Monash University

Over the last decade classification has been an important issue for data mining technology. Now-a-days researchers in the machine learning and statistics communities are trying to build a better classifier. In this study several classifier characteristics based on rule learner, decision tree, Bayesian theorem, neural networks, nearest neighbors and statistical learner for data mining classification task are presented. Experimental results show that Support Vector Machine (SVM) based on statistical learner outperforms others on the basis of accuracy. But it is computationally expensive compared to others. Finally future research directions are presented.

Mr. Shawkat Ali received his Bachelor of Honors and Master’s of Science in Electronics and Applied Physics from Rajshahi University, Bangladesh in 1994 and 1995 respectively. After that he joined as a Masters Research Fellow in the Department of Computer Science and Technology, Rajshahi University, Bangladesh in February 1995. Before submitting his Master’s thesis, he joined in the Department of Computer Science and Technology, Islamic University, Bangladesh as a Lecturer in February 15, 1997. He has been promoted as an Assistant Professor in the same Department in February 15, 1999. Now he is on study leave. Currently he is a PhD research scholar in the Gippsland School of Computing and Information Technology, Monash University, Australia. His main research area is machine learning and data mining.

Monash University

School of Computing and Information Technology

2002 Gippsland Campus Seminar Series