{"paper_id":"2402.14476","title":"Quantifying neural network uncertainty under volatility clustering","authors":["Steven Y. K. Wong","Jennifer S. K. Chan","Lamiae Azizi"],"paper_date":"2024-02-22","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2402.14476v2","page_url":"https://thequant.space/flowcharts/quantifying-neural-network-uncertainty-under-volatility-clus/","scores":{"empirical_rigor":7,"math_complexity":8.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a Scale Mixture Distribution (SMD) with a prior only on the scaling factor ν and uses separate subnetworks for each distribution parameter, combined with model averaging and log‑squared returns as features.","quote":"We propose to place a prior solely on the scaling factor ν using a SMD, rather than on both mean and variance using the NIG prior.","summary":"Time-series with volatility clustering pose a unique challenge to uncertainty quantification (UQ) for returns forecasts. Methods for UQ such as Deep Evidential regression offer a simple way of quantifying return forecast uncertainty without the costs of a full Bayesian treatment. However, the…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The latent scaling factor ν must be greater than 1 to ensure a finite mean of the marginal distribution.","type":"model","stated":"explicit","quote":"We require α > 1 to ensure the mean of the marginal distribution is ﬁnite."},{"assumption":"Volatility clustering is present in the time‑series, making predictive uncertainty tracking essential.","type":"market","stated":"explicit","quote":"Time-series with volatility clustering pose a unique challenge to uncertainty quantification (UQ) for returns forecasts."},{"assumption":"Log of squared returns are informative features for modeling time‑varying forecast uncertainty.","type":"data","stated":"explicit","quote":"We propose to include the log of squared returns {log(r2 t‑K+1), . . . , log(r2 t )} as part of the input."},{"assumption":"Separate subnetworks for each hyperparameter improve specialization and uncertainty estimation.","type":"model","stated":"explicit","quote":"We show that modelling hyperparameters of the posterior distribution using subnetworks rather than a single output layer (as per Ensemble and Evidential) results in superior performance."}]},"datasets":{"status":"available","items":[{"name":"Cryptocurrency dataset","provider":"Binance","kind":"crypto-onchain","access":"public","period":"July 2018 to December 2021","universe":"BTC, ETH, BNB, NEO, LTC, ADA, XRP, EOS, TRX, ETC","quote":"Our cryptocurrency dataset consists of hourly returns downloaded from Binance over July 2018 to December 2021, for ten of the most liquid, non‑stablecoin","known_id":"binance"},{"name":"U.S. equities dataset","provider":null,"kind":"market-prices","access":"unknown","period":null,"universe":null,"quote":"A comparison in U.S. equities is also provided which illustrates performance in conventional financial time-series."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"intraday-bars"},"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":"SMD achieves superior RMSE and NLL performance compared to NIG on the UCI benchmark, winning on 6 of 9 datasets for RMSE and 8 of 9 for NLL.","kind":"performance","quote":"We observe that both RMSE and NLL are overwhelmingly in SMD’s favor, achieving superior results in 6 (of 9) and 8 (of 9) of the datasets for RMSE and NLL, respectively."},{"finding":"Separate subnetworks for each hyperparameter are essential for predictive uncertainty that closely tracks realized forecast error.","kind":"predictive-accuracy","quote":"... that separate modelling of the hyperparameters is essential in producing predictive uncertainty estimates that closely track actual realized forecast error of Bitcoin and Chevron."},{"finding":"Model averaging (ensemble) significantly improves return forecast accuracy without substantially increasing predictive uncertainty.","kind":"performance","quote":"we incorporate model averaging (in the spirit of ensemble) into our Combined method and show that it signiﬁcantly improves return forecast accuracy without signiﬁcantly increasing the estimated predictive uncertainty."},{"finding":"The Combined method outperforms state‑of‑the‑art Evidential and Ensemble methods in return forecasting on both cryptocurrency and U.S. equities data.","kind":"performance","quote":"superior return forecasting performance than the two state-of-the-art neural network UQ methods — Ev"}],"reported_performance":null,"out_of_sample":{"method":"walk-forward","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":36,"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":"2026-11-14T18:14:21Z"},"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/"}