Performance Improvement of Decision Tree: A Robust Classifier Using Tabu Search Algorithm

Classification and regression are the major applications of machine learning algorithms which widely used to solve problems in numerous domains engineering computer science. Different classifiers based on optimization decision tree have been proposed, however, it is still evolving over time. This paper presents a novel robust classifier tabu search algorithms, respectively. In aim improving performance, our proposed algorithm constructs multiple trees while employing consistently monitor leaf nodes corresponding trees. Additionally, responsible balance entropy For training model, we clinical data COVID-19 patients predict whether patient suffering. The experimental results were obtained using built-in sci-kit learn library Python. extensive analysis for performance comparison was presented Big O statistical conventional supervised algorithms. Moreover, optimized state-of-the-art also presented. achieved accuracy 98%, required execution time 55.6 ms area under receiver operating characteristic (AUROC) method 0.95 reveals that convenient large datasets.