Publications
Detailed Information
Building Financial Misstatement Detection Models using Multi-class Cost-sensitive Learning and Feature Generation from CFO survey
DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 조성준 | - |
dc.contributor.author | Kim, Yeonkook | - |
dc.date.accessioned | 2017-07-13T08:57:25Z | - |
dc.date.available | 2017-07-13T08:57:25Z | - |
dc.date.issued | 2016-08 | - |
dc.identifier.other | 000000136238 | - |
dc.identifier.uri | https://hdl.handle.net/10371/119971 | - |
dc.description | 학위논문 (박사)-- 서울대학교 대학원 : 기술경영·경제·정책전공, 2016. 8. 조성준. | - |
dc.description.abstract | Material misstatements are such omissions and misstatements of financial information included in the financial statements that can affect the economic decisions of the users of financial statements. When building material misstatement detection or prediction models, researchers should consider two important issues: first, financial misstatements can be classified as involving either errors (i.e., unintentional misapplications of accounting rules) or irregularities (i.e., intentional misreporting). Second, there is selection bias in target variables. Many firms that manipulate earnings are likely to go unidentified and there could be selection biases in cases pursued by financial authorities.
I develop financial misstatement detection models using machine learning and statistical models addressing the two issues present in target variables. First, to address the issue of fraud intention in the target variable, I develop multi-class financial misstatement detection models to detect misstatements by fraud intention. Hennes, Leone and Miller (2008) performed post-event analysis on financial restatements and classified restatements by fraud intention (i.e. intentional vs. unintentional misstatements). Using their result (along with non-misstated firms) as a three-class target variable, I develop three multi-class classifiers, multinomial logistic regression, support vector machine, and Bayesian networks as predictive tools to detect and classify misstatements by fraud intention. To deal with class imbalance and asymmetric misclassification costs, I perform cost-sensitive learning using MetaCost. Second, one way to reduce the effect of selection bias in the target variable is to perform domain expert guided feature selection. I propose to utilize the earnings management survey to public company CFOs by Dichev et al. (2016) for feature selection and feature generation. To detect material misstatements, I create features using the survey result and build binary detection models. I compare the performance of the new models with the existing scoring models from accounting and finance literature. | - |
dc.description.tableofcontents | Chapter 1 Introduction 1
Chapter 2 Literature Review 6 2.1 Fraud detection 6 2.2 Classification of material misstatements according to fraudulent intention (post-event studies) 7 2.3 Binary Prediction/Detection models 11 Chapter 3 Detecting financial misstatements by fraud intention using multi-class cost-sensitive learning 16 3.1 Research Methodology 19 3.2 Variables 20 3.3 Methods 26 3.3.1 Multinomial logistic regression (MLogit) 27 3.3.2 Support Vector Machines (SVM) 28 3.3.3 Bayesian Networks (BayesNet) 29 3.3.4 Cost-sensitive learning 31 3.4 Results 34 3.4.1 Feature importance 34 3.4.2 Classification result 37 Chapter 4 Building financial misstatement detection models using features generated from CFO survey contents 43 4.1 Research Methodology 47 4.1.1 Feature generation 47 4.1.2 Data 48 4.2 Research Methodology 51 4.2.1 Models 51 4.2.2 Prediction Accuracy 55 4.2.3 Equity return predictability 55 Chapter 5 Conclusion 58 Bibliography 63 국문 초록 70 | - |
dc.format | application/pdf | - |
dc.format.extent | 2194541 bytes | - |
dc.format.medium | application/pdf | - |
dc.language.iso | en | - |
dc.publisher | 서울대학교 대학원 | - |
dc.subject | Financial misstatement detection | - |
dc.subject | Fraud intention | - |
dc.subject | Multi-class cost sensitive learning | - |
dc.subject | CFO survey | - |
dc.subject | Earnings Management | - |
dc.subject.ddc | 658 | - |
dc.title | Building Financial Misstatement Detection Models using Multi-class Cost-sensitive Learning and Feature Generation from CFO survey | - |
dc.type | Thesis | - |
dc.description.degree | Doctor | - |
dc.citation.pages | 71 | - |
dc.contributor.affiliation | 공과대학 협동과정 기술경영·경제·정책전공 | - |
dc.date.awarded | 2016-08 | - |
- Appears in Collections:
- Files in This Item:
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.