders rather than abstract signals. The agent can incorporate feedback while trading using Adaptive-OPRO, a novel prompt-optimization technique that dynamically adapts the prompt by incorporating real-time, stochastic feedback, leading to increasing performance over time. Across regime-specific equity studies and multiple LLM families, Adaptive-OPRO consistently outperforms fixed prompts, while reflection-based feedback fails to provide systematic gains.

This paper presents a comprehensive study on the use of ensemble Reinforcement Learning (RL) models in financial trading strategies, leveraging classifier models to enhance performance. By combining RL algorithms such as A2C, PPO, and SAC with traditional classifiers like Support Vector Machines (SVM), Decision Trees, and Logistic Regression, we investigate how different classifier groups can be integrated to improve risk-return trade-offs. The study evaluates the effectiveness of various ensemble methods, comparing them with individual RL models across key financial metrics, including Cumulative Returns, Sharpe Ratios (SR), Calmar Ratios, and Maximum Drawdown (MDD). Our results demonstrate that ensemble methods consistently outperform base models in terms of risk-adjusted returns, providing better management of drawdowns and overall stability. However, we identify the sensitivity of ensemble performance to the choice of variance threshold τ, highlighting the importance of dynamic τ adjustment to achieve optimal performance. This study emphasizes the value of combining RL with classifiers for adaptive decision-making, with implications for financial trading, robotics, and other dynamic environments.

Forecasting univariate time series in the financial market is a challenging endeavor. While numerous statistical and machine learning models have been introduced to address this challenge, they typically concentrate solely on analyzing temporal patterns within the time series data. In this research, we study the statistical significance of the inclusion of geometric patterns in enhancing forecasting accuracy within the context of time series analysis. We introduce the Time-Geometric model, a combination of models designed to exploit both geometric and temporal patterns. The contribution of this research lies in advancing the domain of univariate time series prediction,as demonstrated through extensive empirical evaluations. Our findings underscore that leveraging geometric patterns, captured through Graph Neural Networks, yields statistically significant improvements in forecasting accuracy.

The 2025 Bondi Beach mass-shooting was perpetrated by individuals inspired by ISIS (Islamic State) propaganda that increasingly featured anti-Semitic hate content following the October 2023 start of the Israel-Palestine war. Similar stories hold for other types of hate attacks, e.g. against Muslims on May 18, 2026. There is an urgent need to get ahead of future threats by understanding how and when a newly created piece of hate content will spread system-wide online. We present a two-species coalescence-fragmentation model with Susceptible-Infected-Recovered dynamics that incorporates the following published empirical features: (1) New pieces of hate content tend to be generated and promoted by a subset of in-built communities on less regulated platforms. (2) These `hate' communities create links (hyperlinks) with each other and with non-hate communities across all platforms to form dynamically evolving clusters (i.e. coalescence) across which new hate content can then spread. (3) These clusters can get broken up by moderator shutdowns (i.e. fragmentation). We present numerical solutions and derive two levels of approximate mean-field theory: Effective Medium Theory (EMT) and Beyond Effective Medium Theory (BEMT). Both numerical and analytic solutions reveal that system-wide spreading is governed by re-entrant threshold phases: as the fraction of hate communities varies, the system can transition from spreading to no-spreading and back to spreading. The derived analytic formulae give explicit insight into how these phase boundaries might be manipulated to prevent system-wide spreading. More broadly, the re-entrant phase behavior warns that policies which steadily reduce the number of hate communities can initially succeed but then backfire if pushed further, suggesting that blanket requirements for platforms to simply do `more' are over-simplistic.

This paper examines how wartime economic controls shaped stock-price formation in Japan from 1930 to 1943. We develop a four-portfolio asset-pricing model in which zaibatsu affiliation affects expected payoffs and the translation of valuations into economic scale through lower financing wedges. We then construct daily capitalization-weighted indices and four benchmark portfolios based on a two-by-two sort by zaibatsu affiliation and military orientation. Using a CAPM-AR(p)-SV event-study framework that allows for serial correlation and stochastic volatility, we show that the model rationalizes capitalization concentration, segmented abnormal returns, delayed cumulative adjustment, regime-risk insulation of zaibatsu portfolios, and zaibatsu-concentrated responses to embedded-rent or group-continuation shocks. The evidence is consistent not with a collapse of semi-strong efficiency, but with institutionally contingent efficiency: stock prices continued to respond to news while capitalizing uneven access to credit, materials, and procurement.

This paper tests whether graph neural networks improve realized volatility forecasts and whether those forecasts improve portfolio performance. Using weekly realized volatility for 465 S&P 500 equities from 2015-2025, Heterogeneous Autoregressive and Long Short-Term Memory baselines are compared against GraphSAGE models built on rolling correlation, sector, and Granger-causal graphs, with and without macro regime features. The empirical finding is that the model with the lowest forecast MSE, the model with the highest cross-sectional ranking accuracy, and the model with the highest portfolio Sharpe ratio are three different models. Forecast accuracy, ranking quality, and portfolio performance are related but not interchangeable objectives. Graph volatility models add value only when the portfolio rule can exploit the cross-sectional structure they encode.

Finite-player dynamic games with dispersed private information are difficult because actions both move payoffs and reshape what opponents learn, generating hierarchies of beliefs about beliefs. This paper provides a recursive representation for this problem. The noise state records agents' beliefs about the underlying shocks that generate histories, so higher-order beliefs are generated by composition rather than tracked as separate state variables. In the canonical continuous-time LQG benchmark, the representation becomes explicit: beliefs, value gradients, and policy rules are deterministic impulse-response functions, and equilibrium is a deterministic fixed point in those functions. Any fixed point in the noise-state linear class is a Nash equilibrium against arbitrary admissible \(L^2\) deviations. The first-order system contains an information wedge, the shadow price of changing opponents' posteriors. In a two-player benchmark, the wedge explains why pooling gains are mostly strategic, why optimal precision allocation can starve an inefficient player of information, and why signal precision changes policy rules themselves, so separation fails.

We study horizontal differentiation when the set of feasible products is a structured subset of the Lancasterian characteristics space. Modeling this set as a compact Riemannian manifold, we show that intrinsic geometry governs substitutability and thereby determines market outcomes. We establish that production constraints induce sectional curvature, which controls the elasticity of technological substitution. Negative curvature amplifies technological divergence and attenuates competitive pressure, whereas positive curvature compresses technological distances and intensifies competition. This mapping yields a characterization of spatial competition in which equilibrium existence and stability are determined by geometric primitives. In particular, we show that sufficiently negative curvature and high dimensionality stabilize minimum differentiation, while continuous symmetries preclude it. The analysis provides a microfoundation linking technological constraints, through the geometry of the feasible set, to endogenous regimes of market power.

The rapid advancements in Large Language Models (LLMs) have unlocked transformative possibilities in natural language processing, particularly within the financial sector. Financial data is often embedded in intricate relationships across textual content, numerical tables, and visual charts, posing challenges that traditional methods struggle to address effectively. However, the emergence of LLMs offers new pathways for processing and analyzing this multifaceted data with increased efficiency and insight. Despite the fast pace of innovation in LLM research, there remains a significant gap in their practical adoption within the finance industry, where cautious integration and long-term validation are prioritized. This disparity has led to a slower implementation of emerging LLM techniques, despite their immense potential in financial applications. As a result, many of the latest advancements in LLM technology remain underexplored or not fully utilized in this domain. This survey seeks to bridge this gap by providing a comprehensive overview of recent developments in LLM research and examining their applicability to the financial sector. Building on previous survey literature, we highlight several novel LLM methodologies, exploring their distinctive capabilities and their potential relevance to financial data analysis. By synthesizing insights from a broad range of studies, this paper aims to serve as a valuable resource for researchers and practitioners, offering direction on promising research avenues and outlining future opportunities for advancing LLM applications in finance.

Senders of messages prefer to communicate uncertainty verbally (e.g., something is likely to happen) rather than numerically (such as 75%), leaving receivers with imprecise information. While it is well established that receivers translate verbal probabilities into numerical values that systematically deviate from the intended numerical meaning, it is less clear how this discrepancy influences subsequent behavioral actions. Thus, the role of verbal versus numerical communication of uncertainty warrants additional attention, to investigate two critical questions: 1) whether differences in decision-making under uncertainty arise between these communication forms, and 2) whether such differences persist even when verbal phrases are translated accurately into the intended numerical meaning. By implementing a laboratory experiment, we show that individuals place significantly lower values on uncertain options with medium to high likelihoods when uncertainty is communicated verbally rather than numerically. This effect may lead to less rational decisions under verbal communication, particularly at high likelihoods. Those results remain consistent even if individuals translate verbal uncertainty correctly into the intended numerical uncertainty, implying that a biased behavioral response is not only induced by miscommunication. Instead, ambiguity about the exact meaning of a verbal phrase interferes with decision-making even beyond potential mistranslations. These findings tie in with previous research on ambiguity aversion, which has predominantly operationalized ambiguity through numerical ranges rather than verbal phrases. Based on our findings we conclude that managers should communicate uncertainty numerically, as verbal communication can unintentionally influence the decision-making process of employees.

We present a generative approach to price options and extract risk-neutral densities from the market. Specifically, we model the underlying log-returns on the time-to-maturity continuum as a generative model from standard normal. Neural nets are used to represent the term structures of the location, the scale, and the higher-order moments. We impose stringent conditions on the learning process to ensure no arbitrage. This model allows for the efficient generation of samples to price options across strikes and maturities. We have validated the effectiveness of this approach by benchmarking it against a comprehensive set of baseline models. Experiments show that the extracted risk-neutral densities accommodate a diverse range of shapes. Its accuracy significantly outperforms the extensive set of baseline models--including three parametric models and nine stochastic process models--in terms of accuracy and stability. The success of this approach is attributed to its capacity to offer flexible term structures for risk-neutral skewness and kurtosis.

The paper examines the effects of stringent land use regulations, measured using the Wharton Residential Land Use Regulatory Index (WRLURI), on employment growth during the period 2010-2020 in the Retail, Professional, and Information sectors across 878 local jurisdictions in the United States. All the local jurisdictions exist in both (2006 and 2018) waves of the WRLURI surveys and hence constitute a unique panel data. We apply a mediation analytical framework to decompose the direct and indirect effects of land use regulation stringency on sectoral employment growth and specialization. Our analysis suggests a fully mediated pattern in the relationship between excessive land use regulations and employment growth, with housing cost burden as the mediator. Specifically, a one standard deviation increase in the WRLURI index is associated with an approximate increase of 0.8 percentage point in the proportion of cost burdened renters. Relatedly, higher prevalence of cost-burdened renters has moderate adverse effects on employment growth in two sectors. A one percentage point increase in the proportion of cost burdened renters is associated with 0.04 and 0.017 percentage point decreases in the Professional and Information sectors, respectively.

This paper assumes a robust, in general not dominated, probabilistic framework and provides necessary and sufficient conditions for a bipolar representation of subsets of the set of all quasi-sure equivalence classes of non-negative random variables, without any further conditions on the underlying measure space. This generalizes and unifies existing bipolar theorems proved under stronger assumptions on the robust framework. Applications are in areas of robust financial modeling.

We develop a unified microeconomic and monetary theory of artificial intelligence inference costs and their pass-through to inflation, welfare, and optimal monetary policy. We introduce the Inference-Cost Phillips Curve (ICPC), an augmented New Keynesian Phillips curve in which firm-level marginal costs of producing differentiated goods include a non-trivial AI inference component lambda-bar, and prove a closed-form structural slope kappa*_inf = lambda-bar * kappa, where kappa is the standard Calvo-Yun slope. We derive a welfare-relevant Hicks-Kaldor decomposition of consumer welfare under inference-cost shocks, prove a generalized Taylor principle for the inference-augmented economy, and characterize the optimal monetary policy response coefficient psi*_inf = (1 + phi*rho) * lambda-bar * kappa under commitment. A second-order welfare loss formula closes the model in closed form. We confront the theory with U.S. monthly data 2022:M01-2026:M04 using a two-step GMM estimator with Newey-West HAC standard errors and Hansen J-test, recovering an empirical slope kappa-hat_inf = 0.087 (HAC s.e. 0.021) which lies within one standard error of the structural prediction. A scaling regression over 50 rolling-window subwindows yields b-hat = 0.987 (R^2 = 0.998), consistent with a near-unit-elasticity pass-through. A G7 reduced-form panel with Driscoll-Kraay HAC standard errors yields b-hat^G7 = 0.094 (s.e. 0.026), and a Wald test fails to reject cross-country homogeneity (p = 0.78). The framework provides a single equilibrium scaffold for the joint study of AI inference cost dynamics, monetary policy under generative-AI shocks, and the welfare cost of inference-driven inflation.

Generative artificial intelligence is rapidly transforming the supply side of training data: an increasing share of new tokens, images, and structured records is produced by previous-generation models rather than by human originators. Recursive training on such synthetic content induces a measurable and often irreversible loss of distributional fidelity, a phenomenon known as model collapse. We develop the first unified microeconomic theory of synthetic data markets under model collapse. We introduce the Synthetic Data Contamination Equilibrium (SDCE), prove existence and generic uniqueness, derive a welfare decomposition W = W_prod + W_cons - L_coll - L_info, establish a Wasserstein-gradient-flow mean-field collapse limit, prove an impossibility of information-constrained implementation, and obtain closed-form expressions for the welfare-maximizing provenance subsidy s* = KL(q||p)/(2 kappa) and the welfare-maximizing watermark strength w* = (1 - psi) KL(q||p)/(2 kappa psi). We prove an information-theoretic Cramer-Rao lower bound on any provenance estimator using only producer-side observations and show that the Provenance-Market Iterative Retraining (PMIR) algorithm attains this bound up to constants while converging to an epsilon-SDCE in O(epsilon^-2 log T) iterations. A reduced-form OLS estimation on a C4-synthetic benchmark over ten retraining generations yields a collapse-rate coefficient b-hat = 0.181 (HAC s.e. 0.024), within one standard error of the structural prediction 0.183. Calibrated experiments raise generation-ten model quality by 23.1 percent over the unregulated benchmark while lowering the 2-Wasserstein drift on a held-out diversity probe from 0.318 to 0.142. Scaling experiments over generations t in {1,...,10} recover a logarithmic-in-t collapse law log Q_t = log Q_0 - 0.183 t rho^2 with R^2 = 0.962.

Prediction markets are powerful mechanisms for information aggregation, but existing designs are optimized for single-event contracts. In practice, traders frequently express beliefs about joint outcomes - through parlays in sports, conditional forecasts across related events, or scenario bets in financial markets. Current platforms either prohibit such trades or rely on ad hoc mechanisms that ignore correlation structure, resulting in inefficient prices and fragmented liquidity. We introduce ParlayMarket, the first automated market-making design that supports parlay-style joint contracts within a unified liquidity pool while maintaining coherent pricing across base markets and their combinations. Our main result is a convergence characterization of the resulting system. Under repeated trading, the AMM dynamics converge to a unique fixed point corresponding to the best approximation to the true joint distribution within the model class. We show that (i) parameter error remains bounded at stationarity due to a balance between signal and noise in trade-induced updates, and (ii) pricing error and monetary loss scale with this parameter error, implying that aggregate market-maker loss remains controlled and grows at most quadratically in the number of base markets. These results establish explicit limits on the information-retrieval error achievable through the trading interface. Importantly, parlay trades play a structural role in this convergence: by providing direct constraints on joint outcomes, they improve identifiability of dependence structure and reduce steady-state error relative to markets that rely only on marginal trades. Empirically, we show both in controlled simulations and in replay on historical Kalshi parlay data that this design achieves the intended scaling while remaining effective in realistic market settings.

Stochastic optimal control control problems with merely measurable coefficients are not well understood. In this manuscript, we consider fully non-linear stochastic optimal control problems in infinite horizon with measurable coefficients and (local) uniformly elliptic diffusion. Using the theory of $L^p$-viscosity solutions, we show existence of an $L^p$-viscosity solution $v\in W_{\rm loc}^{2,p}$ of the Hamilton-Jacobi-Bellman (HJB) equation, which, in turn, is also a strong solution (i.e. it satisfies the HJB equation pointwise a.e.). We are then led to prove verification theorems, providing necessary and sufficient conditions for optimality. These results allow us to construct optimal feedback controls and to characterize the value function as the unique $L^p$-viscosity solution of the HJB equation. To the best of our knowledge, these are the first results for fully non-linear stochastic optimal control problems with measurable coefficients. We use the theory developed to solve a stochastic optimal control problem arising in economics within the context of optimal advertising.