AI and Judicial Productivity: The Impact of MIDAS on the Courts of Fortaleza, Brazil
Date issued
July 2026
Subject
Productivity;
Labor Force;
Artificial Intelligence;
Justice Administration;
Natural Language Processing;
Criminal Justice;
Closing;
Machine Learning
JEL code
O33 - Technological Change: Choices and Consequences • Diffusion Processes;
H83 - Public Administration • Public Sector Accounting and Audits;
K40 - Legal Procedure, the Legal System, and Illegal Behavior: General;
C93 - Field Experiments;
J24 - Human Capital • Skills • Occupational Choice • Labor Productivity
Country
Brazil
Category
Working Papers
This paper presents preliminary results from a pilot study conducted in the courts of Ceará, Brazil. The study evaluates the impact of introducing a tool that uses natural language processing and machine learning techniques to cluster judicial acts by textual similarity on clerk productivity, measured as the number of case files a clerk can produce in a day. Estimates indicate that treatment-group clerks produced approximately 10 more case files per day than control-group clerks, a statistically significant difference equivalent to a 37% increase relative to the control group mean. The results are robust to the exclusion of outlier observations and exceptionally productive clerks.
NO