Construction of Financial Statements Fraud Deiection Models
| Autor: | CHEN, NIEN-I, 陳念頤 |
|---|---|
| Rok vydání: | 2018 |
| Druh dokumentu: | 學位論文 ; thesis |
| Popis: | 106 In addition to the damage to the company itself, financial statements fraud has also caused huge losses for many investors. In recent years, many researchers use data mining methods on the research of financial statements fraud to improve the detection accuracy. The research subjects are 27 of financial statement fraud companies and 81 non-financial statements fraud companies from 2009 to 2016 with financial and non-financial variables. In the first stage of this study, artificial neural network (ANN) and support vector machines (SVM) are used to screen the important variables. In the second stage, decision tree C5.0 and support vector machine (SVM) are used to build the prediction models. The results of this study show that the SVM-C5.0 model has the best detection accuracy of 82.87%. |
| Databáze: | Networked Digital Library of Theses & Dissertations |
| Externí odkaz: |
|