NyayaAnumana Indian Legal Judgment Prediction

NyayaAnumana Indian Legal Judgment Prediction

Largest Indian legal judgment prediction dataset with 702,945 preprocessed court cases from Supreme Court, High Courts, Tribunals, and District Courts (collected from Indian Kanoon up to April 2024). Includes Maharashtra cases from Bombay High Court and district courts with structured judgment outcome labels.

Build a legal precedent search engine for Bombay High Court judgments enabling semantic search over case law.
HomepageGitHubPaper

Quick Start

from datasets import load_dataset
# ds = load_dataset('opennyai/InLegalBERT')
print('Nyaya Anumana: Indian Legal NLP')
print('Judgments from Supreme Court and High Courts')
Modality
text
Size
702,945 preprocessed court cases with structured labels
License
Format
Text + structured annotations
Language
en
Update Frequency
static
Organization
COLING 2025
Category
governance-census-demographics-legal

Schema

FieldTypeDescription
judgment_textstringFull judgment text
courtstringCourt name
case_typestringType of case
decisionstringCase decision/outcome

Build With This

Create a case outcome predictor for Maharashtra courts using historical judgment patterns and NLP analysis
Develop a legal argument extractor that identifies key reasoning chains in Bombay High Court judgments
Build a judgment complexity scorer helping lawyers estimate case difficulty based on similar past judgments

AI Use Cases

Court judgment prediction for Maharashtra casesLegal outcome forecastingCase law similarity searchLegal trend analysis across Bombay High Court
Last verified: 2026-03-09