Implementation of Decision Tree
Aashoo Bais1, Kavita Deshmukh2, Manish Shrivastava3
1Aashoo Bais, M. Tech Student, Department of Information Technology LNCT, Bhopal, (M.P.) India.
2Kavita Deshmukh, Ast. Professor, Department of Information Technology LNCT, Bhopal, (M.P.) India.
3Manish Shrivastava, Head of Department, Department of Information Technology LNCT, Bhopal, (M.P.) India.
Manuscript received on November 21, 2012. | Revised Manuscript received on December 04, 2012. | Manuscript published on December 30, 2012. | PP: 30-34 | Volume-2, Issue-2, December 2012.
Open Access | Ethics and Policies | Cite
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Data mining is rich field of algorithms and data structures to arrange negotiate and navigate the information from the different source of data. There are various kind of mining approaches are developed and implemented to get the knowledge from the raw data. The application of this knowledge is used to enhance the research, organizational growth and others. The data and its complexity is increases day by day in an explosive manner, and due to these complexity there are is a need to discover patterns and knowledge from the large data set. The conventional algorithm that are used to mine the patterns from data are becomes less effective due to the complexity of data. Due to this required to introduce some performance study and improvements over the conventional model to get efficient and effective data modeling technique. In this paper we introduce a modification over the traditional algorithm ID3 and C4.5 to make capable the algorithms to work with large dataset with higher performance. Here we provide the implementation, performance analysis and conclusion after implementation of the work.
Keywords: Data Mining, Modification, Large Datasets, Performance Issues, Implementation, Performance Analysis.