Skip to content
Preprint

Robust Hedging Valuation Adjustment for Deep Hedging Policies under Market Frictions

Jul 2026 · 0 citations · 34 references
Economics

TL;DR

Robust hedging valuation adjustment (HVA) is applied as a post-training valuation-adjustment layer that evaluates tracking-loss CVaR together with explicit funding and margin add-ons together with explicit funding and margin add-ons.

Abstract

Hedging a derivative position under transaction costs and market frictions requires a trading rule that adapts to changing conditions. Deep hedging trains a neural policy for this task but policy training does not determine whether a trading desk can afford to run the policy. We apply robust hedging valuation adjustment (HVA) as a post-training valuation-adjustment layer that evaluates tracking-loss CVaR together with explicit funding and margin add-ons. The funding and margin add-ons share the same KL uncertainty set as HVA. For each policy, a single common-stress tilt computes HVA, funding and margin jointly and a trading desk can get one internally consistent reserve instead of the three separately. We compare classical hedge policies with learned hedge specifications across three market environments with different liquidity. No single specification dominates in every market. Under the strict tracking-risk budget, gamma-wide classical bands are selected in High and Middle Liquidity while sparse learned execution is selected in Low Liquidity. At looser validation budgets wider classical bands are generally selected.

View source

Similar papers

Open access Aug 2026

The Efficacy of “Deep Hedging” vs. Traditional Put-Overlay Strategies in 2025 Market Regimes

Classical put-overlays have long been treated as a reliable hedge against tail risk but the market conditions of 2025 expose their limits in ways that theory didn’t fully anticipate. This paper examines where these strategies break down: in markets defined by elevated volatility, wide bid-ask spreads, and structural frictions that quietly erode the protection investors thought they’d bought. Traditional hedging methods, which rely on the systematic purchase of out-of-the-money (OTM) options, are increasingly hampered by high premiums and reliance on static volatility assumptions. During the significant geopolitical disruptions of 2025, most notably the “Tariff Shock” of April, these traditional models proved inadequate, suffering from “premium bleed” and an inability to account for discontinuous market gaps. To address these systemic vulnerabilities, we formulate the hedging process as a stochastic control problem and implement a Deep Hedging framework utilising Deep Reinforcement Learning (DRL). Optimised specifically for Expected Shortfall (ES), the model utilises Long Short-Term Memory (LSTM) layers to process multi-dimensional state vectors, including implied volatility skew and realised turbulence. Our empirical results demonstrate that this AI-optimised policy achieves a 35% reduction in hedging costs while simultaneously improving tail risk protection and draw-down resilience. Notably, the DRL agent exhibits anticipatory behaviour, transitioning from a reactive to a predictive paradigm by adjusting hedge positions prior to observable volatility spikes. These findings suggest that in structurally incomplete markets, optimal risk management has evolved from simple insurance into a process of continuous, regime-aware policy optimisation. This study provides a robust framework for institutional solvency in an era defined by non-linear correlations and rapid liquidity decay.

Y. Chakrabarti · 0 citations
Preprint Jul 2026

Volatility in Prediction Markets: A Structural Approach

Forward-looking volatility forecasts are central inputs to derivatives pricing, market making, risk management, and volatility-linked trading strategies, with ARCH and GARCH models serving as the canonical workhorses. Such models are natural in standard asset markets, where prices are positive-valued stochastic processes and volatility is typically inferred from return dynamics. Prediction markets have a different structure: prices are bounded probabilities, payoffs are binary, and contracts resolve at known deadlines. We develop and estimate a volatility model tailored to binary prediction markets. The model combines two economic mechanisms: a Wright-Fisher deadline-resolution component, capturing how remaining binary uncertainty is forced to resolve over time, and a Glosten-Milgrom order-flow component, capturing volatility from informed trading as reflected in spreads and volume. Using a large panel of Kalshi contracts, we show that these structural variables carry substantial forecasting power. Plain ARCH/GARCH benchmarks are dominated by structural specifications; combining the structural model with residual GARCH dynamics gives the best overall forecasts. The model also provides an interpretable measurement framework: volatility is highest near fifty-fifty prices, rises near resolution, and varies across categories with the timing and discreteness of information arrival. Economics contracts are closer to smooth deadline-resolution dynamics, while sports contracts exhibit more event-concentrated, jump-like behavior. Across major categories, category-specific fitting does not systematically improve out-of-sample performance, suggesting that the structural specification transfers beyond the pooled headline result.

Weiye Xi, C. Moallemi, Mallesh M. Pai et al. · 0 citations
Open access Aug 2026

A Fractional-Rough Liquidity Model for Bitcoin Options: Implied-Volatility Asymptotics and Market Evidence

Bitcoin option prices reflect terminal variance and the cost of managing convex exposure in a market with changing depth and execution quality. This paper asks whether a liquidity state can be separated from fractional rough volatility in Bitcoin option valuation. The contribution is a modelling combination: standard stochastic-calculus and rough-volatility tools are joined to a regime-switching hedging-cost reserve, producing a leading-order at-the-money implied-volatility lift. The empirical design tests a liquidity–IV association and its scale using a 700-contract Deribit snapshot, a 4513-trade 24-h window spanning two UTC dates, a 775,315-trade panel over 92 dates, Ether replication, and placebos. The association is strong in open-interest-weighted specifications and for puts, but is absent for calls; it remains after controlling for option premium. Leave-one-expiry-out validation improves open-interest-weighted RMSE but not unweighted RMSE. A realised-volatility HMM is only a market-stress diagnostic, not an estimated liquidity regime. An empirical one-step hedging exercise does not validate the model’s simulated hedging comparative static. Accordingly, the evidence is associational, put-side, and narrower than a causal or fully structural validation.

E. Pindza, H. Mashele · 0 citations
Conference Open access Jul 2026

Research on Dynamic Portfolio Rebalancing Strategies with Explicit Consideration of Transaction Costs

Classical portfolio theory frequently assumes frictionless markets, but in reality, transaction costs, like fees and market impact, can erode returns and cause excessive turnover. Incorporating these costs transforms rebalancing from a mechanical rule into a strategic decision: determining exactly when and how much to trade to restore desirable exposures efficiently. This study proposes a dynamic rebalancing framework that explicitly models proportional transaction costs within a multi-period optimization setting. By introducing a transaction cost function, portfolio adjustment becomes a rigorous optimization problem balancing expected returns, risk exposure, and total rebalancing costs. This cost-aware framework empowers investors to avoid unnecessary trading, preserving risk control while improving net performance. To solve this, specific algorithmic procedures are designed to enhance computational efficiency in realistic, multi-asset scenarios. Empirical evaluations using historical financial data compare this cost-aware strategy against conventional periodic and threshold-based methods. Performance is assessed across metrics including cumulative return, portfolio volatility, turnover rate, and net returns after costs. The empirical results demonstrate that explicitly integrating transaction costs into optimization significantly improves strategy performance. The proposed model successfully reduces unnecessary trading activity and lowers portfolio turnover while maintaining competitive risk-adjusted returns. Furthermore, sensitivity analyses reveal that transaction cost levels dictate the optimal rebalancing frequency and adjustment magnitude. Overall, this study provides a systematic modeling framework and strong empirical evidence for cost-aware dynamic portfolio rebalancing, offering practical insights for investors navigating complex environments.

Zhenghao Liang · 0 citations
Preprint Jul 2026

Uniform-Loss Automated Market Making for Prediction Markets

The framework of loss-versus-rebalancing (LVR) is used to study how the total worst-case loss to the subsidizer is distributed across price states or over time and extended to dynamic liquidity management, showing that liquidity levels can be adjusted over time to implement a prescribed target expected cumulative loss schedule.

C. Moallemi, D. Robinson, Brian Z. Zhu · 0 citations
Aug 2026

Equilibrium Liquidity Premia under Hedging Pressure and Margin Constraints

We develop a continuous-time equilibrium model of futures markets in which heterogeneous hedgers and speculators trade under explicit margin constraints. Agents maximize exponential utility and take prices as given, while the equilibrium futures drift is determined endogenously through market clearing. Margin frictions interact with risk-sharing motives to generate a nonlinear fixed-point problem linking individual optimality to aggregate consistency. The equilibrium is characterized by a coupled Hamilton. Jacobi-Bellman (HJB) and backward stochastic differential equation (BSDE) system, and we establish existence and uniqueness of the equilibrium drift under mild regularity conditions. A central contribution of the framework is a new geometric characterization of margin effects: margin constraints create no-trade regions in drift space, producing a frictional wedge that forces the equilibrium drift to be the projection of the frictionless Keynes-Hicks drift onto a margin-dependent interval. This yields a kinked and convex mapping from margin tightness to liquidity premia, with one-for-one amplification when the frictionless drift lies outside the wedge and flat sensitivity once it lies inside. Unlike Brunnermeier-Pedersen [2009] and Gârleanu-Pedersen [2011], whose margin effects are linear and exogenous, our model delivers a fully dynamic, state-dependent amplification mechanism arising endogenously from equilibrium price formation. The structure provides a tractable foundation for empirical implementation using disaggregated trader positions. Using CFTC gold-futures data and CME volatility measures, we find strong empirical support for the model’s nonlinear amplification mechanism: hedging pressure alone has no predictive power; margin tightness exerts a negative baseline effect; the interaction between hedging pressure and margin tightness generates a statistically significant kink; and volatility sharply magnifies the impact of margin tightness, producing the largest and most significant effect in the data. These findings confirm the model’s core prediction that margin constraints generate nonlinear, state-dependent, and volatility-amplified liquidity premia, providing the first structural empirical evidence for a kinked margin-pressure mechanism derived from a full HJB-BSDE equilibrium.

Ryle S. Perera · 0 citations