{"paper_id":"2506.22888","title":"SABR-Informed Multitask Gaussian Process: A Synthetic-to-Real Framework for Implied Volatility Surface Construction","authors":["Jirong Zhuang","Xuan Wu"],"paper_date":"2025-06-28","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2506.22888v1","page_url":"https://thequant.space/flowcharts/sabr-informed-multitask-gaussian-process-a-synthetic-to-rea/","scores":{"empirical_rigor":8,"math_complexity":8.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper introduces a SABR-informed multitask Gaussian process for constructing implied volatility surfaces from sparse option quotes.","quote":"This study introduces a SABR-informed multitask Gaussian process for constructing implied volatility surfaces from sparse option quotes.","summary":"Constructing the Implied Volatility Surface (IVS) is a challenging task in quantitative finance due to the complexity of real markets and the sparsity of market data. Structural models like Stochastic Alpha Beta Rho (SABR) model offer interpretability and theoretical consistency but lack…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Synthetic data is generated by a calibrated SABR model to capture structural patterns of volatility surfaces.","type":"model","stated":"explicit","quote":"In this paper, we used the SABR model [1] for incorporating financial theory to guide the model."},{"assumption":"The Heston stochastic volatility model provides realistic ground‑truth market behavior.","type":"model","stated":"explicit","quote":"We chose the Heston stochastic volatility model [14] for this purpose, as it generates complex volatility dynamics similar to real markets."},{"assumption":"Gaussian noise is added to synthetic volatilities to avoid over‑reliance on synthetic data.","type":"data","stated":"explicit","quote":"In practice, Gaussian noise ϵS ∼N(0, σ2 syn) is added to the synthetic volatilities to prevent the model from becoming overly dependent on the synthetic data."},{"assumption":"The target dataset is much sparser than the source dataset.","type":"data","stated":"explicit","quote":"When the target dataset DT is much sparser than the source dataset DS"},{"assumption":"Hierarchical regularization of task embeddings mitigates over‑fitting and negative transfer.","type":"statistical","stated":"implied","quote":"The task embeddings eS and eT are critical. Their locations in the embedding space determine how much structural information transfers between the SABR synthetic data and market observations."}]},"datasets":{"status":"available","items":[{"name":"Heston ground truth data","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":"synthetic market option contracts","quote":"We generated synthetic “market” data using the Heston model [14]"},{"name":"Synthetic SABR dataset DS","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":"dense synthetic option quotes","quote":"This synthetic dataset acts as a source of information to guide the learning process and prediction, especially in regions where market data is scarce."},{"name":"Market dataset DT","provider":null,"kind":"options","access":"unknown","period":null,"universe":"166 European call option contracts","quote":"we generated a dataset DT comprising N = 166 European call option contracts"}],"known":[{"id":"optionmetrics","name":"OptionMetrics IvyDB","provider":"OptionMetrics","kind":"options","access":"commercial","quote":"Application to SPX Market Data To assess the practical applicability of SABR-MTGP, we evaluate it on SPX option data from the OptionMetrics database dated August 1, 2023.","mentions":1,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"pricing-calibration","findings":[{"finding":"The SABR‑MTGP model achieves lower error than the single‑task GP and SABR at near‑term maturities and remains competitive at long‑term maturities while satisfying no‑arbitrage conditions.","kind":"predictive-accuracy","quote":"On Heston ground truth across ten market regimes and in a case study with SPX options, the model achieves lower error than the single-task Gaussian process and SABR at near-term maturities and remains competitive at long-term maturities, while satisfying standard no-arbitrage conditions."},{"finding":"In the near‑term slice, SABR‑MTGP tracks the Heston truth closely with smooth residuals, outperforming SABR and single‑task GP.","kind":"performance","quote":"The single-task GP follows the curve yet exhibits small local oscillations in the wings where observations are sparse. SABR-MTGP tracks the truth closely and its residuals are centered and smooth."},{"finding":"Butterfly spreads remain non‑negative for SABR‑MTGP, indicating consistency with static no‑arbitrage on the SPX sample.","kind":"statistical","quote":"The butterfly spreads shown in Figure 11 remain nonnegative for SABR-MTGP, SABR, SSVI and cubic spline on the inspected slices, while GP and NN exhibit occasional dips near mid or long maturities."}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":22,"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":1,"extracted_at":"2026-11-14T17:34:45Z"},"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/"}