International Journal of Computer Science and Security | |
Comparative Analysis of Serial Decision Tree Classification Algorithms | |
Matthew Nwokejizie Anyanwu1  Sajjan Shiva1  | |
[1] $$ | |
关键词: Decision tree; Classification Algorithm; data; | |
DOI : | |
来源: Computer Science and Security | |
【 摘 要 】
Classification of data objects based on a predefinedknowledge of the objects is a data mining and knowledgemanagement technique used in grouping similar data objectstogether. It can be defined as supervised learning algorithmsas it assigns class labels to data objects based on the relationshipbetween the data items with a pre-defined class label.Classification algorithms have a wide range of applicationslike churn prediction, fraud detection, artificial intelligence,and credit card rating etc. Also there are many classificationalgorithms available in literature but decision trees is the mostcommonly used because of its ease of implementation and easierto understand compared to other classification algorithms.Decision Tree classification algorithm can be implemented in aserial or parallel fashion based on the volume of data, memoryspace available on the computer resource and scalability ofthe algorithm. In this paper we will review the serial implementationsof the decision tree algorithms, identify those thatare commonly used. We will also use experimental analysisbased on sample data records (Statlog data sets) to evaluatethe performance of the commonly used serial decision treealgorithms
【 授权许可】
Unknown
【 预 览 】
Files | Size | Format | View |
---|---|---|---|
RO201912040511466ZK.pdf | 111KB | download |