{"id":15605826,"url":"https://github.com/hinthornw/supreme_predictions","last_synced_at":"2025-07-26T17:05:54.755Z","repository":{"id":87030030,"uuid":"89093975","full_name":"hinthornw/supreme_predictions","owner":"hinthornw","description":"Princeton COS 424 final project: Predicting Supreme Court Decisions","archived":false,"fork":false,"pushed_at":"2017-05-16T21:33:52.000Z","size":3915,"stargazers_count":0,"open_issues_count":0,"forks_count":1,"subscribers_count":6,"default_branch":"master","last_synced_at":"2025-04-02T08:48:43.362Z","etag":null,"topics":["forests","law","random"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/hinthornw.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2017-04-22T19:27:10.000Z","updated_at":"2017-07-28T06:36:05.000Z","dependencies_parsed_at":"2023-10-11T07:57:27.279Z","dependency_job_id":null,"html_url":"https://github.com/hinthornw/supreme_predictions","commit_stats":{"total_commits":41,"total_committers":5,"mean_commits":8.2,"dds":0.5365853658536586,"last_synced_commit":"054bb5fbff6c871473a43f2b4ada6b99086c6b41"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/hinthornw/supreme_predictions","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hinthornw%2Fsupreme_predictions","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hinthornw%2Fsupreme_predictions/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hinthornw%2Fsupreme_predictions/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hinthornw%2Fsupreme_predictions/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hinthornw","download_url":"https://codeload.github.com/hinthornw/supreme_predictions/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hinthornw%2Fsupreme_predictions/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":267198671,"owners_count":24051559,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-07-26T02:00:08.937Z","response_time":62,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["forests","law","random"],"created_at":"2024-10-03T04:16:46.468Z","updated_at":"2025-07-26T17:05:54.737Z","avatar_url":"https://github.com/hinthornw.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Predicting the Decisions of Supreme Court Justices\n\n## Authors: William Hinthorn, Maia Ezratty, Mihika Kapoor, Alice Zheng\n\n### COS 424 Final Project\n\nFor more notes, see our [wiki](https://github.com/hinthornw/supreme_predictions/wiki).\n\nA pdf copy of our findings is stored [here](/writeup/424_Final_Project.pdf).\n\nDataset: \nHarold J. Spaeth, Lee Epstein, Andrew D. Martin, Jeffrey A. Segal, Theodore J. Ruger, and Sara C. Benesh. 2016 Supreme Court Database, Version 2016 Release 01. URL: http://Supremecourtdatabase.org \n\nTo download the dataset, go to the [website](http://scdb.wustl.edu/data.php) and download the case-centered [csv file](http://scdb.wustl.edu/_brickFiles/2016_01/SCDB_2016_01_caseCentered_Citation.csv.zip). \n\n##### The dataset contains  of 8,737 cases with the following headers:\n\ncaseId, \ndocketId, \ncaseIssuesId, \nvoteId, \ndateDecision, \ndecisionType, \nusCite, \nsctCite, \nledCite, \nlexisCite, \nterm, \nnaturalCourt, \nchief, \ndocket, \ncaseName, \ndateArgument, \ndateRearg, \npetitioner, \npetitionerState, \nrespondent, \nrespondentState, \njurisdiction, \nadminAction, \nadminActionState, \nthreeJudgeFdc, \ncaseOrigin, \ncaseOriginState, \ncaseSource, \ncaseSourceState, \nlcDisagreement, \ncertReason, \nlcDisposition, \nlcDispositionDirection, \ndeclarationUncon, \ncaseDisposition, \npartyWinning, \nprecedentAlteration, \nvoteUnclear, \nissue, \nissueArea, \ndecisionDirection, \ndecisionDirectionDissent, \nauthorityDecision1, \nauthorityDecision2, \nlawType, \nlawSupp, \nlawMinor, \nmajOpinWriter, \nmajOpinAssigner, \nsplitVote, \nmajVotes, and\nminVotes\n\n##### The second dataset is [justice centered](http://scdb.wustl.edu/_brickFiles/2016_01/SCDB_2016_01_justiceCentered_Citation.csv.zip) (same source).\n\nIt has field names: \ncaseId,\ndocketId,\ncaseIssuesId,\nvoteId,\ndateDecision,\ndecisionType,\nusCite,\nsctCite,\nledCite,\nlexisCite,\nterm,\nnaturalCourt,\nchief,\ndocket,\ncaseName,\ndateArgument,\ndateRearg,\npetitioner,\npetitionerState,\nrespondent,\nrespondentState,\njurisdiction,\nadminAction,\nadminActionState,\nthreeJudgeFdc,\ncaseOrigin,\ncaseOriginState,\ncaseSource,\ncaseSourceState,\nlcDisagreement,\ncertReason,\nlcDisposition,\nlcDispositionDirection,\ndeclarationUncon,\ncaseDisposition,\ncaseDispositionUnusual,\npartyWinning,\nprecedentAlteration,\nvoteUnclear,\nissue,\nissueArea,\ndecisionDirection,\ndecisionDirectionDissent,\nauthorityDecision1,\nauthorityDecision2,\nlawType,\nlawSupp,\nlawMinor,\nmajOpinWriter,\nmajOpinAssigner,\nsplitVote,\nmajVotes,\nminVotes,\njustice,\njusticeName,\nvote,\nopinion,\ndirection,\nmajority,\nfirstAgreement,\nsecondAgreement,\n\n\nWe used feature selection, generation, and ranom forests classifiers to build a flexible model which predicts the decisions of the court with an average accuracy of ~80-90%. We obtained similar results by building dedicated models for individual justices.\n\nHere are some cool findings:\n\n\nWe found out that judges tend to stay true to their original biases throughout the length of their term. \n\n![biases](figures/justice_bias.png)\n\nExcept for a few outliers, like Harry Blackmun, who we assume was influenced by the world wars and the New Deal programs to turn an early conservative Justice into an liberally-minded older man. Note that the moderates tend to have shorter terms (though we do not imply any health benefits of having a political bias).\n\nThese biases play a huge role on the bias of the court at large. We show the cumulative sum of justice's voting biases spread out over the cases that are included within the dataset.\n\n![biases_temporal](figures/justice_bias_temporal.png)\n\nWe looked at correlations in voting habits of justices over the length of the term covered by the modern dataset (seen below)\n\n![Covariences](figures/covariances.png)\n\n\nAnd generated features based on clustering methods:\n\n![minMaj](figures/majMin.png)\n![biasVec](figures/average_bias_pca.png)\n\n\n\nWe then used textual data from [CourtListener](https://www.courtlistener.com) and correlated bags of words with political bias of the individual Justice using there $\\chi^2$ values. Below are some word clouds representing our findings.\n\n\nThe first two show words that are strongly correlated with a justice being in the majority vote (left) or dissent (right).\n\n![direction](figures/direction_wordcloud_chi2.png)\n![majority](figures/majority_wordcloud_chi2.png)\n\n\nThe next two show words strongly correlated with a Justice voting in along a more liberal line (left) or conservative one (right)\n\n\n![conservative](figures/liberal_majority_chi2.png)\n![consMaj](figures/conservative_majority_chi2.png)\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhinthornw%2Fsupreme_predictions","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhinthornw%2Fsupreme_predictions","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhinthornw%2Fsupreme_predictions/lists"}