Using deep learning to predict outcomes of legal appeals better than human experts: A study with data from Brazilian federal courts

• Elias Jacob de Menezes-Neto ,

  Contributed equally to this work with: Elias Jacob de Menezes-Neto, Marco Bruno Miranda Clementino

  Roles Conceptualization, Data curation, Formal analysis, Funding acquisition, Investigation, Methodology, Project administration, Software, Validation, Visualization, Writing – original draft, Writing – review & editing

  * E-mail: elias.jacob@ufrn.br

  Affiliation Department of Law, Universidade Federal do Rio Grande do Norte, Caicó, RN, Brazil

  https://orcid.org/0000-0002-1153-8899

  ⨯
• Marco Bruno Miranda Clementino

  Contributed equally to this work with: Elias Jacob de Menezes-Neto, Marco Bruno Miranda Clementino

  Roles Conceptualization, Investigation, Methodology, Writing – original draft, Writing – review & editing

  Affiliations Department of Private Law, Universidade Federal do Rio Grande do Norte, Natal, RN, Brazil, 6th Federal Court, Tribunal Regional Federal da 5a Região, Natal, RN, Brazil

  ⨯