{"paper_id":"2501.00034","title":"Time Series Feature Redundancy Paradox: An Empirical Study Based on Mortgage Default Prediction","authors":["Chengyue Huang","Yahe Yang"],"paper_date":"2024-12-23","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2501.00034v1","page_url":"https://thequant.space/flowcharts/time-series-feature-redundancy-paradox-an-empirical-study-b/","scores":{"empirical_rigor":9,"math_complexity":4.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper empirically validates a “feature redundancy paradox” and offers practical guidelines for optimizing feature and time‑window selection in mortgage default prediction.","quote":"By synthesizing insights from prior studies, our work aims to empirically validate the ”feature redundancy paradox” and provide actionable guidelines for optimizing feature and time window selection in mortgage default prediction.","summary":"With the widespread application of machine learning in financial risk management, conventional wisdom suggests that longer training periods and more feature variables contribute to improved model performance. This paper, focusing on mortgage default prediction, empirically discovers a phenomenon…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Housing markets are dynamic and evolving, so older patterns may become irrelevant.","type":"market","stated":"implied","quote":"A key difficulty lies in the dynamic and evolving nature of housing markets and broader economic conditions."},{"assumption":"Including many non‑critical features can obscure the influence of core variables.","type":"model","stated":"implied","quote":"Likewise, adding numerous non‑essential features can obscure the influence of critical variables and hinder the model’s ability to i…"},{"assumption":"Shorter, more recent time windows provide temporally relevant information that improves forecasting accuracy.","type":"data","stated":"explicit","quote":"Studies have shown that incorporating too much historical data can introduce noise and outdated patterns, which may degrade model performance."}]},"datasets":{"status":"available","items":[{"name":"Freddie Mac single‑family mortgage performance dataset","provider":"Freddie Mac","kind":"other","access":"unknown","period":"2012-2022","universe":"approximately 550,000 loans (50,000 sampled per year)","quote":"Our study utilizes Freddie Mac’s single‑family mortgage monthly performance data spanning from 2012 to 2022, comprising approximately 6.6 million monthly observations from 550,000 mortgage loans (50,000 loans sampled per year)."}],"known":[],"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":"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":"Logistic Regression’s ROC‑AUC drops from 0.858 to 0.803 when moving from a one‑year to a ten‑year training window.","kind":"performance","quote":"Logistic Regression’s performance drops from 0.858 to 0.803, and Random Forest from 0.865 to 0.805 when moving from one-year to ten‑year windows."},{"finding":"The key feature subset (10 features) consistently outperforms the full (26) and reduced (18) feature sets, improving ROC‑AUC by 0.016 to 0.029 in short windows.","kind":"predictive-accuracy","quote":"The key feature subset (n=10) consistently outperforms both the full feature set (n=26) and the reduced feature set (n=18), with improvements ranging from 0.016 to 0.029 in short windows."},{"finding":"Transformer models retain higher ROC‑AUC across longer windows compared to LSTM and other deep‑learning models.","kind":"performance","quote":"Transformer models demonstrate greater robustness to variations in time window lengths compared to LSTM and Transformer models in time series forecasting."},{"finding":"Across all architectures, feature reduction yields beneficial results, with the reduced set (18) serving as an effective intermediate step.","kind":"predictive-accuracy","quote":"The reduced feature set (n=18) often serves as an effective intermediate step, suggesting a gradual benefit to feature parsimony."},{"finding":"Longer historical periods introduce temporal noise that outweighs the benefit of additional training samples.","kind":"theoretical","quote":"while longer historical data periods may provide additional training samples, the potential benefits are outweighed by the introduction of temporal noise and outdated patterns."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[{"paper":{"paper_id":"2610.25822","title":"Conflicting History in Foundation Model Return Forecasts","paper_date":"2026-10-19","authors":["Levent Bulut"],"empirical_rigor":8,"page_url":"https://thequant.space/flowcharts/conflicting-history-in-foundation-model-return-forecasts/"},"question":"Does using longer historical periods of data improve prediction accuracy?","this_paper_finding":"Longer historical periods introduce temporal noise that outweighs the benefit of additional training samples.","other_paper_finding":"Conflicting older history reduces the probability of improving on zero in all 30 higher‑signal comparisons across five models and three processes.","other_paper_quote":"conflicting history reduces the probability of improving on zero in all 30 higher-signal comparisons.","note":"Both findings show older history reduces improvement—30 higher‑signal comparisons across 5 models and 3 processes show no gain, and longer mortgage default histories add temporal noise.","confidence":0.65}],"contradicts":[],"qualifies":[],"compared_with":35,"citations":{"cited_by_in_corpus":1,"by_independent_authors":1,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":1,"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":"2026-11-14T17:48:46Z"},"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/"}