|
Predicting Tax Evasion by Decision Tree Algorithms
|
Mohammad Namazi *1   , Mohammad Sadeghzadeh Maharluie1 |
| 1- Shiraz University |
|
|
Abstract: (2829 Views) |
| This study investigates the ability of tax evasion prediction of listed companies in Tehran Stock Exchange (TSE) by Decision Tree Algorithms. Statistical population of this study is all companies listed in TSE from 2005 to 2016. Statistical sample includes 1081 year-company. Data was analyzed by One-Way ANOVA and Decision Tree Algorithms. In this regard, research data test was done by using SPSS and Weka softwares. The research results showed that the best performances are respectively as what follows here: Random Forest, REPTree, J48, LMT, Decision Stump, and Random Tree. In addition, the One-Way ANOVA showed that differences in the efficiency of Decision Tree Algorithms are statistically significant. |
|
| Keywords: Tax Evasion Prediction, Decision Tree, Random Tree Algorithm, Random Forest Tree algorithm. |
|
|
Full-Text [PDF 781 kb]
(2819 Downloads)
|
|
Type of Study: Research |
Subject:
Special
|
|
|
|
|
|
|
| Send email to the article author |
|
|
|
| Add your comments about this article |
|
|
|
