Marleen Willekens

Bayesian kernel based classification for financial distress detection

Corporate credit granting is a key commercial activity of financial institutions nowadays. A critical first step in the credit granting process usually involves a careful financial analysis of the creditworthiness of the potential client. Wrong decisions result either in foregoing valuable clients or, more severely, in substantial capital losses if the client subsequently defaults. It is thus of crucial importance to develop models that estimate the probability of corporate bankruptcy with a high degree of accuracy. Many studies focused on the use of financial ratios in linear statistical models, such as linear discriminant analysis and logistic regression. However, the obtained error rates are often high. In this paper, Least Squares Support Vector Machine (LS-SVM) classifiers, also known as kernel Fisher discriminant analysis, are applied within the Bayesian evidence framework in order to automatically infer and analyze the creditworthiness of potential corporate clients. The inferred posterior class probabilities of bankruptcy are then used to analyze the sensitivity of the classifier output with respect to the given inputs and to assist in the credit assignment decision making process. The suggested nonlinear kernel based classifiers yield better performances than linear discriminant analysis and logistic regression when applied to a real-life data set concerning commercial credit granting to mid-cap Belgian and Dutch firms.

Attribute differences between U.S. GAAP and IFRS earnings: An exploratory study

With the successful completion of the IASCs standards, IFRS and US GAAP were placed as the two pre-eminent world financial reporting frameworks. For years, however, US GAAP was accepted widely as the international set of standards to ensure high quality financial statements. Especially in the US, but also elsewhere, the introduction of IFRS has lead to a discussion on the (relative) quality of both regimes. However, relatively little research has been devoted to the subject. In this study, we address that void and further compare the quality of the two standard regimes using a sample of German New Market firms. Financial statement quality is measured applying multiple earnings attributes traditionally used in accounting research. Consistently throughout our measures, we find that the quality of US GAAP prepared financial statements and IFRS information is overall very comparable. Only with regard to predictive ability of accounting information do we find US GAAP superiority.

Evidence on (the lack of) Audit-Quality Differentiation in the Private Client Segment of the Belgian Audit Market

This paper contributes to the empirical audit-quality literature and provides evidence on (the lack of) audit-quality differentiation in the private client segment of the Belgian audit market. Auditor size is used as audit-quality proxy. Prior evidence on audit-quality differentiation between Big Six and non-Big Six auditors in the private client segment of the Belgian audit market is mixed. In this paper we investigate whether these mixed results stem from the inability of the dichotomous Big Six/non-Big Six variable to capture auditor-size differences in a less concentrated audit market. To that end we examine whether alternative continuous measures of audit-firm size (i.e. auditor market share, number of audit-firm clients, number of partners in the audit firm, total assets and operating profit of the audit firm) have a constraining impact on earnings management in a large sample of privately held Belgian companies (n = 1,302). Overall, we do not find evidence that is supportive of quality differentiation in the private client segment of the Belgian audit market.

Disclosure on Corporate Governance in the European Union

Manuscript Type: Empirical Research Question/Issue: In this paper, we examine the determinants of the level of disclosure on corporate governance practices among European listed companies in the time period preceding the adoption of the European Union recommendations and Action Plan. Research Findings/Results: Using ratings on corporate governance disclosure issued by an independent rating agency we find that – ceteris paribus – the level of disclosure: (1) is lower for companies with higher ownership concentration; (2) is higher for companies from common-law countries; and (3) increases with the level of working capital accruals. Theoretical Implications: The results of the study support theoretical arguments that companies disclose corporate governance information in order to reduce information asymmetry and agency costs stemming from the separation between ownership and control, and to improve investor confidence in the reported accounting information. The study suggests various avenues for future research on corporate governance. Practical Implications: To policy makers and practitioners, the results suggest that a mandatory corporate governance disclosure requirement is abundant, and perhaps could even be inefficient. The results also indicate which types of companies can be expected to be least willing to comply with recent corporate governance disclosure requirements, and thus will need extra monitoring.

Predicting going concern opinion with data mining

The auditor is required to evaluate whether substantial doubt exists about the client entitys ability to continue as a going concern. Accounting debacles in recent years have shown the importance of proper and thorough audit analysis. Since the 80s, many studies have applied statistical techniques, mainly logistic regression, as an automated tool to guide the going concern opinion formulation. In this paper, we introduce more advanced data mining techniques, such as support vector machines and rule-based classifiers, and empirically investigate the ongoing discussion concerning the sampling methodology. To provide specific audit guidelines, we infer rules with the state-of-the-art classification technique AntMiner+, which are subsequently converted into a decision table allowing for truly easy and user-friendly consultation in every day audit business practices.

Auditing, Trust and Governance. Developing regulation in Europe

Auditing, Trust andGovernancewas published under the auspices of the European Auditing Research Network (EARNet). EARNet was formed in 2000 to ‘foster research and exchange ideas among auditing scholars and researchers at a European level’. This book represents a milestone towards accomplishing this objective. Motivation for the book evolved from the major corporate failures in the USA (e.g. Enron and Worldcom) and Europe (e.g. Ahold and Parmalat), and the resulting loss of trust and confidence in financial reporting and the auditing profession. The response by regulators to these events was the passage of the Sarbanes– Oxley Act in the USA and the revised Eighth Directive on Statutory Audit in the European Union. Auditing, Trust and Governance provides a detailed account of how a number of European countries responded to this crisis in confidence. The book contains 13 chapters written by leading auditing scholars. The first chapter sets up the book by presenting a general discussion of the main issues of trust, audit quality, regulation and corporate governance. This chapter was particularly helpful to me in understanding the extent of research on audit quality in Europe. The authors conclude ‘the evidence on audit quality differentiation in Europe is mixed and highly country specific’ (p. 8). The chapter provides a number of areas for future research studies in Europe on audit quality. The next 11 chapters are written from the perspective of each of the following countries:

Strategic pricing by Big 4 audit firms in private client segments

We examine how Big 4 auditors compete for new private clients. We find evidence suggesting that Big 4 auditors offer fee discounts to attract non‐Big 4 private clients to experience attributes of their brand name audit services. We also find that to attract clients from competing Big 4 suppliers, Big 4 auditors target fee discounts at clients in industries where they are the market leader. Our results further indicate that the Big 4 industry leaders target fee discounts to fast‐growing clients and are able to charge these clients significant price fee increases in the second mandate period (after 3 years).

The Influence of Specific Accounting Differences on the Choice Between IFRS or US GAAP

Due to the increased competition on capital markets and given the global importance of US markets, IFRS and US GAAP are competing to become the world standards set. Although comparable in many aspects, IFRS and US GAAP still differ in accounting for some transactions. This paper addresses the question whether specific accounting differences between IFRS and US GAAP determine the individual firms accounting standard preference. The results show that firms prefer that accounting regime that offers them the largest flexibility (i.e. less disclosure or more measurement options) on relevant accounting items (e.g. R&D expenditures). Furthermore, the flexibility in measurement seems to result in accounting numbers that are significantly valued by investors.