GAM Coach: Towards Interactive and User-centered Algorithmic Recourse
Machine learning (ML) recourse techniques are increasingly used in high-stakes domains, providing end users with actions to alter ML predictions, but they assume ML developers understand what input variables can be changed. However, a recourse plan's actionability is subjective and unlikely to...
Gespeichert in:
| Veröffentlicht in: | arXiv.org 2023-03 |
|---|---|
| Hauptverfasser: | , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | arXiv.org |
| container_volume | |
| creator | Wang, Zijie J Jennifer Wortman Vaughan Caruana, Rich Duen Horng Chau |
| description | Machine learning (ML) recourse techniques are increasingly used in high-stakes domains, providing end users with actions to alter ML predictions, but they assume ML developers understand what input variables can be changed. However, a recourse plan's actionability is subjective and unlikely to match developers' expectations completely. We present GAM Coach, a novel open-source system that adapts integer linear programming to generate customizable counterfactual explanations for Generalized Additive Models (GAMs), and leverages interactive visualizations to enable end users to iteratively generate recourse plans meeting their needs. A quantitative user study with 41 participants shows our tool is usable and useful, and users prefer personalized recourse plans over generic plans. Through a log analysis, we explore how users discover satisfactory recourse plans, and provide empirical evidence that transparency can lead to more opportunities for everyday users to discover counterintuitive patterns in ML models. GAM Coach is available at: https://poloclub.github.io/gam-coach/. |
| doi_str_mv | 10.48550/arxiv.2302.14165 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_arxiv</sourceid><recordid>TN_cdi_arxiv_primary_2302_14165</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2781413433</sourcerecordid><originalsourceid>FETCH-LOGICAL-a523-f1a980a9e3a274a0dbbb56efc68ab840f9ba431c0888e0b8efad326cd454f2413</originalsourceid><addsrcrecordid>eNotj1FLwzAUhYMgOOZ-gE8GfO5McpMu9W2MOQcTQepzuU1vXMfWzqSb-u_tNp8OHD4O52PsToqxtsaIRww_9XGsQKix1DI1V2ygAGRitVI3bBTjRgih0okyBgZsvpi-8lmLbv3E8_YbQxX5sukooOvqI3FsKv4RKSSOTi1VfLr9bEPdrXe14-_k2kOIdMuuPW4jjf5zyPLneT57SVZvi-VsukrQKEi8xMwKzAhQTTSKqixLk5J3qcXSauGzEjVIJ6y1JEpLHitQqau00V5pCUN2f5k9Oxb7UO8w_BYn1-Ls2hMPF2If2q8Dxa7Y9Aeb_lOhJrZnQAPAH4sbVn8</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2781413433</pqid></control><display><type>article</type><title>GAM Coach: Towards Interactive and User-centered Algorithmic Recourse</title><source>arXiv.org</source><source>Free E- Journals</source><creator>Wang, Zijie J ; Jennifer Wortman Vaughan ; Caruana, Rich ; Duen Horng Chau</creator><creatorcontrib>Wang, Zijie J ; Jennifer Wortman Vaughan ; Caruana, Rich ; Duen Horng Chau</creatorcontrib><description>Machine learning (ML) recourse techniques are increasingly used in high-stakes domains, providing end users with actions to alter ML predictions, but they assume ML developers understand what input variables can be changed. However, a recourse plan's actionability is subjective and unlikely to match developers' expectations completely. We present GAM Coach, a novel open-source system that adapts integer linear programming to generate customizable counterfactual explanations for Generalized Additive Models (GAMs), and leverages interactive visualizations to enable end users to iteratively generate recourse plans meeting their needs. A quantitative user study with 41 participants shows our tool is usable and useful, and users prefer personalized recourse plans over generic plans. Through a log analysis, we explore how users discover satisfactory recourse plans, and provide empirical evidence that transparency can lead to more opportunities for everyday users to discover counterintuitive patterns in ML models. GAM Coach is available at: https://poloclub.github.io/gam-coach/.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.2302.14165</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Artificial intelligence ; Computer Science - Artificial Intelligence ; Computer Science - Human-Computer Interaction ; Computer Science - Learning ; Empirical analysis ; End users ; Integer programming ; Linear programming ; Machine learning ; User satisfaction</subject><ispartof>arXiv.org, 2023-03</ispartof><rights>2023. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,777,781,882,27906</link.rule.ids><backlink>$$Uhttps://doi.org/10.1145/3544548.3580816$$DView published paper (Access to full text may be restricted)$$Hfree_for_read</backlink><backlink>$$Uhttps://doi.org/10.48550/arXiv.2302.14165$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Wang, Zijie J</creatorcontrib><creatorcontrib>Jennifer Wortman Vaughan</creatorcontrib><creatorcontrib>Caruana, Rich</creatorcontrib><creatorcontrib>Duen Horng Chau</creatorcontrib><title>GAM Coach: Towards Interactive and User-centered Algorithmic Recourse</title><title>arXiv.org</title><description>Machine learning (ML) recourse techniques are increasingly used in high-stakes domains, providing end users with actions to alter ML predictions, but they assume ML developers understand what input variables can be changed. However, a recourse plan's actionability is subjective and unlikely to match developers' expectations completely. We present GAM Coach, a novel open-source system that adapts integer linear programming to generate customizable counterfactual explanations for Generalized Additive Models (GAMs), and leverages interactive visualizations to enable end users to iteratively generate recourse plans meeting their needs. A quantitative user study with 41 participants shows our tool is usable and useful, and users prefer personalized recourse plans over generic plans. Through a log analysis, we explore how users discover satisfactory recourse plans, and provide empirical evidence that transparency can lead to more opportunities for everyday users to discover counterintuitive patterns in ML models. GAM Coach is available at: https://poloclub.github.io/gam-coach/.</description><subject>Artificial intelligence</subject><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Human-Computer Interaction</subject><subject>Computer Science - Learning</subject><subject>Empirical analysis</subject><subject>End users</subject><subject>Integer programming</subject><subject>Linear programming</subject><subject>Machine learning</subject><subject>User satisfaction</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GOX</sourceid><recordid>eNotj1FLwzAUhYMgOOZ-gE8GfO5McpMu9W2MOQcTQepzuU1vXMfWzqSb-u_tNp8OHD4O52PsToqxtsaIRww_9XGsQKix1DI1V2ygAGRitVI3bBTjRgih0okyBgZsvpi-8lmLbv3E8_YbQxX5sukooOvqI3FsKv4RKSSOTi1VfLr9bEPdrXe14-_k2kOIdMuuPW4jjf5zyPLneT57SVZvi-VsukrQKEi8xMwKzAhQTTSKqixLk5J3qcXSauGzEjVIJ6y1JEpLHitQqau00V5pCUN2f5k9Oxb7UO8w_BYn1-Ls2hMPF2If2q8Dxa7Y9Aeb_lOhJrZnQAPAH4sbVn8</recordid><startdate>20230301</startdate><enddate>20230301</enddate><creator>Wang, Zijie J</creator><creator>Jennifer Wortman Vaughan</creator><creator>Caruana, Rich</creator><creator>Duen Horng Chau</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20230301</creationdate><title>GAM Coach: Towards Interactive and User-centered Algorithmic Recourse</title><author>Wang, Zijie J ; Jennifer Wortman Vaughan ; Caruana, Rich ; Duen Horng Chau</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a523-f1a980a9e3a274a0dbbb56efc68ab840f9ba431c0888e0b8efad326cd454f2413</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Artificial intelligence</topic><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Human-Computer Interaction</topic><topic>Computer Science - Learning</topic><topic>Empirical analysis</topic><topic>End users</topic><topic>Integer programming</topic><topic>Linear programming</topic><topic>Machine learning</topic><topic>User satisfaction</topic><toplevel>online_resources</toplevel><creatorcontrib>Wang, Zijie J</creatorcontrib><creatorcontrib>Jennifer Wortman Vaughan</creatorcontrib><creatorcontrib>Caruana, Rich</creatorcontrib><creatorcontrib>Duen Horng Chau</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection><collection>arXiv Computer Science</collection><collection>arXiv.org</collection><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Wang, Zijie J</au><au>Jennifer Wortman Vaughan</au><au>Caruana, Rich</au><au>Duen Horng Chau</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>GAM Coach: Towards Interactive and User-centered Algorithmic Recourse</atitle><jtitle>arXiv.org</jtitle><date>2023-03-01</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>Machine learning (ML) recourse techniques are increasingly used in high-stakes domains, providing end users with actions to alter ML predictions, but they assume ML developers understand what input variables can be changed. However, a recourse plan's actionability is subjective and unlikely to match developers' expectations completely. We present GAM Coach, a novel open-source system that adapts integer linear programming to generate customizable counterfactual explanations for Generalized Additive Models (GAMs), and leverages interactive visualizations to enable end users to iteratively generate recourse plans meeting their needs. A quantitative user study with 41 participants shows our tool is usable and useful, and users prefer personalized recourse plans over generic plans. Through a log analysis, we explore how users discover satisfactory recourse plans, and provide empirical evidence that transparency can lead to more opportunities for everyday users to discover counterintuitive patterns in ML models. GAM Coach is available at: https://poloclub.github.io/gam-coach/.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.2302.14165</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | EISSN: 2331-8422 |
| ispartof | arXiv.org, 2023-03 |
| issn | 2331-8422 |
| language | eng |
| recordid | cdi_arxiv_primary_2302_14165 |
| source | arXiv.org; Free E- Journals |
| subjects | Artificial intelligence Computer Science - Artificial Intelligence Computer Science - Human-Computer Interaction Computer Science - Learning Empirical analysis End users Integer programming Linear programming Machine learning User satisfaction |
| title | GAM Coach: Towards Interactive and User-centered Algorithmic Recourse |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-19T18%3A28%3A53IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_arxiv&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=GAM%20Coach:%20Towards%20Interactive%20and%20User-centered%20Algorithmic%20Recourse&rft.jtitle=arXiv.org&rft.au=Wang,%20Zijie%20J&rft.date=2023-03-01&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.2302.14165&rft_dat=%3Cproquest_arxiv%3E2781413433%3C/proquest_arxiv%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2781413433&rft_id=info:pmid/&rfr_iscdi=true |