| dc.contributor | 國立政治大學資訊管理學系 | en_US |
| dc.contributor | 行政院國家科學委員會 | en_US |
| dc.creator (作者) | 蔡瑞煌;林宛瑩 | zh_TW |
| dc.date (日期) | 2009 | en_US |
| dc.date.accessioned | 30-Aug-2012 15:51:18 (UTC+8) | - |
| dc.date.available | 30-Aug-2012 15:51:18 (UTC+8) | - |
| dc.date.issued (上傳時間) | 30-Aug-2012 15:51:18 (UTC+8) | - |
| dc.identifier.uri (URI) | http://nccur.lib.nccu.edu.tw/handle/140.119/53511 | - |
| dc.description.abstract (摘要) | 財務報表舞弊不僅對股東造成顯著的投資危機，也掀起資本市場的財務風暴。雖然財務報表的舞弊已經引起許多關注，但大部分相關研究者著重在預測財務危機和破產，而鮮少聚焦在對財報舞弊本身知識的探討。本研究旨在透過以下四個階段而對財報舞弊有更深的了解。 (1) 從文獻中整理出財務和公司治理方面和財報舞弊相關的所有指標，然後用統計分析方法採擷、獲得和財報舞弊顯著相關的指標; (2) 利用Growing Hierarchical Self-Organizing Map (GHSOM)之人工智慧分群方法來對正常及舞弊的財報資料分群; (3) 剖析分群的財報資料以及利用專家之研判，以擷取財報舞弊的相關知識; (4) 再利用專家來研判所採擷的財報舞弊的相關知識之可信度。 因為人工智慧分群方法可以從龐大的資料中找尋隱藏的階層關聯；所以學理上，這項研究是可行的。 在第一年，這項研究計畫將著重於財務和公司治理方面和財報舞弊相關的所有指標之文獻整理，然後利用統計分析方法採擷、獲得和財報舞弊相關的顯著指標；並且利用GHSOM分群方法來對正常及舞弊的財報資料分群。在第二年，研究計畫將剖析GHSOM分群的財報資料以及利用專家之研判，以擷取財報舞弊的相關知識，並且再利用專家來研判所採擷的財報舞弊的相關知識之可信度。 | - |
| dc.description.abstract (摘要) | Fraudulent financial reporting (FFR) has drawn much public as well as academic attention. However,most literature focuses on predicting the likelihood of financial fraud, financial distress or bankruptcy. Less emphasis has been placed on exploring FFR itself, and FFR techniques and knowledge. The purpose of this research is to explore FFR via Growing Hierarchical Self-Organizing Map (GHSOM), an unsupervised Neural Network tool, to enhance the understanding of FFR. This study addresses the challenge through the following two-stage approach: a classification stage that well trains the GHSOM to cluster the sample into subgroups with hierarchical relationship and a pattern-disclosure stage that uncovers patterns of the common financial reporting fraud techniques and relevant risk indicators to enhance the understanding of FFR. An application is conducted and its results show that the proposed two-stage approach is helpful in enhancing the understanding of FFR. | - |
| dc.language.iso | en_US | - |
| dc.relation (關聯) | 應用研究 | en_US |
| dc.relation (關聯) | 學術補助 | en_US |
| dc.relation (關聯) | 研究期間:9808~ 9907 | en_US |
| dc.relation (關聯) | 研究經費:629仟元 | en_US |
| dc.subject (關鍵詞) | 財務報表 | en_US |
| dc.title (題名) | 財務報表舞弊探索與類神經網路(I) | zh_TW |
| dc.title.alternative (其他題名) | Financial Reporting Fraud and Neural Networks | en_US |
| dc.type (資料類型) | report | en |
