{"paper_id":"2512.12334","title":"Extending the application of dynamic Bayesian networks in calculating market risk: Standard and stressed expected shortfall","authors":["Eden Gross","Ryan Kruger","Francois Toerien"],"paper_date":"2025-12-13","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2512.12334v1","page_url":"https://thequant.space/flowcharts/extending-the-application-of-dynamic-bayesian-networks-in-ca/","scores":{"empirical_rigor":7,"math_complexity":8.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper extends dynamic Bayesian networks to estimate 10‑day 97.5% expected shortfall and stressed expected shortfall.","quote":"We extend the application of dynamic Bayesian networks (DBNs) to the estimation of 10-day 97.5% ES and stressed ES","summary":"In the last five years, expected shortfall (ES) and stressed ES (SES) have become key required regulatory measures of market risk in the banking sector, especially following events such as the global financial crisis. Thus, finding ways to optimize their estimation is of great importance. We extend…","strategy":"dynamic Bayesian networks (DBNs)"},"assumptions":{"status":"available","items":[{"assumption":"The S&P 500 index proxies the equities trading desk of a US bank.","type":"market","stated":"explicit","quote":"The S&P 500 index is used as a proxy for the equities trading desk of a US bank"},{"assumption":"Return distributions are either normal or skewed Student’s t.","type":"model","stated":"explicit","quote":"using either the normal or the skewed Student’s t distribution as the underlying return distribution"},{"assumption":"DBN structure is selected by minimizing AIC on each rolling training window.","type":"model","stated":"explicit","quote":"each training iteration was the one that minimized the Akaike information criterion (AIC)"},{"assumption":"Non‑daily variables are converted to daily by carrying forward the last known value.","type":"data","stated":"explicit","quote":"non-daily data were converted to daily by carrying forward the last known value"},{"assumption":"Conditional backtest assumes ES forecasts are produced after corresponding VaR forecasts.","type":"statistical","stated":"explicit","quote":"The conditional backtest (Acerbi & Székely, 2014) rests on the assumption that ES forecasts are produced and tested after their corresponding VaR forecasts have been produced and tested."},{"assumption":"Stressed period is defined by a rolling methodology aggregating the most severe S&P 500 return days.","type":"other","stated":"explicit","quote":"the stressed period is determined using a rolling period methodology as the amalgamation of the most severe return days of the S&P 500 index"}]},"datasets":{"status":"available","items":[{"name":"S&P 500 daily closing values","provider":"Bloomberg","kind":"market-prices","access":"commercial","period":"15 March 1991 to 14 February 2020","universe":"S&P 500 index","quote":"We use daily closing values of the S&P 500 index from 15 March 1991 to 14 February 2020, obtained from the Bloomberg database","known_id":"bloomberg"}],"known":[{"id":"bloomberg","name":"Bloomberg","provider":"Bloomberg L.P.","kind":"market-prices","access":"commercial","quote":"Data and Methodology We use daily closing values of the S&P 500 index from 15 March 1991 to 14 February 2020, obtained from the Bloomberg database, to forecast 7,286 out-of-sample 10-day 97.5% ES and SES forecasts using ten traditional models and three BNs.","mentions":2,"used_in":2}],"sample":{"start":"1991-03","end":"2020-02","market":"S&P 500 index","asset_class":"equities","frequency":"daily"},"data_resolution":"daily"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"n/a","evidence_card":"unclear","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"For ES, the EGARCH(1,1) model with normal distribution yields the most accurate forecasts.","kind":"predictive-accuracy","quote":"For ES, the EGARCH(1,1) model (normal) produces the most accurate forecasts"},{"finding":"For SES, the GARCH(1,1) model with normal distribution performs best.","kind":"predictive-accuracy","quote":"for SES, the GARCH(1,1) model (normal) performs best"},{"finding":"All models, including DBNs, fail statistical backtests at the 2.5% level, indicating inaccurate ES and SES forecasts.","kind":"statistical","quote":"... forecasts were statistically inaccurate at the 97.5% confidence level"},{"finding":"DBNs perform comparably to the historical simulation model but have limited tail‑prediction contribution.","kind":"performance","quote":"The DBNs perform comparably to the historical simulation model, but their contribution to tail prediction is limited"},{"finding":"Models using the skewed Student’s t distribution deteriorate substantially compared to normal distribution.","kind":"performance","quote":"All distribution-dependent models deteriorate substantially when using the skewed Student's t distribution"}],"reported_performance":{"strategy":"dynamic Bayesian networks (DBNs)","sharpe":null,"sharpe_benchmark":null,"annual_return_pct":null,"total_return_pct":null,"max_drawdown_pct":null},"out_of_sample":{"method":"walk-forward","headline_out_of_sample":true}},"independent_evidence":{"status":"available","supports":[],"contradicts":[{"paper":{"paper_id":"2508.18921","title":"Forecasting Probability Distributions of Financial Returns with Deep Neural Networks","paper_date":"2025-08-26","authors":["Jakub Michańków"],"empirical_rigor":8,"page_url":"https://thequant.space/flowcharts/forecasting-probability-distributions-of-financial-returns-with-deep-neural/"},"question":"Does using a skewed Student’s t distribution improve model performance for financial return forecasting and market risk estimation?","this_paper_finding":"Models using the skewed Student’s t distribution deteriorate substantially compared to normal distribution.","other_paper_finding":"The LSTM with skewed Student’s t distribution performs best across multiple evaluation criteria, capturing heavy tails and asymmetry.","other_paper_quote":"The LSTM with skewed Student's t distribution performs best across multiple evaluation criteria, capturing both heavy tails and asymmetry in financial returns.","note":"Finding A reports it performs best across multiple criteria, while Finding B reports substantial deterioration versus a normal distribution.","confidence":0.659}],"qualifies":[],"compared_with":40,"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":"2026-11-14T17:19:17Z"},"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/"}