{"paper_id":"2510.04569","title":"Risk-Sensitive Option Market Making with Arbitrage-Free eSSVI Surfaces: A Constrained RL and Stochastic Control Bridge","authors":["Jian’an Zhang"],"paper_date":"2025-10-06","paper_type":"theoretical","paper_url":"https://arxiv.org/pdf/2510.04569v1","page_url":"https://thequant.space/flowcharts/risk-sensitive-option-market-making-with-arbitrage-free-essv/","scores":{"empirical_rigor":7.8,"math_complexity":9.2,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a constrained, risk‑sensitive option market‑making control framework that jointly learns half‑spreads, hedge intensity and structured eSSVI surface deformations while enforcing static no‑arbitrage via a fully differentiable eSSVI layer.","quote":"We formulate option market making as a constrained, risk-sensitive control problem that unifies execution, hedging, and arbitrage-free implied-volatility surfaces inside a single learning loop. A fully differentiable eSSVI layer enforces static no-arbitrage conditions (butterfly and calendar) while the policy controls half-spreads, hedge intensity, and structured surface deformations (state-dependent rho-shift and","summary":"We formulate option market making as a constrained, risk-sensitive control problem that unifies execution, hedging, and arbitrage-free implied-volatility surfaces inside a single learning loop. A fully differentiable eSSVI layer enforces static no-arbitrage conditions (butterfly and calendar) while…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The action set is compact, rewards and penalties are bounded and locally Lipschitz in eSSVI parameters, and the Markov kernel is weakly continuous, ensuring well‑posedness of the CMDP.","type":"model","stated":"explicit","quote":"The action set is compact; r, ℓ, gj are bounded and locally Lipschitz in the eSSVI parameters under Assumption 1; and the Markov kernel P(·|s, a) is weakly continuous.","support":"full"},{"assumption":"Static no‑arbitrage constraints (butterfly and calendar) are enforced only on a finite lattice; dynamic arbitrage across time is not ruled out.","type":"market","stated":"explicit","quote":"Static (not dynamic) arbitrage. The BF/CAL penalties enforce static no-arbitrage on a finite lattice (§3.2).","support":"full"},{"assumption":"The simulation environment uses a Heston fallback model and ABIDES‑ready order‑flow intensities, abstracting away queue position, tick size, fees/rebates and latency.","type":"execution","stated":"explicit","quote":"Consequently, (i) order flow is exogenous and 16 (a) Per-step P&L distribution with tail markers (VaR5%, CVaR5%). Figure 2: Training dynamics, constraints, and behavior across episodes. summarized by smooth intensity maps (logistic in mispricing), (ii) queue position, tick discreteness, venue fees/rebates, and latency are abstracted away, and (iii) self-impact and cross-venue liquidity fragmentation are not modeled.","support":"full"},{"assumption":"The eSSVI parameterization follows the classical SSVI butterfly‑free sufficient condition and is squashed into the open interval to guarantee static arbitrage‑free surfaces.","type":"model","stated":"explicit","quote":"The classical SSVI butterfly-free sufficient condition is 0 ≤ψm ≤ 2 1 + |ρm| for all m, (3) which we enforce by a smooth squashing into the open interval [0, ψmax(ρm)) with ψmax(ρ) = 2 1+|ρ| −εψ for a small εψ > 0 [14].","support":"full"},{"assumption":"The CVaR regularizer uses a per‑step downside CVaR proxy estimated via Monte‑Carlo scenarios with Poisson order volumes and Gaussian price perturbations.","type":"statistical","stated":"explicit","quote":"In our setting we estimate a per-step downside CVaR proxy by sampling execution and price scenarios conditioned on (st, at). For each scenario we compute ˜ PNLt = PNLquote t (˜v) + hedget ∆net t ˜∆S, 7 and plug into the smooth RU objective \\ CVaR − q,t ≡min η∈R n η + 1 1 −q bE \u0002 sτ(η − ˜ PNLt) \u0003 o , (23) where sτ(x) is a temperature-τ softplus approximation of x+ = max{x, 0} and bE averages over the Monte Carlo","support":"full"}]},"datasets":{"status":"available","items":[{"name":"Synthetic Heston simulation","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":null,"quote":"In simulation (Heston fallback; ABIDES-ready), the agent attains positive adjusted P\\&L on most intraday segments while keeping calendar violations at numerical zero and butterfly violations at the numerical floor; ex-post tails remain realistic and can be tuned through the CVaR weight.","support":"full"}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"synthetic"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":null,"detail":"Reward includes an impact/fees term (− impact/fees) as part of the per‑step reward function.","quote":"The reward is Rt = spread revenue −impact/fees −λQ∥Qt+1∥2 −λarb Φarb(θt+1) | {z } butterfly & calendar surrogates and the training objective maximizes expected cumulative reward subject to a CVaR regularizer on episodic PnL: max π Eπ h X t γtRt i −λCVaR · CVaRq \u0000−PnL(τ) \u0001 .","source":"evidence_card","rule":"R2","candidates":{"front_matter":"unclear","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"Reward includes an impact/fees term (− impact/fees) as part of the per‑step reward function.","card_quote":"The reward is Rt = spread revenue −impact/fees −λQ∥Qt+1∥2 −λarb Φarb(θt+1) | {z } butterfly & calendar surrogates and the training objective maximizes expected cumulative reward subject to a CVaR regularizer on episodic PnL: max π Eπ h X t γtRt i −λCVaR · CVaRq \u0000−PnL(τ) \u0001 .","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"none","findings":[{"finding":"In simulation the agent achieves positive adjusted P&L on most intraday segments while keeping calendar violations at numerical zero and butterfly violations at the numerical floor.","kind":"performance","quote":"In simulation (Heston fallback; ABIDES-ready), the agent attains positive adjusted P\\&L on most intraday segments while keeping calendar violations at numerical zero and butterfly violations at the numerical floor; ex-post tails remain realistic and can be tuned through the CVaR weight.","support":"full"},{"finding":"Ex‑post tail risk remains realistic and can be tuned via the CVaR weight, demonstrating controllable tail‑risk shaping.","kind":"performance","quote":"In simulation (Heston fallback; ABIDES-ready), the agent attains positive adjusted P\\&L on most intraday segments while keeping calendar violations at numerical zero and butterfly violations at the numerical floor; ex-post tails remain realistic and can be tuned through the CVaR weight.","support":"full"}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":7,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":2,"extracted_at":"2026-11-14T19:47:20Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}