{"paper_id":"2308.08550","title":"Recurrent Neural Networks with more flexible memory: better predictions than rough volatility","authors":["Damien Challet","Vincent Ragel"],"paper_date":"2023-08-04","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2308.08550v1","page_url":"https://thequant.space/flowcharts/recurrent-neural-networks-with-more-flexible-memory-better/","scores":{"empirical_rigor":8,"math_complexity":7.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes extending recurrent neural networks with several flexible timescales per output dimension to improve long‑memory prediction.","quote":"We extend recurrent neural networks to include several flexible timescales for each dimension of their output, which mechanically improves their abilities to account for processes with long memory or with highly disparate time scales.","summary":"We extend recurrent neural networks to include several flexible timescales for each dimension of their output, which mechanically improves their abilities to account for processes with long memory or with highly disparate time scales. We compare the ability of vanilla and extended long short term…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Asset price volatility exhibits long memory.","type":"model","stated":"explicit","quote":"We compare the ability of vanilla and extended long short term memory networks (LSTMs) to predict asset price volatility, known to have a long memory."},{"assumption":"Training and testing are performed on a dataset containing multiple time series.","type":"data","stated":"explicit","quote":"We also show that the model with the smallest validation loss systemically outperforms rough volatility predictions by about 20% when trained and tested on a dataset with multiple time series."}]},"datasets":{"status":"none_found","items":[],"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":"Extended LSTMs require roughly half the training epochs compared to standard LSTMs.","kind":"performance","quote":"Generally, the number of epochs needed to train extended LSTMs is divided by two, while the variation of validation and test losses among models with the same hyperparameters is much smaller."},{"finding":"Models with flexible timescales show much smaller variation in validation and test losses.","kind":"statistical","quote":"while the variation of validation and test losses among models with the same hyperparameters is much smaller."},{"finding":"The best‑validation‑loss model outperforms rough volatility predictions by about 20%.","kind":"predictive-accuracy","quote":"We also show that the model with the smallest validation loss systemically outperforms rough volatility predictions by about 20% when trained and tested on a dataset with multiple time series."},{"finding":"Adding a flexible kernel structure to LSTMs improves convergence time, overall prediction accuracy, and reduces accuracy variation across models.","kind":"performance","quote":"Adding an explicit but flexible kernel structure to LSTMs brings significant improvements in every metric: number of epochs needed to reach convergence, overall prediction accuracy, and accuracy variation between models at fixed."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":33,"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":true,"code_url":"https://github.com/damienchallet/LaSTM","note":null},"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":"2026-11-14T18:23:34Z"},"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/"}