{"paper_id":"2309.07843","title":"Applying Deep Learning to Calibrate Stochastic Volatility Models","authors":["Abir Sridi","Paul Bilokon"],"paper_date":"2023-09-14","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2309.07843v2","page_url":"https://thequant.space/flowcharts/applying-deep-learning-to-calibrate-stochastic-volatility-mo/","scores":{"empirical_rigor":8,"math_complexity":7.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper applies Differential Machine Learning (DML) to price vanilla European put options under the Heston stochastic volatility model and uses the trained network for fast model calibration.","quote":"The present work aims to apply the DML technique to price vanilla European options (i.e. the calibration instruments), more specifically, puts when the underlying asset follows a Heston model and then calibrate the model on the trained network.","summary":"Stochastic volatility models, where the volatility is a stochastic process, can capture most of the essential stylized facts of implied volatility surfaces and give more realistic dynamics of the volatility smile/skew. However, they come with the significant issue that they take too long to…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The underlying asset follows the Heston stochastic volatility dynamics under the risk‑neutral measure.","type":"model","stated":"explicit","quote":"The Heston model is a stochastic volatility model where the dynamic of the underlying S = {St, t ≥0} and its volatility √vt can be described by the following Stochastic Differential Equation (SDE): (dSt = St(rdt + √vtdW1t ) dvt = κ(θ −vt)dt + σ√vtdW2t )"},{"assumption":"The Feller condition is satisfied for the variance process.","type":"model","stated":"explicit","quote":"In the sequel, we will work with the dataset generated when the feller condition is satisfied."},{"assumption":"Synthetic data are generated i.i.d. using Random Latin Hypercube sampling.","type":"data","stated":"explicit","quote":"assumption about the features and labels (xi, yi), i = 1, . . . , m, is often made. Thus the data needs to be generated by a pseudo‑random method such as simple Monte Carlo (MC)"},{"assumption":"Risk‑free rate r is constant during pricing and calibration.","type":"market","stated":"implied","quote":"we generate synthetic dataset for the input parameters for the model (θ, κ, σ, ρ and v0), the option and the market ones, which include m, τ and r within appropriate ranges"}]},"datasets":{"status":"available","items":[{"name":"Synthetic Heston calibration dataset","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":null,"quote":"we generate synthetic dataset for the input parameters for the model (θ, κ, σ, ρ and v0), the option and the market ones, which include m, τ and r within appropriate ranges selected for each parameter."},{"name":"Training set of 16 384 samples","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":null,"quote":"we then decide to retain a dataset of 16 384 samples."}],"known":[{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"In this work, we use the S&P 500 index options that we collect from yahoo finance https://finance.yahoo.com/quote/ %5ESPX/options?p=%5ESPX.","mentions":1,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"unclear"},"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":"Differential Machine Learning (DML) vastly outperforms classical deep learning (DL) for pricing under the Heston model.","kind":"performance","quote":"We show that the DML outperforms the DL."},{"finding":"DML can learn effectively from small datasets; with 16 K samples it achieves an MSE of 0.44 bp versus 1.73 bp for a classical network trained on six times more data.","kind":"predictive-accuracy","quote":"The MSE on the differential network trained on 16K examples is 0.44 bp, lower than the MSE on the classical network with 6 times the training dataset size, which equals 1.73."},{"finding":"The trained neural network dramatically reduces Heston calibration computation time compared to traditional calibration.","kind":"pricing-calibration","quote":"the trained neural network dramatically reduces Heston calibration’s computation time."},{"finding":"Calibration with three parameters is as accurate as with five but considerably faster, especially when using the DNN‑based price.","kind":"pricing-calibration","quote":"We found that the calibration accuracy with three parameters is similar to that with five. The calibration of three parameters is faster regardless of the price computation type (real pricer or DNN‑based)."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":32,"citations":{"cited_by_in_corpus":2,"by_independent_authors":2,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":1,"unclassified":1},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":true,"code_url":"https://github.com/asridi/DML-Calibration-Heston-Model","note":null},"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":"2026-11-14T18:22:15Z"},"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/"}