{"paper_id":"2401.10370","title":"Deep Generative Modeling for Financial Time Series with Application in VaR: A Comparative Review","authors":["Lars Ericson","Xuejun Zhu","Xusi Han","Rao Fu","Shuang Li","Steve Guo","Ping Hu"],"paper_date":"2024-01-18","paper_type":"survey-review","paper_url":"https://arxiv.org/pdf/2401.10370v1","page_url":"https://thequant.space/flowcharts/deep-generative-modeling-for-financial-time-series-with-appl/","scores":{"empirical_rigor":8,"math_complexity":7.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes two new deep learning methods for conditional multi-step time series generation: Encoder-Decoder CGAN and Conditional TimeVAE.","quote":"we propose and test two new deep learning methods for conditional multi-step time series generation in Section 2, which are Encoder-Decoder CGAN (Fu (2022)) and Conditional TimeVAE (VAE for short).","summary":"In the financial services industry, forecasting the risk factor distribution conditional on the history and the current market environment is the key to market risk modeling in general and value at risk (VaR) model in particular. As one of the most widely adopted VaR models in commercial banks…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Only models that generate conditional distribution are considered.","type":"model","stated":"explicit","quote":"For this study, only models that generate conditional distribution are considered."},{"assumption":"Volatility clustering is an important feature that models must capture.","type":"market","stated":"explicit","quote":"Once in a high (low) volatility market episode, it is expected that the market stays in the high (low) volatility episode for certain period of time. This phenomenon is called volatility clustering."},{"assumption":"Synthetic data that are too close to real data may not be useful complements to real data.","type":"data","stated":"explicit","quote":"if the synthetic data are too close to real data (e.g. having a very high correlation), then they may not be useful complements to real data."}]},"datasets":{"status":"available","items":[{"name":"USD yield curve data","provider":null,"kind":"market-prices","access":"unknown","period":null,"universe":null,"quote":"All models (HS, parametric and neural networks) are tested on both historical USD yield curve data and additional data simulated from GARCH and CIR processes."},{"name":"Simulated data from GARCH process","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":null,"quote":"All models (HS, parametric and neural networks) are tested on"},{"name":"Simulated data from CIR process","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":null,"quote":"All models (HS, parametric and neural networks) are tested on"},{"name":"Market risk dataset (8 key time series)","provider":null,"kind":"market-prices","access":"unknown","period":"2007-2022","universe":"SPX, VIX, 3M, 10Y, CDX IG, CDX HY, USD/EUR, Oil","quote":"we compile another dataset for market risk, which includes eight key time series spanning the period 2007-2022: SPX and VIX for equity market, 3M and 10Y forward Treasury rates for fixed income market, North American CDX IG and HY for credit market, USD/EUR exchange rate for foreign exchange market, 1M Oil futures for "}],"known":[],"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":"forecast-accuracy","findings":[{"finding":"Historical simulation (HS) model performs the best across all simulated and historical datasets.","kind":"performance","quote":"HS model perform the best across all simulated and historical datasets used in model testing."},{"finding":"GARCH model (with conditional t distribution) is the best parametric model, ranking only behind HS.","kind":"performance","quote":"GARCH model (for returns, with conditional t distribution in particular) is consistently the best parametric model, and ranked only behind HS model."},{"finding":"CWGAN is the consistently best performing deep generative model across different datasets.","kind":"performance","quote":"CWGAN is consistently the best performing deep generative model across different datasets."},{"finding":"Other deep learning models (SIG, CGAN, VAE) show good performance on some datasets but are not consistent across all.","kind":"performance","quote":"Other deep learning models such as SIG, CGAN and VAE also have good performance for some datasets, however the performance is not consistent across all datasets."},{"finding":"Simulated data with very fat tails (GARCH and t distribution with three degrees of freedom) produce a different model ranking.","kind":"statistical","quote":"Simulated data from GARCH and t distribution with three degrees of freedom have very different model ranking from other datasets."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":22,"citations":{"cited_by_in_corpus":5,"by_independent_authors":5,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":5,"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":"2026-11-14T18:16:13Z"},"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/"}