{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/feature-responsiveness-scores-model-agnostic","title":"Feature Responsiveness Scores: Model-Agnostic Explanations for Recourse","arxiv_id":"2410.22598","date":"2024-10-29","proceeding":null,"authors":["Seung Hyun Cheon","Anneke Wernerfelt","Sorelle A. Friedler","Berk Ustun"],"abstract":"Machine learning models routinely automate decisions in applications like lending and hiring. In such settings, consumer protection rules require companies that deploy models to explain predictions to decision subjects. These rules are motivated, in part, by the belief that explanations can promote recourse by revealing information that individuals can use to contest or improve their outcomes. In practice, many companies comply with these rules by providing individuals with a list of the most important features for their prediction, which they identify based on feature importance scores from feature attribution methods such as SHAP or LIME. In this work, we show how these practices can undermine consumers by highlighting features that would not lead to an improved outcome and by explaining predictions that cannot be changed. We propose to address these issues by highlighting features based on their responsiveness score -- i.e., the probability that an individual can attain a target prediction by changing a specific feature. We develop efficient methods to compute responsiveness scores for any model and any dataset. We conduct an extensive empirical study on the responsiveness of explanations in lending. Our results show that standard practices in consumer finance can backfire by presenting consumers with reasons without recourse, and demonstrate how our approach improves consumer protection by highlighting responsive features and identifying fixed predictions.","url_abs":"https://arxiv.org/abs/2410.22598v2","url_pdf":"https://arxiv.org/pdf/2410.22598v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"feature-responsiveness-scores-model-agnostic","repo_url":"https://github.com/ustunb/reachml","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"feature-responsiveness-scores-model-agnostic","repo_url":"https://github.com/ustunb/reach-ml","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"feature-importance","task_name":"Feature Importance"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"lime","method_name":"LIME"},{"method_slug":"shap","method_name":"SHAP"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.22598","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.22598"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ustunb/reachml","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ustunb/reach-ml","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":7},"by_repo_kind":{"listed":{"samples":7,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"8bd1ca22e60b991e","entry":"expand_values","repo":"ustunb/reach-ml","repo_kind":"listed","path":"reachml/utils.py","file_url":"https://github.com/ustunb/reach-ml/blob/HEAD/reachml/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8bd1ca22e60b991e"}},{"code_sha256_prefix":"53a60af562f0ddb7","entry":"get_action_set_file","repo":"ustunb/reach-ml","repo_kind":"listed","path":"reachml/paths.py","file_url":"https://github.com/ustunb/reach-ml/blob/HEAD/reachml/paths.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"53a60af562f0ddb7"}},{"code_sha256_prefix":"2decd86c92adafea","entry":"get_data_csv_file","repo":"ustunb/reach-ml","repo_kind":"listed","path":"reachml/paths.py","file_url":"https://github.com/ustunb/reach-ml/blob/HEAD/reachml/paths.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2decd86c92adafea"}},{"code_sha256_prefix":"a0098860145ad174","entry":"get_data_file","repo":"ustunb/reach-ml","repo_kind":"listed","path":"reachml/paths.py","file_url":"https://github.com/ustunb/reach-ml/blob/HEAD/reachml/paths.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a0098860145ad174"}},{"code_sha256_prefix":"35a58be574ff2f38","entry":"givemecredit_cts_slim","repo":"ustunb/reach-ml","repo_kind":"listed","path":"reachml/datasets.py","file_url":"https://github.com/ustunb/reach-ml/blob/HEAD/reachml/datasets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"35a58be574ff2f38"}},{"code_sha256_prefix":"f1591b2229cee5f4","entry":"has_feature_vector_discrete","repo":"ustunb/reach-ml","repo_kind":"listed","path":"reachml/utils.py","file_url":"https://github.com/ustunb/reach-ml/blob/HEAD/reachml/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f1591b2229cee5f4"}},{"code_sha256_prefix":"90cc02227c088c98","entry":"has_feature_vector_float","repo":"ustunb/reach-ml","repo_kind":"listed","path":"reachml/utils.py","file_url":"https://github.com/ustunb/reach-ml/blob/HEAD/reachml/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"90cc02227c088c98"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}