Predicting Indian Supreme Court Judgments, Decisions, or Appeals

Abstract

Abstract Legal predictive models are of enormous interest and value to legal community. The stakeholders, particularly, the judges and attorneys, can take the best advantages of these models to predict the case outcomes to further augment their future course of actions, for example speeding up decision making, support arguments, strengthening the defense, etc. However, accurately predicting the legal decisions and case outcomes is an arduous process, which involves several complex steps—finding suitable bulk case documents, data extracting, cleansing and engineering, etc. Additionally, the legal complexity further adds to its intricacies. In this paper, we introduce our newly developed Machine Learning (ML)-enabled legal prediction model and its operational prototype, eLegPredict, which successfully predicts the Indian supreme court decisions. The eLegPredict is trained and tested over 3072 supreme court cases and has achieved 76% accuracy (F1-score). The eLegPredict is equipped with a mechanism to aid end users, where as soon as a document with new case description is dropped into a designated directory, the system quickly reads through its content and generates prediction. To our understanding, eLegPredict is one of the first few legal prediction models trying to predict Indian supreme court decisions.