Papers

We introduce ALM-GARCH, an asymmetric long-memory GARCH model in which positive and negative innovations enter conditional variance with different injection amplitudes and kernel offsets. These departures define testable level and memory channels relative to a nested symmetric benchmark. Positive Harris recurrence holds for interior configurations under a Foster-Lyapunov condition. Across five equity indices and Bitcoin, joint symmetry is rejected throughout, driven primarily by the level channel. The memory channel is supported for the Nikkei 225, KOSPI, and Bitcoin but is weakly identified when the positive branch is nearly inactive. Out-of-sample performance is broadly comparable to standard benchmarks.

This study investigates the spatial relationships among housing-market appreciation, housing affordability, and automobile commuting to Toronto across 23 census metropolitan areas and municipalities in southern Ontario from 2016 to 2021. Utilizing Statistics Canada Census data, the analysis employed linear and quadratic ordinary least-squares regression, Global and Local Moran's I, and residual spatial diagnostics to assess geographic patterns in average dwelling values, owner shelter-cost burden, and lone-driver commuting. The study found that average dwelling values increased significantly throughout the region, maintaining a strong nonlinear relationship with distance from Toronto, which indicates a persistent metropolitan accessibility gradient. Commuter volumes also demonstrated pronounced nonlinear distance gradients; however, housing appreciation was not significantly correlated with percentage changes in commuting ($R^2$ = .045, p = .331), suggesting that the expansion of the housing market did not result in proportional growth in Toronto-bound automobile travel. The shelter-cost burden exhibited weaker distance relationships and greater residual spatial dependence, indicating localized affordability influences not fully explained by distance or dwelling values. Overall, the findings suggest an increasingly extensive regional housing market with spatially heterogeneous affordability and commuting outcomes, highlighting the importance of integrating housing, transportation, and regional planning.

Optimal transport provides a common language for allocation, equilibrium, computation, and inference. Its primal problem assigns mass or agents, while its dual variables admit economic interpretations as utilities, prices, and scarcity rents. This review explains why this combination has proved unusually effective in economics. We first present the core results, including Kantorovich duality, integrality, cyclical monotonicity, the canonical distance and quadratic costs, and entropic regularization. We then trace the field's development from planning and operations research to modern analysis, statistics, and computation. The economic literature is organized around two roles for transport: as a model of matching, trade, hedonic equilibrium, and aggregate assignment; and as a tool for coupling distributions, measuring discrepancies, constructing multivariate ranks, solving inverse problems, and certifying economic conclusions. We conclude by examining extensions beyond transferable utility, one-to-one matching, static allocation, and unconstrained transport, together with open questions involving learning and identification across multiple markets.

Investment performance is commonly presented either as a conventional cumulative-return chart, which fixes a historical starting date and traces performance forward, or as a trailing-return table, which fixes the current endpoint but reports only a small set of prespecified horizons. These two displays have complementary limitations: fixed-start comparisons are conditional on the selected origin, whereas trailing returns provide only discrete snapshots of the underlying fixed-endpoint return function. We present the Return-to-Present (RTP) curve as a continuous fixed-endpoint representation that brings these perspectives together by holding the evaluation date fixed while allowing the hypothetical historical purchase date to vary over the available history. Familiar 1-month, 3-month, 6-month, 1-year, and longer trailing returns therefore become selected points on a continuous curve. When multiple investments are overlaid, RTP directly displays entry-date sensitivity, persistent relative advantage, crossings, and the timing and magnitude of separation without requiring selection of a single historical origin. The same endpoint-based construction naturally accommodates investments with unequal inception dates, recurring purchases, and retrospective portfolio rotation decisions in which sale and replacement-purchase dates may differ. We illustrate these uses with real investment data and discuss its relationship to momentum. RTP does not define a new return measure; its contribution is a simple graphical organization of familiar realized returns for historical comparison and decision support rather than prediction or statistical inference.

Pathwise differentiation of Monte Carlo estimators fails at payoff discontinuities, producing zero or biased sensitivities for barriers, autocallables, and digital options. The industry workaround — smoothing the indicator functions — introduces bias and requires per-product calibration. We derive a correction formula that restores unbiased Greeks without smoothing. For a payoff $F(Z,\theta)$ that is piecewise smooth with discontinuities on surfaces $\{g_i = 0\}$, we show that the sensitivity decomposes into a pathwise term (computed by standard AAD) plus a sum of boundary corrections, each involving the payoff jump, the Gaussian density at the boundary, and the sensitivity of the boundary to the parameter. The correction is computed by Newton root-finding in the normal-random space, with the jump evaluated by two forward replays of the pricing kernel. The implementation uses AADC (pip install aadc), whose tape replay and automatic discontinuity tracking make the method fully automatic — the quant writes standard pricing code, and the correction driver identifies and handles all discontinuities. We prove the formula for arbitrary compositions of smooth functions and indicator functions (not just outer products), covering real autocallable payoff structures with recursive alive/dead logic. Benchmarks on QuantLib models (GBM, Heston, Hull-White) show all Greeks within 0.1–4% of analytic or bump-and-revalue references.

The relationship between investment policy associated with species growth profile is essential in seeking the most appropriate strategy for a policymaker. Balancing maximum profit with the sustainability of species remains a central issue in both ecological and economic contexts. This study presents a comparative analysis of two interest principles, annuity and compounding, within the framework of optimal control. Various investment policies are examined from the perspective of capital theory, incorporating concepts such as future value, accumulation function, and force of interest, each contributing to the formulation of an optimal control strategy. Our analysis is based on a one dimensional logistic model incorporating linear harvesting. Key parameters include the species growth rate and interest rate, and optimality is evaluated with respect to these variables. Using Pontryagins Maximum Principle, we derive the optimal harvesting policies under both discounting laws and characterize the resulting steady state equilibria. The principal finding indicates that for species with low intrinsic growth rates and low annual interest rates, the annuity law of interest yields optimal outcomes. Conversely, for any annual interest rate, species exhibiting moderate or high growth rates maximize profit under the compound law of interest. The study also addresses maximum net revenue and optimal strategies for varying growth rates under each interest law.

In this note, we introduce a new comonotonic approximation for sums of lognormal random variables based on the famous Perron-Frobenius theorem.

Understanding the joint dynamics of prices and trades is central to market microstructure, where returns and order flow interact through nonlinear and state-dependent mechanisms. Linear models are interpretable but may miss these effects, while deep neural networks improve forecasting at the cost of transparency. We use neural networks as tools for structural discovery rather than only for prediction. A deep feed-forward network is trained on high-frequency returns and signed volumes for large- and small-tick stocks and compared with a linear VAR benchmark. The neural network improves predictive performance, especially for returns, revealing nonlinear dependencies beyond the linear specification. Using Shapley-based explainability, we show that the dominant contributions are concentrated at the most recent lags. Model-implied responses are consistent with conditional averages reconstructed from the data. Unlike empirical averages, however, the neural-network decomposition isolates individual regressor contributions to the aggregate dependence. Lagged signed volume generates sign-preserving and saturating effects, consistent with nonlinear price impact and order-flow persistence. Lagged returns act as state variables: when the previous trade does not move the price, the model predicts continuation in the direction of past order flow, whereas non-zero returns generate attenuation or reversal. Building on these findings, we introduce a parsimonious SHAP-inspired nonlinear parametric model. It reproduces the main return-volume dependencies, outperforms the linear VAR benchmark, and achieves performance comparable to the neural network. A multi-lag extension captures residual longer-memory effects while preserving interpretability. Overall, explainability offers a route from black-box prediction to economically meaningful parametric models of price and trade dynamics.

Why China Succeeds offers what no existing book does: a single, unified explanatory framework that traces China's rise from its ancient civilizational foundations to its twenty first century technological ascent. Rather than treating China's success as ideologically exceptional or historically accidental, it reveals the universal institutional logic (regulated social mobility, functional land and taxation systems, and formidable state capability) that has sustained Chinese governance across millennia and powered its modern economic miracle. The book directly challenges Western development orthodoxy by demonstrating that institutions can be built through growth, not before it. For policymakers, scholars, and development practitioners worldwide seeking transferable lessons from the world's most consequential development story, this book provides the most historically grounded, analytically rigorous, and forward-looking account available.

We propose a new model of expected stock returns that incorporates quantity information from market trading activities into the factor pricing framework. We posit that the expected return of a stock is determined by not only its factor risk exposures (beta) but also the factor's quantity fluctuations (q) induced by trading flows, and hence term the model beta times quantity (BTQ). The rationale is that sophisticated investors should demand a higher factor premium when they have absorbed noise trading flows of stocks with high loadings to that factor. The BTQ model provides a compelling risk-based explanation for stock returns, which is otherwise obscured without considering the quantity information. The cross-sectional risk-return association, which is nearly flat unconditionally, strongly depends on the quantity variable. The structured BTQ model reliably predicts monthly stock returns out of sample, and addresses the factor zoo problem by selecting a small number of factors.

Creativity researchers often distinguish between two stages of the creative process: generation versus selection. While much is known about the psychology of idea generation (e.g., the factors that lead to a greater number of novel and useful ideas), less is understood about the nature of selection, or how generation and selection interact. Here we investigate how the act of generating ideas may potentially distort the selection process. Using an incentive-compatible paradigm in which pairs of participants reviewed the same ideas and were rewarded for submitting only high-quality ideas, we find that people submit a greater number of lower-quality ideas when selecting among their own ideas than when selecting among another person's ideas (the Creative Endowment Effect). This effect generalizes across three tasks in two domains and is resistant to an informational intervention (i.e., explicitly telling people about the effect). However, having participants revisit their ideas several months later increases their selectivity. The broader implications for individuals and organizations are discussed.

We consider the Heston model with perfect negative spot–variance correlation and its one-dimensional local-volatility projection. Let $I_T^{\mathrm H}$ and $I_T^{\mathrm{LV}}$ denote their respective integrated variances over $[0,T]$. We establish the inequality \[ \mathbb{E}\bigl[(I_T^{\mathrm H}-K)^+\bigr] < \mathbb{E}\bigl[(I_T^{\mathrm{LV}}-K)^+\bigr] \] for every maturity $T>0$ and every strike $K>0$. Consequently, Heston integrated variance is strictly smaller in convex order than the integrated variance of the calibrated local-volatility model. This strict ordering gives a Heston-model counterexample to the convex-order inequality conjectured by J. Gatheral.

Artificial intelligence (AI) now supports investment workflows from data and prediction through research, portfolios, execution, and tool use. Technical capability, however, is not evidence of investment profitability. This critical state-of-the-art review examines public research available through 31 August 2026 on listed equities, exchange-traded funds, centralized crypto spot, perpetual futures, and on-chain markets. We organize evidence with an alpha-translation chain: point-in-time information must yield a stable signal, feasible positions, executable orders, and risk-adjusted returns after costs. Across machine learning, time-series foundation models, financial language models, reinforcement learning, and agents, the examined record shows real but mainly upstream progress in prediction, text processing, portfolio design, and workflow integration. Evidence is thinner for durable net performance. Temporal contamination, repeated selection, survivorship, weak benchmarks, implementation costs, venue mechanics, and capacity can break translation to net alpha. Strong historical results coexist with predictor decay, corrected look-ahead failures, mixed prospective evidence, and few audited live-capital records. Crypto adds informative state but requires separate treatment of spot, perpetual, and decentralized cash flows and execution. Within the public evidence examined here, no general AI architecture is shown to deliver persistent, cross-regime, capacity-aware net alpha. More credible claims require point-in-time data and models, decision-aligned objectives, joint portfolio–execution evaluation, controlled adaptation, prospective tests, and authority-matched governance. These conditions can improve evidence and implementation; they do not guarantee profit.

Transaction costs can make or break a trading strategy, particularly in relative-value trading of commodity and macro markets, where edges are a few basis points. Price impact is a central component of transaction cost. Price impact models usually include self-impact (a trade in a contract moves that contract's price) but omit two well-documented effects: cross-impact (a trade in one contract also moves the prices of related contracts) and transient impact (price impact decays over time, so an unwind recovers part of the entry cost). A model without these effects overprices the impact of relative-value trades, whose correlated legs are built and unwound over days, and so forgoes potentially profitable trades. This paper models both effects with a convex quadratic cost. In each period, a positive semidefinite matrix built from volatility, volume, and correlation forecasts couples trades across contracts. A power-law decay kernel then couples trades across periods. The resulting cost admits no price manipulation even when liquidity varies over the planning horizon. The model is demonstrated empirically on calendar spread trading of crude oil futures around the commodity index roll.

This paper develops a framework to assess loan portfolio budget in credit portfolios exposed to climate risk over a 3-5 year horizon. Using short-term scenarios from the NGFS, the approach translates transition and physical risk pathways into changes in obligor default risk. Firm performance is modeled within a structural credit risk framework where scenario-dependent climate shocks adjust the drift of firm value dynamics. Defaults occur when firm value falls below a liability threshold. Joint defaults are simulated using Monte Carlo methods with dependence captured via principal components. Resulting default-probability estimates inform a constrained optimization used to examine lending allocation across exposures. Climate scenario choice affects model-implied default probabilities and the resulting risk-return tradeoff across obligors and sectors. The results show scenario-specific differences in default-probability distributions, upper-tail risk, and lending allocation patterns. Under the benchmark synthetic portfolio, HWTP produces the highest mean and upper-tail PDs, while SWUC produces the lowest mean and median PDs. These rankings are model-implied and calibration-dependent rather than empirical rankings of climate-scenario severity. The framework remains transparent and can be refined as more granular climate and firm-level data become available. The framework helps banks link NGFS scenarios to sector-level credit risk and portfolio loss outcomes. It can support ICAAP and climate stress testing by highlighting exposures most sensitive to climate risk, adding a forward-looking overlay to existing models.

Herein, we propose a quantum circuit learning framework for modeling the realized volatility (RV) of Bitcoin and investigate the statistical properties of the predicted time series through multifractal analysis. Unlike conventional GARCH-type models, which require a pre-specified functional form for the volatility process, a parameterized quantum circuit directly approximates the volatility function from empirical data, eliminating the need for explicit model selection. Using five-minute Bitcoin price data, we construct daily RV, train a single-qubit parameterized quantum circuit, and generate a long synthetic time series from the optimized quantum circuit. Multifractal Detrended Fluctuation Analysis is applied to calculate the generalized Hurst exponent $h(q)$, the singularity spectrum $f(\alpha)$, and the multifractal scaling exponent $\tau(q)$. The predicted return series exhibits $h(2)\approx 0.5$, consistent with near-random dynamics, and both the predicted and the empirical return series display multifractality that partially persists after random shuffling. The increment series of RV shows pronounced anti-persistence with $h(2)\approx 0.05$–$0.1$, consistent with the rough volatility hypothesis. These results demonstrate that a simple single-qubit parameterized quantum circuit captures qualitatively some observed properties in Bitcoin volatility dynamics.

Modern portfolio theory identifies diversification as the primary tool for risk reduction. However, under model uncertainty, this cornerstone may no longer remain optimal. This paper investigates the tension between portfolio diversification and concentration under dependence uncertainty. In the absence of model uncertainty, we employ the framework of the majorization order and doubly stochastic matrices to formalize the degree of diversification, and prove that quasi-convexity is a necessary and sufficient property for a risk functional to be weakly consistent with the majorization order. We further derive worst-case risk measure inequalities and solve robust portfolio selection problems for a broad class of risk measures, including VaR, ES, Range-VaR (RVaR), and standard deviation (SD). Our results reveal a ”concentration paradox” for many widely-used risk functionals: when the dependence structure is fully ambiguous, robust optimization often recommends concentrating investment in a single asset to hedge against the worst-case dependence scenario. As an application, we propose a weighted robustness formulation that interpolates between a reference dependence structure and the worst-case structure. The formulation is structurally analogous to the constrained/unconstrained Expected Shortfall blend in the Fundamental Review of the Trading Book (FRTB) and provides a theoretical foundation for balancing diversification against robustness in the presence of model uncertainty.

Let a finite population of n labelled examples carry a class-weighted loss, with pi*n in a rare positive class weighted by N0/N1. We study estimation of total risk from a subsample K << n under designs allocating K0 and K1 draws to the two strata. We derive the exact finite-population variance of the weighted risk estimator under class-conditional sampling without replacement and solve for the optimal allocation. The class multiplier inflates positive-stratum dispersion by the imbalance ratio, causing that ratio to cancel from the optimal allocation and making equal, rather than proportional, allocation the natural default. Simple random sampling is dominated by an explicit between-stratum term; an exact bias identity shows that cluster-representative selection has no general unbiasedness guarantee; and a Serfling bound transfers the allocation result to selection error over a finite candidate set. Under the implemented truncation, the realised allocation ratio is gamma=min(2*pi/f,1), independent of n, yielding the parameter-free efficiency prediction A(pi,f)=gamma/[pi(1-pi)(1+gamma)^2]. A separate measurability result bounds the record occupied by a labelled example, determining the required train-test separation and controlling departure from block independence under absolute regularity. We test these predictions on forecasting the onset of statistically explosive price regimes, dated ex post by the Phillips-Shi-Yu procedure, using 350 U.S. equities from 2004-2011 with under 1% positive rows and five purged forward blocks. The predicted ordering of the four designs holds, and at the 10-day horizon the five design points are ordered exactly as predicted by A (Spearman rho=1, exact p=0.0167). The predicted dependence on pi across horizons does not hold; we identify the channels lying outside the design-based argument.

We develop a global martingale optimal transport framework for joint S&P 500 (SPX)-VIX smile calibration across multiple maturities, without the conditional independence that Markovian stitching imposes between months. We prove that exact local and global feasibility are equivalent, yet the stitched laws, which carry earlier months only through the current SPX level, can form a strict subset of the global ones, so adjacent smiles cannot identify the dependence across months. We show that relative entropy against the standard Markov reference selects the stitched law, so this dependence must be supplied deliberately. We supply it through a finite-memory reference, in which a latent autoregressive state drives the VIX levels while every VIX marginal stays exact, and calibrate the resulting law on a junction tree whose size grows linearly with the number of maturities. On market data with up to nine SPX maturities, a law with memory and a law without it fit the same quotes but price VIX-conditioned SPX Asian claims differently: on every calendar, memory makes a claim on the maximum VIX cheaper and a claim on the minimum VIX dearer. Varying the memory strength on one calendar moves these differences steadily from zero, so the vanilla quotes, which fix the law of each date, do not determine prices that depend on the joint law across dates.

Robust portfolio rules that reconstruct confidence sets after learning need not preserve the evaluator obtained by prior-by-prior Bayesian transport. In the Gaussian model, this discrepancy is summarized by natural-coordinate displacement: inherited transport preserves it whereas fresh reconstruction can replace it. We price evaluator replacement and trace the resulting optimized curvature through endogenous research. Optimized robust value represents protocol regret as a functional Bregman divergence, while a within-vintage rectangular Gaussian benchmark with constant absolute risk aversion (CARA) yields a stopped recalibration tax. In a versioned model-release economy, validated history propagates through a strictly causal network and a same-cycle share of current optimized marginal value feeds back into research supply. The capacity-constrained equilibrium reduces to a scalar equation with protocol-indexed gain \(\mathfrak g_I^P=\lambda\beta_{R,I}(W_R^P)''\). Purely causal validation cannot create a same-cycle unit mode; provenance changes criticality through optimized curvature. For a scalar primitive supplier-score shock \(z\) in direction \(h_I\) and financial outcome \(\mathcal O\), sensitivity factors as \(\omega_{\mathcal O,h,I}/(1-\mathfrak g_I^P)\). Conditional on a smooth equilibrium state and active cell, completion-time information sharply bounds this multiplier when all compatible timing laws are subcritical; no finite uniform bound exists when the timing set reaches the pole.

The comparative analysis of banks' financial statements poses significant challenges for automated question answering systems due to their complexity, substantial length, technical language, and inhomogeneity of both textual and numerical content across different jurisdictions and institutions. We introduce FinRAG-QA, a novel benchmark dataset for financial question answering, which comprises 999 practitioner-curated questions on 10 standardised indicators, grounded in 209 annual and Pillar 3 reports from 24 major European and U.S. banks spanning 2019-2023. Unlike prior financial QA benchmarks, which centre on U.S. filings and single-institution analysis, FinRAG-QA targets cross-institutional retrieval over documents averaging 198k words, longer than any existing financial QA resource. On this benchmark we evaluate a multi-stage RAG pipeline and isolate the contribution of each component. Contextual chunk enrichment combined with a retrieval-optimised embedding model raises NDCG@10 from 0.322 to 0.710; conditional on the ground truth being retrieved, a reasoning-optimised generator raises answer accuracy from 44.6% to 79.0% (+34.4 percentage points), at roughly 20x the generation latency. We further show that cross-encoder reranking degrades retrieval when the first-stage ranking is already strong, and that a single top-ranked chunk outperforms larger contexts at generation time. Experiments were run in late 2024-early 2025 with the models available at that time.

Portfolio replication, or the construction of a tradable basket of assets to match the risk-return profile of a target benchmark, is fundamentally an ill-posed inverse problem. When restricted to a subset of available assets, classical variance-minimizing models often yield unstable, over-leveraged portfolios highly vulnerable to market shocks. We propose a unified, two-stage methodology rooted in information theory to achieve robust portfolio replication. First, we model the constituent asset returns against target factors, estimating parameters within data-driven empirical bounds via an entropy minimization principle. Second, using the same entropic approach, we determine the optimal weight replication. In both cases we use an entropy function of the Fermi-Dirac type defined directly on sets of constraints of the inverse problem. We validate this Entropic Factor Model (EFM) against standard Ordinary Least Squares (OLS) across five numerical experiments, including standard equity tracking, multi-asset synthesis, and severe stress-test scenarios. Empirical results demonstrate that the EFM consistently outperforms OLS in terms of annualized turnover and net-of-fees returns. Crucially, during the COVID-19 market crash and under severe idiosyncratic data corruption, the entropic framework acts as a probabilistic “circuit breaker", defensively reducing capital allocation to compromised assets and providing a highly robust, risk-averse solution for generalized portfolio replication.

Language models used in financial backtests suffer from look-ahead bias, as a model trained on text published after the study period has already observed the outcomes it is asked to predict. To handle this issue, point-in-time (PIT) language models are pretrained on chronologically filtered corpora and released as one checkpoint per calendar year, each with a documented cutoff. However, each additional year costs a full pretraining run, and whether that run is necessary has never been tested. In this paper, we show that the annual pretraining run is not necessary. We instead compare each checkpoint against the newer one that replaced it, and find that the newer checkpoint scores no better on the same evaluation window. Motivated by this observation, we propose PALM (Point-in-time Adaptation for financial Language Models), a simple yet effective alternative to annual pretraining that fits a low-rank adapter on text published before the decision date without modifying any pretrained weight. We further find that a small adapter is enough to add a new period to the knowledge an old checkpoint already encodes, and that this outperforms continued pretraining. We validate PALM on a decade of financial news and on various families of PIT models, whose cutoffs span two decades and whose sizes range from 1.3 to 4.2B. Code is available at: https://github.com/seunghan96/palm.

Validating a model on a time series asks for three things at once: each training run should use most of the sample (sufficiency), the test sets should together cover most of the sample (coverage), and training data should come before test data (causality). We prove that the three cannot be had together and price each one. Let $\alpha$ be the smallest training fraction over folds, $\beta$ the fraction of the sample covered by tests, $\Lambda$ the fraction of the sample used as training data from the future of a test point, and $\delta$ the distance from a test point to the nearest training point in its future. Every scheme on a sample of length $T$ satisfies $\alpha+\beta \le 1+\Lambda$ and $\alpha+\min\{\beta,\delta/T\} \le 1$, and under $\beta$-mixing the leakage bias at a test point is at most $2M\beta_{\mathrm{mix}}(\delta)$. In words: going beyond the causal frontier $\alpha+\beta=1$ requires training on the future; that future data must sit within $(1-\alpha)T$ of a test point; and its harm depends on its distance, not its amount. Hence expanding walk-forward is exactly the Pareto frontier of causal validation, $k$-fold cross-validation buys the most future data, and purged $k$-fold with an embargo pays in distance instead, which is cheap when the process forgets quickly but cannot repair the part of causality demanded by non-stationarity. On pure noise, shuffled 5-fold reports an information coefficient of $+0.32$, while contiguous 5-fold, using the same amount of future data, reports $+0.004$.

Large Language Models (LLMs) increasingly use user context such as memory, profiles, and role prompts to personalize their responses. This personalization can affect evidence-based judgment: the same evidence may lead to different conclusions under different user contexts. Finance provides a high-stakes setting to study this problem because decisions often depend on interpreting long and complex documents. We test this using 3,575 SEC filings across twelve LLMs. We compare persona-conditioned retrieval, neutral retrieval, and memory-framed context to separate the effect of evidence selection from the effect of interpretation. We find that most user-context spillover comes from how models interpret the same evidence under different roles, rather than from retrieving different evidence. We then test two simple mitigation strategies: expressing the same investor mindset as a user profile instead of an assistant role, and separating evidence-based and personalized outputs. Both reduce spillover, but neither removes it completely, and their effectiveness varies substantially across models.

Although market participants generally have access to a common information set, they make decisions based on forecasts formed over heterogeneous horizons. Because market impact depends on aggregate positions rather than trader identities, these decisions feed back into prices through their collective effect. We introduce a linear mean-field model of this interaction. The observed price is decomposed into a martingale component, a common predictable signal represented by a Volterra process, and the market impact generated by aggregate positions. Agents take positions according to conditional forecasts of future signal increments and a fraction of anticipated aggregate impact over their respective horizons. Within a Gaussian-Volterra framework, we characterize equilibrium through a linear fixed-point equation for aggregate positions and establish existence and uniqueness under explicit conditions. At equilibrium, we identify a balance condition that cancels the direct transmission of the common signal to the observed price. We then study the limit in which agents fully account for market impact. Along a suitably scaled family of equilibria satisfying explicit conditions, the contributions of the predictable signal and the market impact cancel in the limit, and the observed price converges to its martingale component. For fractional-type signals and Gamma-distributed horizons, we further derive local Hölder bounds and identify the horizon distributions for which the observed price has local regularity compatible with that of Brownian motion.

Scaling laws in modern deep learning describe how held-out loss improves as model capacity, training data, and compute increase, often following power-law trends. We investigate whether analogous scaling regularities arise in actuarial ratemaking, where data are tabular, heterogeneous, and noisy, and where classical models such as GLMs remain strong baselines. Using a real-world motor insurance portfolio, we train models from different families across increasing fractions of the training data and multiple random seeds, evaluating out-of-sample Poisson deviance, a likelihood-based loss for Poisson count predictions in which lower values indicate better held-out fit. We find that all model families improve with additional data, but scaling exponents differ substantially: TabM exhibits markedly stronger data scaling than purely supervised tabular Transformers and standard MLP baselines. Transformer variants show weak parameter scaling unless augmented with additional inductive biases (TabM-style adaptation or self-supervision). These results provide quantitative guidance on model selection by data regime and suggest that effective scaling on actuarial tabular tasks depends on architecture and loss function objective design, with simple increases in Transformer size providing limited gains.

Reputation is a fundamental mechanism through which markets sustain trust when service quality cannot be perfectly assessed ex ante, constituting a form of intertemporal economic capital by attracting future demand. Its effectiveness as a disciplinary mechanism depends not only on past interactions but also on the persistence of the identity to which reputation is attached. When identities can be abandoned and recreated cheaply, reputational capital may itself become an object of opportunistic exploitation. This paper develops a dynamic economic framework to study when reputation is sufficient to discipline autonomous agents. We model reputation as capital attracting future economic activity. At each point, an agent chooses between operating honestly, investing in quality to preserve future gains, or executing a one-shot deviation to extract its reputation's value and restart from a penalized identity. Our analysis relates the temptation to opportunistic behavior to identity-reset costs, reputation persistence, demand sensitivity, and enforcement design, deriving comparative statics on optimal quality provision. Autonomous AI-agent operating on the blockchain are a relevant application: infrastructures such as ERC-8004, ERC-8183, and x402 combine reputation, identity, and payments in permissionless markets. Nonetheless, our framework applies to any environment where reputation generates future business and identities are replaceable.

People increasingly use language models to support life decisions. Many such decisions involve a probabilistic forecast: How likely is a major life event, a natural disaster, or an economic outcome? Users of language models may implicitly trust that these forecasts fall out of a coherent world model. In this paper, we evaluate the coherence of language model probabilistic forecasts through a procedure that builds on a theorem due to de Finetti. We elicit forecasts from language models across events generated from stock returns data. We then use linear programs to compute the largest Dutch-book profit - the profit an arbitrageur could guarantee by betting against model-generated probabilities - which we use as a measure of incoherence. Our procedure does not require outcome labels, so we can evaluate coherence even in settings where outcomes are not observed or have not yet resolved. We find substantial evidence of incoherence in language model forecasts. Such incoherence increases when there are richer logical relationships between events, and irrelevant contextual details can increase incoherence by an order of magnitude. We conclude by discussing how alternative training strategies may improve probabilistic coherence.

Modern portfolio management increasingly demands a balance between traditional risk-adjusted returns and strict Environmental, Social, and Governance (ESG) mandates. Current Reinforcement Learning (RL) approaches typically optimize for a single ESG provider, neglecting the significant divergence in rating methodologies across the industry and the unintuitive nature of manually weighting conflicting objectives. This paper addresses these limitations by formulating ESG-aware portfolio optimization as a Multi-Objective Reinforcement Learning (MORL) problem that simultaneously incorporates ratings from three distinct ESG agencies. To bridge the gap between high-dimensional algorithmic trade-offs and human decision-making, we integrate a Preference Elicitation framework using Gaussian Processes. This system enables practitioners to infer their latent utility functions through intuitive pairwise comparisons of candidate portfolios based on their Sharpe ratios and aggregate ESG scores. We systematically evaluate our framework by employing Large Language Model (LLM) personas to simulate Portfolio Managers operating under varied regional contexts. Empirical results using historical market data reveal that regional backgrounds fundamentally shift the derived preference weights. For instance, European-based personas tend to prioritize ESG alignment over financial returns, while Texas-based personas favor risk-adjusted performance. This work offers a highly adaptable framework that successfully aligns multi-objective algorithmic trading with diverse, real-world human sustainability preferences.