{"paper_id":"2408.09960","title":"Causality-Inspired Models for Financial Time Series Forecasting","authors":["Daniel Cunha Oliveira","Yutong Lu","Xi Lin","Mihai Cucuringu","Andre Fujita"],"paper_date":"2024-08-19","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2408.09960v1","page_url":"https://thequant.space/flowcharts/causality-inspired-models-for-financial-time-series-forecast/","scores":{"empirical_rigor":6,"math_complexity":7,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a novel causality‑inspired framework for financial time series forecasting that balances invariance to distributional changes with prediction error minimization.","quote":"We introduce a novel framework to financial time series forecasting that leverages causality‑inspired models to balance the trade‑off between invariance to distributional changes and minimization of prediction errors.","summary":"We introduce a novel framework to financial time series forecasting that leverages causality-inspired models to balance the trade-off between invariance to distributional changes and minimization of prediction errors. To the best of our knowledge, this is the first study to conduct a comprehensive…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Causal invariance: there exists a set of variables S* such that the conditional distribution of the outcome given S* is consistent across all environments.","type":"statistical","stated":"explicit","quote":"The key assumption is causal invariance: there exists a set of variables S∗such that the conditional distribution of the outcome given S∗is consistent in all environments e, h ∈E"},{"assumption":"No unmeasured confounder affects the treatment‑outcome relationship.","type":"model","stated":"explicit","quote":"The method also assumes no unmeasured confounder affects the treatment‑outcome relationship."},{"assumption":"The study adheres to linear models for causal future selection.","type":"model","stated":"explicit","quote":"As we focus more on the performance of causal future selection, we adhere to linear models in this study"},{"assumption":"SPY price data are taken at the last business day of each month and FRED‑MD data at the first business day, implying alignment of monthly observations.","type":"data","stated":"implied","quote":"The SPY prices data are available on the last business day of every month, whereas the FRED‑MD data is on the first business."}]},"datasets":{"status":"available","items":[{"name":"SPY","provider":"Bloomberg (WRDS)","kind":"market-prices","access":"commercial","period":"2000‑02‑02 to 2023‑04‑28","universe":"SPDR S&P 500 ETF (SPY)","quote":"dataset contains monthly closing prices of SPY from February 2nd, 2000, to April 28th, 2023, and is collected from Bloomberg.","known_id":"wrds"},{"name":"FRED‑MD","provider":"Federal Reserve Economic Data (FRED)","kind":"macro","access":"public","period":"1960‑01‑01 to 2022‑12‑30","universe":"U.S. macroeconomic indicators","quote":"dataset ... begins on January 1st, 1960, and concludes on December 30th, 2022.","known_id":"fred"}],"known":[{"id":"fred","name":"FRED","provider":"Federal Reserve Bank of St. Louis","kind":"macro","access":"public","quote":"We extract price data from the WRDS and macroeconomic data from the Federal Reserve Economic Data (FRED) databases.","mentions":12,"used_in":4},{"id":"bloomberg","name":"Bloomberg","provider":"Bloomberg L.P.","kind":"market-prices","access":"commercial","quote":"This dataset contains monthly closing prices of SPY from February 2nd, 2000, to April 28th, 2023, and is collected from Bloomberg.","mentions":1,"used_in":1},{"id":"wrds","name":"WRDS","provider":"Wharton Research Data Services","kind":"other","access":"commercial","quote":"We extract price data from the WRDS and macroeconomic data from the Federal Reserve Economic Data (FRED) databases.","mentions":1,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"weekly-monthly"},"transaction_costs":{"status":"available","modeled":"unclear","headline_net_of_costs":null,"detail":null,"quote":null,"source":"conflict","rule":"R4b","candidates":{"front_matter":"no","evidence_card":"n/a","evidence_card_quoted":false},"conflict_kind":"applicability","meaning":"the platform classifier and the paper-text extraction disagree, so no value is asserted"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"Modified VAR‑LiNGAM consistently achieves the lowest MAE and RMSE across both regular and crisis periods.","kind":"performance","quote":"First, the Modified VAR–LiNGAM consistently outperforms (lowest prediction error) other methods in terms of MAE and RMSE, regardless of the period."},{"finding":"Causal methods (e.g., Modified VAR‑LiNGAM, Dynotears) have lower RMSE than the non‑causal benchmark SFS‑Linear during crises.","kind":"predictive-accuracy","quote":"Over the GFC and COVID‑19 pandemic, the SFS‑linear method consistently shows higher RMSE than causal methods."},{"finding":"Dynotears yields lower RMSE than SFS‑Linear in crisis periods, highlighting the advantage of invariant prediction.","kind":"predictive-accuracy","quote":"The bottom plot in Figure 1 highlights the difference in RMSE between SFS‑Linear and Dynotears. Values above 0 indicate that Dynotears yields a lower RMSE than SFS‑Linear."},{"finding":"During stable periods, causal methods perform similarly to the benchmark, indicating comparable efficiency when distributions do not shift.","kind":"performance","quote":"During regular periods with stable economic conditions, the prediction accuracy of causal methods is similar to the benchmark."},{"finding":"Causal feature selection models exhibit smaller increases in MAE from regular to crisis periods compared to the non‑causal SFS‑Linear model.","kind":"statistical","quote":"The last column of Table 1 depicts the MAE increase in percentage terms from regular periods to crisis periods"}],"reported_performance":null,"out_of_sample":{"method":"walk-forward","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":32,"citations":{"cited_by_in_corpus":3,"by_independent_authors":3,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":1,"unclassified":2},"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":"2026-11-14T18:03:48Z"},"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/"}