Classification is one of the major tasks in data mining and has also been studied extensively in statistics, machine learning, expert systems, and different application areas on different domains over decades. Decision tree is one of the popular and practical classification approaches in data mining. It is also widely used in several research areas. Tree growing methods used to construct the decision tree may vary the performance of this classifier. Tree based classification algorithms are separated based on their attribute selection measure method. Therefore, this paper presents the comparative analysis of different tree based algorithms such as CART, ID3, J48, Random Tree and PART. Macro average accuracy, precision, recall, and F-measure are used for performance comparisons of these algorithms by using WEKA tool.
Thin Thin Swe (2019); Analysis of Tree Based Supervised Learning Algorithms on Medical Data; International Journal of Scientific and Research Publications (IJSRP)
9(4) (ISSN: 2250-3153), DOI: http://dx.doi.org/10.29322/IJSRP.9.04.2019.p8817