Data mining is a multi-disciplinary field of science and technology widely used in developing predictive models and data visualization in various domains. Although there are numerous data mining algorithms and techniques across multiple fields, it appears that there is no consensus on the suitability of a particular model, or the ways to address data preprocessing issues. Moreover, the effectiveness of data mining techniques depends on the evolving nature of data. In this study, we focus on the suitability and robustness of various data mining models for analyzing real financial data to identify financial restatements. From data mining perspective, it is quite interesting to study financial restatements for the following reasons: (i) the restatement data is highly imbalanced that requires adequate attention in model building, (ii) there are many financial and non-financial attributes that may affect financial restatement predictive models. This requires careful implementation of data mining techniques to develop parsimonious models, and (iii) the class imbalance issue becomes more complex in a dataset that includes both intentional and unintentional restatement instances. Most of the previous studies focus on fraudulent (or intentional) restatements and the literature has largely ignored unintentional restatements. Intentional (i.e. fraudulent) restatements instances are rare and likely to have more distinct features compared to non-restatement cases. However, unintentional cases are comparatively more prevalent and likely to have fewer distinct features that separate them from non-restatement cases. A dataset containing unintentional restatement cases is likely to have more class overlapping issues that may impact the effectiveness of predictive models. In this study, we developed predictive models based on all restatement cases (both intentional and unintentional restatements) using a real, comprehensive and novel dataset which includes 116 attributes and approximately 1,000 restatement and 19,517 non-restatement instances over a period of 2009 to 2014. To the best of our knowledge, no other study has developed predictive models for financial restatements using post-financial crisis events. In order to avoid redundant attributes, we use three feature selection techniques: Correlation based feature subset selection (CfsSubsetEval), Information gain attribute evaluation (InfoGainEval), Stepwise forward selection (FwSelect) and generate three datasets with reduced attributes. Our restatement dataset is highly skewed and highly biased towards non-restatement (majority) class. We applied various algorithms (e.g. random undersampling (RUS), Cluster based undersampling (CUS) (Sobhani et al., 2014), random oversampling (ROS), Synthetic minority oversampling technique (SMOTE) (Chawla et al., 2002), Adaptive synthetic sampling (ADASYN) (He et al., 2008), and Tomek links with SMOTE) to address class imbalance in the financial restatement dataset. We perform classification employing six different choices of classifiers, Decision three (DT), Artificial neural network (ANN), Naïve Bayes (NB), Random forest (RF), Bayesian belief network (BBN) and Support vector machine (SVM) using 10-fold cross validation and test the efficiency of various predictive models using minority class recall value, minority class F-measure and G-mean. We also experiment different ensemble methods (bagging and boosting) with the base classifiers and employ other meta-learning algorithms (stacking and cost-sensitive learning) to improve model performance. While applying cluster-based undersampling technique, we find that various classifiers (e.g. SVM, BBN) show a high success rate in terms of minority class recall value. For example, SVM classifier shows a minority recall value of 96% which is quite encouraging. However, the ability of these classifiers to detect majority class instances is dismal. We find that some variations of synthetic oversampling such as ‘Tomek Link + SMOTE’ and ‘ADASYN’ show promising results in terms of both minority recall value and G-mean. Using InfoGainEval feature selection method, RF classifier shows minority recall values of 92.6% for ‘Tomek Link + SMOTE’ and 88.9% for ‘ADASYN’ techniques, respectively. The corresponding G-mean values are 95.2% and 94.2% for these two oversampling techniques, which show that RF classifier is quite effective in predicting both minority and majority classes. We find further improvement in results for RF classifier with cost-sensitive learning algorithm using ‘Tomek Link + SMOTE’ oversampling technique. Subsequently, we develop some decision rules to detect restatement firms based on a subset of important attributes. To the best of our knowledge, only Kim et al. (2016) perform a data mining study using only pre-financial crisis restatement data. Kim et al. (2016) employed a matching sample based undersampling technique and used logistic regression, SVM and BBN classifiers to develop financial restatement predictive models. The study’s highest reported G-mean is 70%. Our results with clustering based undersampling are similar to the performance measures reported by Kim et al. (2016). However, our synthetic oversampling based results show a better predictive ability. The RF classifier shows a very high degree of predictive capability for minority class instances (97.4%) and a very high G-mean value (95.3%) with cost-sensitive learning. Yet, we recognize that Kim et al. (2016) use a different restatement dataset (with pre-crisis restatement cases) and hence a direct comparison of results may not be fully justified. Our study makes contributions to the data mining literature by (i) presenting predictive models for financial restatements with a comprehensive dataset, (ii) focussing on various datamining techniques and presenting a comparative analysis, and (iii) addressing class imbalance issue by identifying most effective technique. To the best of our knowledge, we used the most comprehensive dataset to develop our predictive models for identifying financial restatement.

In this study, I examine whether firms hire new CFOs with improved qualifications following a financial reporting failure and subsequently experiencing CFO turnover. Prior literature provides evidence that restating firms attempt to take remedial actions to restore their credibility and reputation. This study extends prior literature by testing whether the decision to hire a new CFO is a valued remedial action for restating firms. The empirical results show that restating firms are more likely to hire new CFOs with more accounting expertise and from external sources than non-restating firms are. The market reacts more favorably when restating firms hire a CFO with more relevant accounting expertise than the incumbent CFO. I also find that the improved qualifications of the new CFO mitigate the information risk generated by the restatement. This study contributes to the literature with the assertion that accounting expertise is a valuable attribute that firms consider when making hiring decisions for CFOs, especially those firms that issued a restatement. The results imply that replacing CFOs is a valued remedial action for restating firms. The improved qualifications of the new CFOs improve the information environment for restating firms and reduce perceived risk from investors.

Financial statement quality can directly affect investor confidence. Financial fraud is most through misstated financial reports, and even fraudulent misstatement may result from financial restatement. Well-functioning mechanisms can improve financial statement quality. In this study, the financial restatements from 2002 to 2008 were investigated to discuss the influences of operating performance, degree of earnings management and corporate governance mechanisms. The results reveal that the worse the operating performance, the more probability the financial restatements. It indicates that increasing earnings can cover up bad operation. It is further found that the financial restatements with worse operating performance will probably increase their restatement amounts. In the aspect of earnings management, the results show that the higher the degree of earnings management by discretionary accruals, the more probability the financial restatements. It is indicative of the manager use discretionary accruals to operate the earnings management in order to cover up their worse financial performance. But the verified result is not outstanding. It is also found that the financial restatements with higher degree of earnings management by discretionary accruals will probably increase their restatement amounts. Finally, the results can not prove whether the corporate governance mechanisms show that the financial restatements probably occur in the companies with CEO duality. Moreover, the results also can not prove whether the larger the board of directors, the higher their restatement amounts.

審計公費係影響審計品質之一大因素，且中國事務所家數眾多，更易產生低價攬客的惡性競爭行為，再者，中國上市公司重編狀況近來層出不窮，因此本文以2004-2008年中國大陸A股上市公司為研究對象，欲研究重編事件對中國企業審計公費之影響。財務報表重編事件可以分為三個時間點：財務報表錯誤年度、財務報表執行重編年度以及重編後的次一年度。就財務報表發生錯誤年度而言，本研究發現該事件會伴隨較高的審計公費，但是無論是執行重編年度或次一年度，均未發現顯著提高公費的證據。除此之外，本研究也未能獲得審計委員會之設立與審計公費有統計關聯性的證據。具體而言，除了傳統審計公費的解釋變數之外，本文未能發現財務報表重編及審計委員會與審計公費有關之證據。 / Audit fees is one of the major factors affecting quality, and there are many audit firms in China, so it is easier to produce vicious competition . Furthermore, the number of Chinese listed company which has restated financial report is increasing in recent years. So, with a sample of A-share listed corporations in China from 2004 to 2008 , this dissertation develops a conceptual model for studying the relationship between financial restatement and audit fees. Financial restatement can be divided into three time points: the year when an error occurred in the financial report , the year when the financial report is restated ,and the year after the financial report is restated .In terms of the year when an error occurred in the financial report , this dissertation find the event associated with higher audit fees ,but in other two time point , this dissertation doesn’ t find the evidence of significantly increased audit fees. Moreover ,there is no statistical significant relationship between setting up an audit committee and audit fees. Specifically, in addition to the traditional explanatory variables, this dissertation can’t find the evidence that financial restatement and setting up an audit committee are related to audit fees.

本研究以財務長與審計委員會相對任期作為財務長與審計委員會相對影響力之指標，探討財務長與審計委員會相對影響力對財務報表重編之影響。利用2007至2014年間中國滬深A股為樣本，本研究發現，財務長之任期較審計委員會長時，財務報表越有可能重編，顯示財務長相對於審計委員會影響力較大時，會降低財務報表品質。本研究亦發現，前述情況並不因為客戶重要性較高而更加明顯，顯示財務長與審計委員會相對影響力與財務報表重編之關係，不會受到客戶重要性的影響。 / This thesis uses the relative tenures of CFO and audit committee as an indicator of the relative power between CFO and audit committee, and examines the relation between the relative power of CFO versus audit committee and the probability of financial restatement. Based on a sample of A-share stocks listed in Shanghai and Shenzhen during 2007-2014, the empirical result shows that when CFO has relative higher tenure than audit committee, the incidence of financial restatement increases. This result suggests that CFO who has more power than audit committee tends to compromise the quality of financial statement, at least in terms of financial restatement. The empirical result also shows that the effect of the relative power of CFO and audit committee does not vary among clients’ importance.

本研究以台灣上市櫃公司及分析師投資報告為研究對象，探討會計師忙碌程度與審計品質之關聯性，以及產生學習或互斥效果。審計品質以裁決性應計項目、財務報表重編及迎合或擊敗分析師預期三種特性進行分析。 研究結果發現，會計師忙碌程度與裁決性應計項目、財務報表重編及迎合或擊敗分析師預期皆呈現顯著負相關。此結果表示，會計師忙碌程度愈高，受查公司管理當局進行盈餘管理之可能性愈低。本研究藉此結果推論，會計師忙碌程度愈高，透過累積查核經驗，促進知識改善，產生正向的學習效果，進而提高審計品質。 / This thesis examines the association between the busyness of auditors at partner level and audit quality and whether the association stems from learning effect or crowding-out effect, by using the listed firms’ data and the analysts’ reports in Taiwan. I use the following three measures of audit quality to examine my hypotheses: discretionary accruals, financial restatement, and meet or beat analyst forecast. The empirical results indicate that firms experience lower discretionary accruals, are less likely to restate financial statements and have lower likelihood of meeting or beating analysts’ expectations when auditors are busier. The results are consistent with the notion that auditor busyness is positively related to audit quality. Taken together, the findings provide strong evidence in favor for learning effect rather than crowding-out effect of auditor busyness. Further analyses reveal that the results remain unchanged, regardless of lead auditor busyness or concurring auditor busyness.