Dataset for Research Article titled Hybrid Machine Learning Modelling with Explainability for Predicting Case Delays and Durations in Indian Lower Courts

This repository accompanies the research article“Hybrid Machine Learning Modelling with Explainability for Predicting Case Delays and Durations in Indian Lower Courts”by Mohit Bhatnagar and Shivaraj Huchhanavar. It contains all pre-processed datasets and results generated. The datasets enable replication of the hybrid classification–regression pipeline used to predict judicial delays and case durations based on filing-stage variables from over 22.4 million criminal cases drawn from the e-Courts / National Judicial Data Grid (NJDG) in India. The pre-processed dataset included here is based on data collated by Ash et al. (2025),“In-Group Bias in the Indian Judiciary: Evidence from 5 Million Criminal Cases”,The Review of Economics and Statistics (DOI: 10.1162/rest_a_01569), and made publicly available at https://www.devdatalab.org/judicial-data. Licensing and Attribution:Contains information from https://www.devdatalab.org/judicial-data,which is made available under the Open Database License (ODbL).Any rights in individual contents of the database are licensed under the Database Contents License (DbCL).You must attribute the original source in any public use or redistribution of these data. Derived pre-processed datasets and analysis scripts in this repository are released under the same licensing terms as the original dataset (ODbL/DbCL).