A Review of Decision Tree Algorithms for Predictive Analysis in Data Mining

Diana Moses*, B. DEEPA**, Trilochan Patri***, M.Sowmya****
DOI : https://doi.org/10.26634/jse.12.1.13923


There is a wealth of data archived by business organizations. Analysis of this data provides predictive information for taking proactive decisions and making statistical algorithms which are used for improving the knowledge regarding the engineering process and analysis of data. Data mining is a class of algorithms that analyses the relationship between data and identifies futuristic trends from archived data. Decision tree learning will help us to create a predictive model which will map different items consisting in the set of data and its targets in such a way that each element in this dataset is true. There are many strategies to construct the decision trees, but ID3 is one of the simplest and popularly used decision tree algorithms as there is a disadvantage in ID3 algorithm that it gives more importance to the attributes having multiple values while selecting any item affecting the decision tree. Hence in this paper, the objective is to justify that C4.5 algorithm works better than the ID3 algorithm. C4.5 system of Quinlan is one best classification algorithm that deserves a special mention for several reasons. First best reason is that it is used to represent result of research in machine learning that traces back to the ID3 system. For that reason it is taken as the point of reference for the development and analysis of novel proposals. On the other hand the results of the datasets in this paper proves that C4.5 tree-induction algorithm provides good classification, accuracy, and it is the fastest among the compared main memory algorithms for machine learning and data mining.


Decision Tree Algorithms, ID3 Algorithm, C4.5 Algorithm, Data Mining.

How to Cite this Article?

Moses, D., Deepa, B., Patri , T., and Sowmya, M. (2017). A Review of Decision Tree Algorithms for Predictive Analysis in Data Mining. i-manager’s Journal on Software Engineering, 12(1), 38-45. https://doi.org/10.26634/jse.12.1.13923


If you have access to this article please login to view the article or kindly login to purchase the article
Options for accessing this content:
  • If you would like institutional access to this content, please recommend the title to your librarian.
    Library Recommendation Form
  • If you already have i-manager's user account: Login above and proceed to purchase the article.
  • New Users: Please register, then proceed to purchase the article.

Purchase Instant Access

Single Article

Print 35 35 200
Online 35 35 200
Print & Online 35 35 400