{"paper_id":"2410.00288","title":"GARCH-Informed Neural Networks for Volatility Prediction in Financial Markets","authors":["Zeda Xu","John Liechty","Sebastian Benthall","Nicholas Skar-Gislinge","Christopher McComb"],"paper_date":"2024-09-30","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2410.00288v1","page_url":"https://thequant.space/flowcharts/garch-informed-neural-networks-for-volatility-prediction-in/","scores":{"empirical_rigor":8,"math_complexity":7,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a hybrid deep learning model called GARCH-Informed Neural Network (GINN) that combines GARCH with an LSTM network for volatility forecasting.","quote":"we constructed a new, hybrid Deep Learning model that combines the strengths of GARCH with the flexibility of a Long Short-Term Memory (LSTM) Deep Neural Network (DNN), thus capturing and forecasting market volatility more accurately than either class of models are capable of on their own. We refer to this novel model ","summary":"Volatility, which indicates the dispersion of returns, is a crucial measure of risk and is hence used extensively for pricing and discriminating between different financial investments. As a result, accurate volatility prediction receives extensive attention. The Generalized Autoregressive…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The weight term λ in the GINN model lies between 0 and 1 and is selected via out‑of‑sample validation.","type":"model","stated":"explicit","quote":"Different values of λ were tested ranging from 0 to 1, with 0.01 increments between 0 and 0.2, and 0.05 increments between 0.2 and 1."},{"assumption":"Training converges after 300 epochs for both LSTM and GINN models.","type":"model","stated":"explicit","quote":"It was found that both the LSTM and the GINN models reached convergence after training for 300 epochs."}]},"datasets":{"status":"available","items":[{"name":"NASDAQ Composite (IXIC)","provider":null,"kind":"market-prices","access":"public","period":"06/01/1992 to 05/31/2022","universe":null,"quote":"The NASDAQ Composite (IXIC) dated from 06/01/1992 to 05/31/2022 is used as the dataset for the parametric study."}],"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 GINN model achieved the best out‑of‑sample prediction accuracy, obtaining 16 first‑place, 18 second‑place and 4 third‑place rankings across 21 time‑series and metric combinations.","kind":"predictive-accuracy","quote":"Overall, the proposed GINN model and the GINN-0 model achieved high performance in out-of-sample prediction accuracy, beating other models in most test categories. Combined, they scored 16 first places, 18 second places, and 4 third places out of a total of 21 time series data and performance metric combinations."},{"finding":"A weight λ of 0.01 was identified as the optimal hyper‑parameter for maximizing the Coefficient of Determination (R2) on the testing set.","kind":"performance","quote":"Through testing, we determined that λ = 0.01 would yield the best performance."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":9,"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":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":"2026-11-14T18:01:02Z"},"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/"}