{"paper_id":"2412.05889","title":"Multi-Factor Function-on-Function Regression of Bond Yields on WTI Commodity Futures Term Structure Dynamics","authors":["Peilun He","Gareth W. Peters","Nino Kordzakhia","Pavel V. Shevchenko"],"paper_date":"2024-12-08","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2412.05889v1","page_url":"https://thequant.space/flowcharts/multi-factor-function-on-function-regression-of-bond-yields/","scores":{"empirical_rigor":7,"math_complexity":8.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a novel two‑factor state‑space functional regression model that incorporates yield‑curve dynamics to improve commodity futures pricing.","quote":"we extend this framework by introducing a novel state-space functional regression model that incorporates yield curve dynamics.","summary":"In the analysis of commodity futures, it is commonly assumed that futures prices are driven by two latent factors: short-term fluctuations and long-term equilibrium price levels. In this study, we extend this framework by introducing a novel state-space functional regression model that incorporates…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Both latent factors χt and ξt follow Ornstein–Uhlenbeck (OU) processes.","type":"model","stated":"explicit","quote":"We assume that both χt and ξt follow an Ornstein–Uhlenbeck (OU) process:"},{"assumption":"Constant risk premiums λχ and λξ are assumed.","type":"model","stated":"explicit","quote":"Assuming constant risk premiums λχ, λξ ∈R, the risk-neutral processes of χt and ξt are given by:"},{"assumption":"The interest rate is non‑stochastic.","type":"model","stated":"explicit","quote":"assuming the interest rate is non‑stochastic)"},{"assumption":"Monthly data from January 2010 to December 2019 are used.","type":"data","stated":"explicit","quote":"We use monthly data for both datasets, covering the period from January 2010 to December 2019."},{"assumption":"US Treasury yield curve is evaluated at five monthly maturities (1, 3, 6, 9, 12 months).","type":"data","stated":"explicit","quote":"The US Treasury yield curve is evaluated at five observed points each month, corresponding to maturities of 1, 3, 6, 9, and 12 months."},{"assumption":"Kalman filter jointly estimates hidden state variables and unknown model parameters.","type":"model","stated":"explicit","quote":"In Section 4, we employ the Kalman filter to jointly estimate the hidden state variables and the unknown model parameters."}]},"datasets":{"status":"available","items":[{"name":"WTI crude oil futures","provider":"LSEG Datascope Select","kind":"market-prices","access":"commercial","period":"2010-2019","universe":"Contracts with maturities 1‑12 months","quote":"The futures data, we select contracts with maturities ranging from 1 month to 12 months. The","known_id":"refinitiv"},{"name":"US Treasury yields","provider":"TradingView","kind":"macro","access":"public","period":"2010-2019","universe":"Yield curve evaluated at 1, 3, 6, 9, 12 month maturities","quote":"Data was sourced from TradingView."}],"known":[{"id":"refinitiv","name":"Refinitiv / LSEG (Datastream, Eikon, Tick History)","provider":"LSEG","kind":"market-prices","access":"commercial","quote":"The data was obtained from LSEG Datascope Select.","mentions":1,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"weekly-monthly"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"n/a","evidence_card":"unclear","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"pricing-calibration","findings":[{"finding":"The functional regression model yields a lower mean RMSE (0.2284) than the Schwartz‑Smith model (0.2583).","kind":"predictive-accuracy","quote":"In general, the functional regression model provides more accurate estimates of the futures curve, with a mean RMSE of 0.2284, compared to 0.2583 for the SS model."},{"finding":"Functional regression outperforms the SS model for short‑term contracts, while the SS model is better for long‑term contracts.","kind":"predictive-accuracy","quote":"The functional regression model outperforms the SS model for short-term contracts, whereas the SS model gives lower RMSEs for long-term contracts."},{"finding":"Stress testing shows both permanent and temporary shocks significantly affect short‑term futures (1‑4 months).","kind":"performance","quote":"both shocks significantly affect short-term futures, with maturities between 1 and 4 months."},{"finding":"Under normal conditions (short‑term yields lower than long‑term), the SS model shrinks after accounting for Treasury yields, with yields contributing more to long‑term futures.","kind":"theoretical","quote":"under normal economic conditions, when short-term Treasury yields are lower than long-term yields, the original Schwartz‑Smith model shrinks after accounting for the effects of Treasury yields, with yields contributing more to long‑term futures than short‑term futures."},{"finding":"During recession (short‑term yields exceed long‑term), the SS model expands, with Treasury yields having greater influence on short‑term futures.","kind":"theoretical","quote":"during an economic recession, indicated by short‑term Treasury yields exceeding long‑term yields, the Schwartz‑Smith model expands, with Treasury yields having a greater influence on short‑term futures than on long‑term futures."}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":23,"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":"2026-11-14T17:50:55Z"},"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/"}