Article
Version 1
Preserved in Portico This version is not peer-reviewed
Performance Analysis of CHAID Algorithm for Accuracy
Version 1
: Received: 13 May 2023 / Approved: 15 May 2023 / Online: 15 May 2023 (07:53:11 CEST)
A peer-reviewed article of this Preprint also exists.
Yang, Y.; Yi, F.; Deng, C.; Sun, G. Performance Analysis of the CHAID Algorithm for Accuracy. Mathematics 2023, 11, 2558. Yang, Y.; Yi, F.; Deng, C.; Sun, G. Performance Analysis of the CHAID Algorithm for Accuracy. Mathematics 2023, 11, 2558.
Abstract
Chi-squared automatic interaction detector (CHAID) algorithm is considered to be one of the mostly used supervised learning methods as it is adaptable to solving any kind of problem at hand. We have been starkly aware of CHAID maps non-linear relationships quite well, and it can empower predictive models with stability. But we don’t know how high its accuracy is precisely. To find out the perfect scope CHAID algorithm fits into, this paper presents the analysis of the accuracy of the CHAID algorithm. We introduce the causes, applicable conditions and application scope of CHAID algorithm at first, and then highlight the difference of branching principal between the CHAID algorithm and several other common decision tree algorithms, which is our first step towards basic analysis on CHAID algorithm. We next employee an actual branching case to help us understand CHAID algorithm better. Specifically, we use vehicle customer satisfaction data to compare multiple decision tree algorithms, and cite some factors that affecting the accuracy and some corresponding countermeasures which are more conducive to us to obtain accurate results. The results show that CHAID can analyze the data very well, and detect the significantly correlated factors surely. In this paper, we learn the clear information required to understand CHAID algorithm, thereby make better choices when we need to use decision tree algorithms.
Keywords
CHAID algorithm; Chi-square detection; Decision tree algorithm; Branching principle
Subject
Computer Science and Mathematics, Computer Science
Copyright: This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Comments (1)
We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.
Leave a public commentSend a private comment to the author(s)
* All users must log in before leaving a comment
Commenter: Lu Su
The commenter has declared there is no conflict of interests.