{"paper_id":"2306.12446","title":"Comparing Deep Learning Models for the Task of Volatility Prediction Using Multivariate Data","authors":["Wenbo Ge","Pooia Lalbakhsh","Leigh Isai","Artem Lensky","Hanna Suominen"],"paper_date":"2023-06-20","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2306.12446v2","page_url":"https://thequant.space/flowcharts/comparing-deep-learning-models-for-the-task-of-volatility-pr/","scores":{"empirical_rigor":7,"math_complexity":4,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes to compare multiple deep learning-based forecasters for volatility prediction using multivariate data, evaluating models from shallow MLPs to deep TFT and TCN architectures.","quote":"This study aims to compare multiple deep learning-based forecasters for the task of predicting volatility using multivariate data.","summary":"This study aims to compare multiple deep learning-based forecasters for the task of predicting volatility using multivariate data. The paper evaluates a range of models, starting from simpler and shallower ones and progressing to deeper and more complex architectures. Additionally, the performance…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The current trading day is assumed to be over and observed when forecasting volatility.","type":"data","stated":"explicit","quote":"This assumed that at the time of forecasting, the current trading day is over and observed, an assumption maintained for all forecasting models."},{"assumption":"A 70-15-15 train‑validation‑test split is used for model evaluation.","type":"data","stated":"explicit","quote":"…ction of a 70-15-15 train-validation-test split with the evaluation process were statistically significantly different from each other."},{"assumption":"Statistical significance testing assumes normality of MSE distributions when using the Shapiro‑Wilk test.","type":"statistical","stated":"explicit","quote":"The Shapiro-Wilk (SW) test [58] was first applied to assess the normality of the distribution with significance level 𝛼= 0.05."},{"assumption":"If both distributions are normal, Student’s t‑test is used; otherwise Kruskal‑Wallis test is applied.","type":"statistical","stated":"explicit","quote":"If both distributions were normal then Student’s t-test [61] was used, otherwise the Kruskal-Wallis (KW) test [31] was employed."},{"assumption":"The naive benchmark repeats the most recent known volatility value.","type":"model","stated":"explicit","quote":"The naïve model simply repeated the most recent known value of volatility (Fig. 2)."},{"assumption":"GARCH variants are selected based on auto‑correlation and partial auto‑correlation functions.","type":"model","stated":"explicit","quote":"Lag orders were 1 and 2, as informed by the auto-correlation and partial auto-correlation functions."}]},"datasets":{"status":"available","items":[{"name":"Five asset price series","provider":null,"kind":"market-prices","access":"unknown","period":null,"universe":"S&P500, NASDAQ100, gold, silver, oil","quote":"The prediction of volatility for five assets, namely S&P500, NASDAQ100, gold, silver, and oil, is specifically addressed using GARCH models, Multi-Layer Perceptrons, Recurrent Neural Networks, Temporal Convolutional Networks, and the Temporal Fusion Transformer."}],"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":"The Temporal Fusion Transformer (TFT) most often achieved the lowest MSE, followed by variants of the Temporal Convolutional Network (TCN), outperforming classical GARCH and shallow networks with statistical significance.","kind":"performance","quote":"In the majority of cases, the Temporal Fusion Transformer, followed by variants of the Temporal Convolutional Network, outperformed classical approaches and shallow networks."},{"finding":"Variants of TCN and TFT forecast volatility with less error across almost all assets and tasks investigated, with statistical significance.","kind":"statistical","quote":"The results indicate that variants of TCN and TFT were able to forecast volatility with less error across almost all assets and tasks investigated, with statistical significance."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":39,"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":"2026-11-14T18:25:27Z"},"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/"}