000 | 01941nam a2200205 4500 | ||
---|---|---|---|
999 |
_c383052 _d383052 |
||
003 | APU | ||
005 | 20200312010353.0 | ||
008 | 200311b2019 xxu||||| |||| 00| 0 eng d | ||
050 | _aPG-24-0110 | ||
100 | 0 |
_aWONG YUN SENG (TP038263) _945620 |
|
245 | 1 | 4 |
_aTHE APPLICATION OF THE ARTIFICIAL NEURAL NETWORK (ANN) MODEL AS A FINANCIAL STATEMENT FRAUD (FSF) PREDITOR / _cWONG YUN SENG. |
260 |
_aKuala Lumpur : _bAsia Pacific University, _c2019. |
||
300 |
_a78 pages : _billustrations ; _c30 cm. |
||
502 | _aA project submitted in partial fulfillment of the requirements of Asia Pacific University of Technology and Innovation for the degree of BSc (Hons) in Accounting and Finance with specialism in Forensic Accounting (UC3F1810AF(FA)). | ||
520 | _aThis study applies the Artificial Neural Network (ANN) to predict Financial Statement Fraud (FSF). FSF is a type of fraudulent activity, it involves the misinterpretation of the financial statements intentionally. Financial statements that conceal the company's true financial situation causes a huge loss to market participants, including creditors, employees, shareholders, and investors. Previous research has found that ANN is one of the efficient ways to predict FSF. This study will introduce the technological and methodological characteristics of ANN model using the Multilayer Feed Forward Neural Network (MLF) model to predict FSF. The MLF was adapted to enable pattern recognition, function fitting, pattern approximation, classification and to overcome prediction problems. This research had focused on fifty fraudulent firms and five-year time series to predict FSF in Malaysia. The findings of this research show that the ANN model is able to predict FSF accurately at 84.2%. | ||
650 | 0 |
_aFraud _xPrevention. _945612 |
|
650 | 0 |
_aNeural networks (Computer science) _945621 |
|
700 | 0 |
_aMs. Geetha Rubasundram _eSupervisor. _945623 |
|
942 |
_2lcc _cUndergraduate Theses |