{"paper_id":"2505.11163","title":"Foundation Time-Series AI Model for Realized Volatility Forecasting","authors":["Anubha Goel","Puneet Pasricha","Martin Magris","Juho Kanniainen"],"paper_date":"2025-05-16","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2505.11163v1","page_url":"https://thequant.space/flowcharts/foundation-time-series-ai-model-for-realized-volatility-fore/","scores":{"empirical_rigor":8,"math_complexity":5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes an incremental fine‑tuning procedure for the pre‑trained TimesFM foundation model to improve realized volatility forecasting.","quote":"We first evaluate TimesFM in its pretrained (zero-shot) form, followed by our custom fine-tuning procedure based on incremental learning, and compare the resulting models against standard econometric benchmarks.","summary":"Time series foundation models (FMs) have emerged as a popular paradigm for zero-shot multi-domain forecasting. These models are trained on numerous diverse datasets and claim to be effective forecasters across multiple different time series domains, including financial data. In this study, we…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The explanatory variables are assumed to be stationary, limiting adaptability of traditional econometric models.","type":"statistical","stated":"explicit","quote":"limited adaptability to evolving market conditions primarily due to the stationarity assumption of the explanatory variables."},{"assumption":"Forecast horizon is set to one day ahead (H = 1).","type":"model","stated":"explicit","quote":"Throughout this study, we set H = 1."},{"assumption":"The model is retrained on a rolling window of the most recent L observations.","type":"model","stated":"explicit","quote":"the model is trained using the most recent L observations, xt−L+1, . . . , xt, where L denotes the length of the historical context."},{"assumption":"Data are daily realized volatility observations.","type":"data","stated":"explicit","quote":"The dataset provides daily observations, including key realized measures of market volatility."}]},"datasets":{"status":"available","items":[{"name":"Oxford-Man Institute Realized Library","provider":"Oxford-Man Institute","kind":"market-prices","access":"public","period":"2000-01 to 2021-12","universe":"21 major global stock market indices","quote":"This study employs high-frequency realized volatility data from the Oxford-Man Institute’s Realized Library for 21 major global stock market indices. The"}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"unclear"},"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":"Fine‑tuned TimesFM variants improve forecast accuracy and statistically outperform traditional econometric models according to Diebold‑Mariano and Giacomini‑White tests.","kind":"statistical","quote":"Fine-tuned variants not only improve forecast accuracy but also statistically outperform traditional models, as demonstrated through Diebold-Mariano and Giacomini-White tests."},{"finding":"TimesFM models (e.g., TFM64logIL and TTFM512PT) achieve lower relative errors across loss functions such as MSE, QLIKE, and sMAPE.","kind":"performance","quote":"TimesFM models, particularly TFM64logIL and TTFM512PT, consistently achieve lower relative errors across loss functions such as MSE, QLIKE, and sMAPE."},{"finding":"TFM512PT and TFM512IL consistently outperform traditional models under the Q‑like loss function, with p‑values below 0.10 in DM and GW tests.","kind":"statistical","quote":"TFM512PT and TFM512IL consistently outperform traditional models under the Q-like loss function, with p-values below 0.10 in DM and GW tests."}],"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":"2026-11-14T17:38:02Z"},"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/"}