Comparative Analysis of Decision Tree Classification Algorithms
Date
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Department of Computer Science and Information Technology
Abstract
In our daily life there is lots of records, phone call records, salary records, homework
records, assignment record, personal details record, sales record, song, videos and so
on. These all records kept in a table are called data; we have lots of data in different
field. Whenever there is data we can have lots of information, patterns, meaning etc.
Data mining applications has got rich focus due to its significance of classification
algorithms. The comparison of classification algorithm is a complex and it is an open
problem. First, the notion of the performance can be defined in many ways: accuracy,
speed, cost, reliability, etc. Second, an appropriate tool is necessary to quantify this
performance. Third, a consistent method must be selected to compare with the
measured values. The selection of the best classification algorithm for a given dataset
is a very widespread problem. In this sense it requires to make several methodological
choices. So this research focused in the analysis of decision tree classification
algorithm in different datasets of multiple attributes and multiple instances. Where
analysis was done among five decision tree algorithms (BFTree, J48, Random Tree,
REP Tree and Simple Cart).J 48 was able to classify 82.16% of the data correctly which
was best among all in comparison to results of evaluation metrics (Accuracy,
Precision, Recall and F-Measure) and Simple Cart was able to build decision tree with
small tree size of 17.24 (averaged value).
Keywords: BF Tree,CART, Data Mining, Decision Tree, J48,Random Tree,
REP Tree.