Predicting Court Rulings with SVM and NL

P. Subashini, Satyajeet Sarfare, M. Vaibhav and P. Abhijith

Experts have increasingly investigated machine learning as an alternative to expert-based judgment or purely data-driven approaches to predicting the court decisions. Under certain conditions, scholars have found that machine learning can outperform these other approaches. However, despite interest in the topic and a series of successful use cases, relatively few studies have applied empirical model thinking to evaluate the accuracy and robustness of machine learning in real-world contexts. In this paper, we offer novel contributions. First, we explore a dataset of large number of rulings from over multiple hundreds cases in a multi-city environment to predict the decisions of the European Court of Human Rights. Second, we develop a comprehensive crowd construction framework that allows for the formal description and application of machine learning to real-world data. Third, we apply this framework to our data to construct learning models. We find that in out-of-sample historical simulations, machine learning robustly outperforms the commonly-accepted null model, yielding the performance for this context at high case level accuracy. To our knowledge, this dataset and analysis represent one of the largest explorations of recurring human prediction to date, and our results provide additional empirical support for the use of machine learning as a prediction method.

Volume 11 | 04-Special Issue

Pages: 1123-1129