Machine Learning Techniques and Risk Management

Crises around the world reveal a generally unstable environment in the last decades within which banks and financial institutions operate. Risk is an inherent characteristic of financial institutions and is a multifaceted phenomenon. Everyday business practice involves decisions, which requires the use of information regarding various types of threats involved together with an evaluation of their impact on future performance, concluding to combinations of types of risks and projected returns for decision makers to choose from. Moreover, financial institutions process a massive amount of data, collected either internally or externally, in an effort to continuously analyse trends of the economy they operate in and decode global economic conditions. Even though research has been performed in the field of accounting and finance, the authors explore the application of machine learning techniques to facilitate decision making by top management of contemporary financial institutions improving the quality of their accounting disclosure.

Outsourcing of Internal Audit Services Instead of Traditional Internal Audit Units

The internal audit function traditionally establishes and continues its activities within the company, but it can also be provided by professionals outside the organization. Therefore, internal audit activities can be provided in three ways: the internal audit department established within the organization (in-house), the internal audit service provided by an audit firm (outsourcing), the joint operation of the internal audit department and the audit firm (co-sourcing). To choose the better approach for a company, the scale of the organization, the attitude and understanding of the management, and industry in which the company operates in must be taken into consideration. This study is a literature review that classifies the studies carried out on these methods that are used in performing internal audit activities.

Theoretical Analysis of Creative Accounting

This chapter begins with the definitions of creative accounting, fraud and financial statement fraud and explains the relationship between them. Next, it presents the classical theories on the determinants of financial statement fraud. Section 1.4 presents the profile of accounting scandals. Section 1.5 presents the components of financial report fraud as well as the parties involved in in creative accounting. Section 1.6 presents the reasons and motivations for creative accounting. Specifically, the authors analyse manipulation practices, the methods and the opportunities for creative accounting and address why financial frauds occur. Finally, they offer conclusions in Section 1.7.

Detection and Prevention of Fraud in the Digital Era

It is essential for businesses to keep up with the technological advances. Today nearly all the businesses depend on computer technologies and the Internet to operate as technological developments have introduced many practical methods for businesses. Yet, transformation of businesses technologically also presents new means for the criminals, which has led to new types of fraud. It is crucial for businesses to take measures to prevent fraud. Traditional methods to prevent or to detect fraud seems to be ineffective for new types of fraud in the digital era. Therefore, new methods have been used to prevent and detect fraud. This chapter reviews fraud as a form of cybercrime in the digital era and aims to introduce the methods that have been used to detect and prevent it.

Downside Risk Premium

The purpose of this chapter is to address the main developments and challenges on risk assessment and portfolio management. The former innovation in modern portfolio theory, Markowitz, has been succeeded from linear and non-linear optimization techniques that improve portfolio efficiency. Special emphasis is given on Roy's seminal work on “Safety First Criterion” which advocates that the safety of investments should be prioritized. Thus, an investment should be chosen in a way that it has the lowest probability of falling short of a required threshold of investors. This motivated Markowitz to advocate a downside risk measure based on semivariance. It captures the notion of risk as failure to meet some minimum target. It is influenced by returns below the target rate. It focuses on investors' concern with downside variability and loss reduction. This chapter offers a critical reflection of these recent developments and could be of interest for individual and institutional investors.

Current Trends in Investment Analysis

The purpose of this chapter is to review the current trends in investment management and performance research. The adaption of both the classic CAPM and the factor models seems to continue, with the realistic factors playing a crucial role and best represent the drivers of investment performance. Another rising area is the search for skill, which is based on the enhanced benchmarks. The availability of quantitative and qualitative data in the academic community has allowed for these areas to evolve in recent years and to emerge as expected in the next decade, as well as to be explored.

Impact of Corporate Fraud on Foreign Direct Investment?

The capital market reputation attracts foreign investment. Corporate fraud phenomenon is one of the most crucial aspects that threaten foreign investors. This study investigates the impact of corporate fraud on foreign direct investment FDI. Using data of Chinese listed firms, over the period 2009 to 2017, the results show that corporate fraud is negatively associated with foreign direct investment. This suggests that corporate fraud declines foreign shareholders ratio, and foreign investors avoid investing in a risky environment where their wealth may be expropriated. Further, we explore the impact of having foreign shareholders on corporate fraud. We find that increasing foreign shareholders may help in curbing corporate fraud due to diversified corporate experience and risk-taking behavior. However, the findings remain robust after controlling for the potential endogeneity problem. Our findings have important implications for policymakers and governments as it shows that corporate fraud is a crucial determinant to the cause of foreign direct investment.

Corporate Governance as a Tool for Fraud Mitigation

Financial fraud through the falsification of financial statements is an evident problem. The restatement is enormous, and there have been developed many approaches to confront it. Profits manipulation has reached alarming proportions worldwide. The tendency of management to present a misleading image based on accounting weaknesses and gaps, to present accounting results as it wishes and not as it should according to the accounting standards, is essentially a key feature of profit manipulation. The executives' motives to falsify financial results and creative accounting practices have concerned researchers and their efforts to identify the necessary changes and improvements in accounting systems to protect the stakeholders and the public from misleading information.

Prediction of Corporate Failures for Small and Medium-Sized Enterprises in Europe

The risk of bankruptcy is naturally faced by all corporate organizations, and there are various factors that may lead an organization to bankruptcy, including microeconomic and macroeconomic ones. Many researchers have studied the prediction of business bankruptcy risk in recent decades. However, the research on better tools continues to evolve, utilizing new methodologies from various scientific fields of management science and computer science. This chapter deals with the development of statistical and artificial intelligence methodologies for predicting failures for small and medium-sized enterprises, considering financial and macroeconomic data. Empirical results are presented for a large sample of European firms.

Application of Adaptive Neurofuzzy Control in the Field of Credit Insurance

Credit insurance is of vital importance for the trade sector and almost every related business. Moreover, every policy in credit insurance is tailor-made in order to suit in the best available way the unique needs and demands of the insured business. Thus, pricing of such service can be tricky for an insurance company. In the present chapter, this pricing problem in the field of credit insurance will be addressed through the use of intelligent control mechanisms. More specifically, a way of calculating the price of insurance policies that has to be paid by a prospective client of an insurance company will be suggested. The model will be created and implemented with the use of fuzzy logic, and more specifically, through the implementation of an adaptive neurofuzzy inference system. The training data that will be used for the tuning of the system will be derived from real anonymous insurance policies of the Greek insurance market.