Title: Forecasting the decision making process of Supreme Court using hierarchical convolutional neural network
Authors: N. Sivaranjani; J. Jayabharathy
Addresses: Pondicherry Engineering College, Pillaichavady, Pondicherry, India ' Pondicherry Engineering College, Pillaichavady, Pondicherry, India
Abstract: Artificial intelligence is one of the most energising innovations applied in many fields like text processing, and image processing. Every case, which is present in the courtroom, is inspired to get justice. In this paper, we propose a decision forecasting model which aims to predict whether the filed case in the Supreme Court and also the cases with an unsatisfied decision from the lower court will win or not by considering the past similar cases. This is to be able to better predict if the current case will win if an appeal is chosen. In this paper, two algorithms have been proposed: 1) bi-SVM, it is used to classify the cases as civil or criminal; 2) C-XGB is used to predict the chances of winning. When an out-of-sample case, is given as input, the model yields 96% of accuracy which is higher than the accuracy of existing models.
Keywords: neural networks; machine learning; feature engineering; Chi2 (χ2); convolutional neural network; CNN; error metrics.
International Journal of Ad Hoc and Ubiquitous Computing, 2022 Vol.40 No.1/2/3, pp.116 - 126
Received: 20 Jan 2021
Accepted: 03 Mar 2021
Published online: 27 Jun 2022 *