|
on Market Microstructure |
| By: | Zhuohan Wang; Carmine Ventre |
| Abstract: | Modern generative models for limit order books (LOBs) can reproduce realistic market dynamics, but remain fundamentally passive: they either model what typically happens without accounting for hypothetical future market conditions, or they require interaction with another agent to explore alternative outcomes. This limits their usefulness for stress testing, scenario analysis, and decision-making. We propose \textbf{DiffLOB}, a regime-conditioned \textbf{Diff}usion model for controllable and counterfactual generation of \textbf{LOB} trajectories. DiffLOB explicitly conditions the generative process on future market regimes--including trend, volatility, liquidity, and order-flow imbalance, which enables the model to answer counterfactual queries of the form: ``If the future market regime were X instead of Y, how would the limit order book evolve?'' Our systematic evaluation framework for counterfactual LOB generation consists of three criteria: (1) \textit{Controllable Realism}, measuring how well generated trajectories can reproduce marginal distributions, temporal dependence structure and regime variables; (2) \textit{Counterfactual validity}, testing whether interventions on future regimes induce consistent changes in the generated LOB dynamics; (3) \textit{Counterfactual usefulness}, assessing whether synthetic counterfactual trajectories improve downstream prediction of future market regimes. |
| Date: | 2026–02 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2602.03776 |
| By: | David Hirshleifer; Lin Peng; Qiguang Wang; Weichen Zhang; Xiaoyan Zhang |
| Abstract: | Generative AI use for content generation is associated with divergent outcomes on different financial social media platforms: indications of reasoning enhancement on Seeking Alpha, and of belief distortions on WallStreetBets. On Seeking Alpha, adoption is associated with information frictions. AI-assisted postings tilt toward analysis/credibility, and their sentiment positively predicts future returns. Use of AI is associated with more informative retail order flow and lower bid-ask spreads. In contrast, AI adoption on WallStreetBets follows surges in retail buying, and AI-assisted content is associated with emotionality and sentiment contagion. Such content precedes higher trading volume, greater volatility, and more lottery-like return distributions. |
| JEL: | D02 D82 D83 D84 D9 G11 G12 G14 G2 G4 G5 K22 O33 |
| Date: | 2026–02 |
| URL: | https://d.repec.org/n?u=RePEc:nbr:nberwo:34807 |
| By: | Ewens, Michael (California Institute of Technology); Faber, Jacob W. |
| Abstract: | Expanding retirement account access to alternative investments requires delivering illiquid returns to small-balance investors without compromising valuation integrity or liquidity. This paper studies the intermediation process using 110 registered interval and tender offer funds (>$100B AUM, 2015-2024) that offer periodic rather than daily repurchases. The performance gap between these vehicles and institutional drawdown peers averages approximately 130 basis points per quarter. A factor decomposition attributes roughly one-third of the gap to fees and a larger share to imperfect replication of the private-market return stream; liquidity buffers (8-15% of NAV) contribute at the margin. The funds hold an average of 76% illiquid assets, but valuations are frequently stale, with 40% of trading days recording zero NAV changes. Approximately 40% of interval funds face excess repurchase demand in a given quarter. Despite aggregate underperformance, retail-held assets generate comparable IRRs to same-vintage institutional peers while distributing significantly more cash, consistent with managers selecting liquid, distribution-friendly assets to satisfy repurchase obligations. The current equilibrium is one where regulatory frameworks permit access, but the structural costs of liquidity provision limit the transmission of the private equity premium to retail portfolios. |
| Date: | 2026–02–09 |
| URL: | https://d.repec.org/n?u=RePEc:osf:socarx:5897u_v1 |
| By: | Bali, Turan G.; Goyal, Amit; Mörke, Mathis; Weigert, Florian |
| Abstract: | We uncover momentum and reversal patterns in half-day option returns that persist for up to at least 20 business days, with economic magnitudes of 0.22% to 0.45% per half-day. Specifically, returns show strong momentum within the same period (e.g., intraday-to-intraday) but reverse sharply across opposite periods (e.g., intraday-to- overnight). These patterns increase over time, are robust to various delta-hedging schemes and option selection criteria, and persist across different subsamples. Mo- mentum and reversal strengthen when market makers actively manage capacity constraints during intraday-overnight transitions, indicating supply-side constraints drive predictability. |
| Keywords: | Option return momentum, Option return reversal, Intraday option returns |
| JEL: | G12 G13 G14 G11 |
| Date: | 2026 |
| URL: | https://d.repec.org/n?u=RePEc:zbw:cfrwps:336775 |