{"paper_id":"2511.08588","title":"Explainable Federated Learning for U.S. State-Level Financial Distress Modeling","authors":["Lorenzo Carta","Fernando Spadea","Oshani Seneviratne"],"paper_date":"2025-10-28","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2511.08588v1","page_url":"https://thequant.space/flowcharts/explainable-federated-learning-for-u.s.-state-level-financia/","scores":{"empirical_rigor":7.5,"math_complexity":6,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes the first federated learning application to predict consumer financial distress across all U.S. states with an interpretable framework that does not centralize sensitive data.","quote":"We present the first application of federated learning (FL) to the U.S. National Financial Capability Study, introducing an interpretable framework for predicting consumer financial distress across all 50 states and the District of Columbia without centralizing sensitive data.","summary":"We present the first application of federated learning (FL) to the U.S. National Financial Capability Study, introducing an interpretable framework for predicting consumer financial distress across all 50 states and the District of Columbia without centralizing sensitive data. Our cross-silo FL…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Each U.S. state can be treated as an independent data silo for cross‑silo federated learning.","type":"data","stated":"implied","quote":"Our cross-silo FL setup treats each state as a distinct data silo, simulating real-world governance in nationwide financial systems."},{"assumption":"Class weighting can effectively mitigate the severe class imbalance (only 18% minority class).","type":"model","stated":"implied","quote":"using class weighting to address the significant imbalance (only 18% of respondents had been contacted by a DCA)"},{"assumption":"A minority class weight factor of 1.1835 yields the best precision‑recall trade‑off.","type":"statistical","stated":"explicit","quote":"increasing the standard minority class weight by a factor of 1.1835 yielded the best balance between precision and recall"},{"assumption":"The 2021 NFCS survey responses are representative of state‑level financial distress patterns.","type":"data","stated":"implied","quote":"more than 25,000 U.S. respondents, with approximately 500 respondents per state"},{"assumption":"Communication cost reductions (GB transferred) are a relevant metric for federated learning efficiency.","type":"execution","stated":"implied","quote":"We also optimized model update communication, reducing costs from 12.954 GB to 4.935 GB over 200 training rounds."}]},"datasets":{"status":"available","items":[{"name":"2021 National Financial Capability Study (NFCS)","provider":"FINRA Investor Education Foundation","kind":"alternative","access":"public","period":null,"universe":"more than 25,000 U.S. respondents, ~500 per state + DC","quote":"for our analysis. This comprehensive dataset is derived from a 126‑question multiple choice survey that captures various statistics such as income, education, and financial education from more than 25,000 U.S. respondents, with approximately 500 respondents per state, plus the District of Columbia."}],"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":"R4a","candidates":{"front_matter":"n/a","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"Model update communication reduced from 12.954 GB to 4.935 GB over 200 training rounds.","card_quote":"We also optimized model update communication, reducing costs from 12.954 GB to 4.935 GB over 200 training rounds.","meaning":"the paper reports no trading or execution result; the cost the extractor found is a model parameter"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"Federated learning achieves predictive performance on‑par with a centralized model and outperforms locally trained state models.","kind":"predictive-accuracy","quote":"showed through comparison that our results were on-par with the centralized model, while also outperforming localized ones."},{"finding":"Communication overhead was cut by more than 60%, from 12.954 GB to 4.935 GB across 200 rounds.","kind":"performance","quote":"We also optimized model update communication, reducing costs from 12.954 GB to 4.935 GB over 200 training rounds."},{"finding":"Critical predictors of financial distress include Gender/Age and Annual Income.","kind":"statistical","quote":"Our analysis identified critical predictors of financial distress, including Gender/Age and Annual Income."},{"finding":"Combining SHAP and Owen values enables interpretation of both global (national) and local (state‑level) model behavior.","kind":"theoretical","quote":"Our contribution is distinct in combining SHAP with Owen values, enabling interpretation of both global (national) and local (state-level) model behavior."},{"finding":"A minority class weight factor of 1.1835 provides the best balance between precision and recall.","kind":"statistical","quote":"increasing the standard minority class weight by a factor of 1.1835 yielded the best balance between precision and recall"}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":37,"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/brains-group/xfl-for-loan-eligibility","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":"2026-11-14T17:23:21Z"},"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/"}