Research on the Detection of Financial Fraud Using Data Mining Techniques

DOI

10.2991/icadme-17.2017.90How to use a DOI?

Keywords

Financial information fraud detection; Data mining; Ada Boost method; Rattle package

Abstract

Financial information plays a crucial role for future investors to make important decisions, and how to provide true, reliable and accurate financial information becomes a top mission for enterprises. To effectively identify financial fraud information, we first select the relative indicators by reviewing the financial information of previous studies, and the indicators related to false information are prepared for data modeling using data mining tool. Furthermore, we analyze these relative indicators through the rattle package in the R and Ada Boost method. The results we obtained demonstrate that a company's solvency is the primary factor in determining whether a company has financial information fraud. Meanwhile, key factors like profitability, operating capacity, accounts receivable turnover days, business debt ratio, and financial debt ratio are useful when detecting financial information fraud.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Yanling Li
AU  - Nan Li
AU  - Mingpei Yang
PY  - 2017/07
DA  - 2017/07
TI  - Research on the Detection of Financial Fraud Using Data Mining Techniques
BT  - Proceedings of the 2017 7th International Conference on Advanced Design and Manufacturing Engineering (ICADME 2017)
PB  - Atlantis Press
SP  - 473
EP  - 481
SN  - 2352-5401
UR  - https://doi.org/10.2991/icadme-17.2017.90
DO  - 10.2991/icadme-17.2017.90
ID  - Li2017/07
ER  -