Classification of Multi-Criteria Group Decision Making in Dynamic Environments for Resolving Corruption Cases

Abstract

In group decision making, decision-makers have their criteria for making decisions so that the decision-making parameters have a multi-criteria nature. Things like this often happen in dynamic environments. One example of a multicriteria problem in a dynamic environment is when the Inspectorate Work Unit examines corruption cases. In one corruption case, there are many criteria (multi-criteria), and it is dynamic to solve them. For this reason, the Inspectorate can choose the criteria used by the classification method, including Neural Network, Logistic Regression, SVC, Gradient Boosting Classifier, Extra Trees Classifier, Bagging Classifier, AdaBoost Classifier, Gaussian NB, MLP Classifier, XGB Classifier, LGBM Classifier, K Nearest Neighbor Classifier, Decision Tree Classifier, and Random Forest Classifier. The data used is the Inspectorate s criteria data to examine corruption cases. The five criteria are classified into three criteria with several classification methods. Each classification method can choose criteria, and it can be seen the accuracy of the selection of criteria. The highest accuracy is 100%, so it can be concluded that the classification method can be used to select criteria and support group decision making.