Comparison of Artificial Neural Networks and Decision Trees Methods on Health Insurance Data |
Author(s): |
| Burcin Seyda Corba , ONDOKUZ MAYIS UNIVERSITY; Pelin KASAP, ONDOKUZ MAYIS UNIVERSITY; Tuba Celebi, ONDOKUZ MAYIS UNIVERSITY |
Keywords: |
| Artificial Neural Networks Model; CART Algorithm; C4.5 Algorithm; CRISP-DM; Data Mining |
Abstract |
|
In this study, the insurance expenditures of the people who have health insurance are evaluated. We present Business understanding and Data understanding stages of The Cross-Industry Standard Process for Data Mining (CRISP-DM) process to investigate attributes influencing health insurance. In Data preparation stage of CRISP-DM process, Artificial Neural Networks (ANNs) method, C4.5 and Classification and Regression Trees (CART) Algorithms are used. When the applied methods are compared, it is shown that C4.5 is the most appropriate model with high accuracy rate. |
Other Details |
|
Paper ID: IJSRDV6I100181 Published in: Volume : 6, Issue : 10 Publication Date: 01/01/2019 Page(s): 252-257 |
Article Preview |
|
|
|
|
