{"paper_id":"2408.05701","title":"Why Groups Matter: Necessity of Group Structures in Attributions","authors":["Dangxing Chen","Jingfeng Chen","Weicheng Ye"],"paper_date":"2024-08-11","paper_type":"perspective-policy","paper_url":"https://arxiv.org/pdf/2408.05701v1","page_url":"https://thequant.space/flowcharts/why-groups-matter-necessity-of-group-structures-in-attribut/","scores":{"empirical_rigor":2,"math_complexity":8.5,"quadrant":"Lab Rats"},"proposes":{"status":"available","statement":"The paper proposes group axioms for attribution methods and introduces a group version of the Shapley value (GShap) that preserves these axioms.","quote":"(1) we propose group axioms for attribution methods with a rigorous theoretical framework.","summary":"Explainable machine learning methods have been accompanied by substantial development. Despite their success, the existing approaches focus more on the general framework with no prior domain expertise. High-stakes financial sectors have extensive domain knowledge of the features. Hence, it is…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The dataset D has n samples and m features, and the model f is differentiable almost everywhere.","type":"data","stated":"explicit","quote":"For problem setup, assume we have D ×Y, where D is the dataset with"},{"assumption":"Zero baselines are used for attribution calculations.","type":"model","stated":"explicit","quote":"For simplicity, we consider the zero baselines as x′ = 0."},{"assumption":"Group structures are present in the feature set and should be respected by attribution methods.","type":"other","stated":"explicit","quote":"When group structures are present, direct applications of explainable machine learning methods, such as Shapley values and Integrated Gradients, may not provide consistent explanations; alternatively, group versions of the Shapley value can provide consistent explanations."}]},"datasets":{"status":"available","items":[{"name":"credit scoring dataset","provider":"Kaggle","kind":"fundamentals","access":"public","period":null,"universe":null,"quote":"We examine the significance of group structure using a widely-used credit scoring dataset from Kaggle, publicly available at 3.","known_id":"kaggle"}],"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":"unclear","findings":[{"finding":"GShap preserves all knowledge-inspired axioms (ASI, DIM, GASI, GLFI, GDIM, GSPM) whereas BShap and IG do not.","kind":"theoretical","quote":"As a result of the preservation of axioms when group structures are present, GShap is preferred over BShap and IG."},{"finding":"BShap and IG can produce absurd attributions for past‑due features, reducing attribution when past‑due payments increase.","kind":"negative","quote":"In the content of Example 4.13, according to BShap and IG, for a candidate with more past‑due payments, the overall past‑due attributions could be significantly reduced, which is absurd."}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":7,"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":"2026-11-14T18:04:20Z"},"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/"}