Fotios Pasiouras

Assessing Bank Efficiency and Performance with Operational Research and Artificial Intelligence Techniques: A Survey

This paper presents a comprehensive review of 196 studies which employ operational research (O.R.) and artificial intelligence (A.I.) techniques in the assessment of bank performance. Several key issues in the literature are highlighted. The paper also points to a number of directions for future research. We first discuss numerous applications of data envelopment analysis which is the most widely applied O.R. technique in the field. Then we discuss applications of other techniques such as neural networks, support vector machines, and multicriteria decision aid that have also been used in recent years, in bank failure prediction studies and the assessment of bank creditworthiness and underperformance.

Regulations, Competition and Bank Risk-Taking in Transition Countries

This study investigates whether regulations have an independent effect on bank risk-taking or whether their effect is channeled through the market power possessed by banks. Given a well-established set of theoretical priors, the regulations considered are capital requirements, restrictions on bank activities and official supervisory power. We use data from the Central and Eastern European banking sectors over the period 1998-2005. The empirical results suggest that banks with market power tend to take on lower credit risk and have a lower probability of default. Capital requirements reduce risk in general, but for banks with market power this effect significantly weakens. Higher activity restrictions in combination with more market power reduce both credit risk and the risk of default, while official supervisory power has only a direct impact on bank risk.

Bank efficiency and share performance: Evidence from Greece

This article examines for the first time the association between the efficiency of Greek banks and their share price performance. Our analysis consists of three parts. First, we calculate the annual share price returns of the banks for each year between 2001 and 2005. Then we use data envelopment analysis to estimate the efficiency of the banks between 2000 and 2005. Finally, we regress the annual share price returns over the annual change of efficiency while controlling for changes in banks’ size and risk. We find that the average technical efficiency under constant returns to scale is 0.931 and increases to 0.977 under variable returns to scale, resulting in a scale efficiency of 0.953. The regression results indicate a positive and statistically significant relationship between annual changes in technical efficiency and stock returns, while changes in scale efficiency have no impact on stock returns.

The Effect of Board Size and Composition on the Efficiency of UK Banks

Abstract We examine a sample of 17 banking institutions operating in the UK between 2001 and 2006 to provide empirical evidence on the association between the efficiency of UK banks and board structure, namely board size and composition. Our approach is to use data envelopment analysis to estimate several measures of the efficiency of banks, and then to use panel data regressions for investigating the impact of board structure on efficiency. After controlling for bank size and capital strength, we find some evidence of a positive association between board size and efficiency, although this is not robust across all our specifications. Board composition, by contrast, has a robustly significant and positive impact on all measures of efficiency.

Probabilistic Neural Networks for the Identification of Qualified Audit Opinions

Prior studies that examine the application of neural networks in auditing investigate the efficiency of artificial neural networks (ANNs). In the present study, considering the well known disadvantages of artificial neural network, we propose the application of probabilistic neural networks (PNNs) that combine the computational power and flexibility of ANNs, while managing to retain simplicity and transparency. The sample consists of 264 financial statements that received a qualified audit opinion over the period 1997-2004 and 3069 unqualified ones, from 881 firms listed on the London Stock Exchange. The results demonstrate the high explanatory power of the PNN model in explaining qualifications in audit reports. The model is also found to outperform traditional ANN models, as well as logistic regression. Sensitivity analysis is used to assess the relative importance of the input variables and to analyze their role in the auditing process.

Multicriteria Decision Support Methodologies for Auditing Decisions: The Case of Qualified Audit Reports in the UK

All UK companies are required by company law to prepare financial statements that must comply with law and accounting standards. With the exception of very small companies, financial accounts must then be audited by UK registered auditors who must express an opinion on whether these statements are free from material misstatements, and have been prepared in accordance with legislation and relevant accounting standards (unqualified opinion) or not (qualified opinion). The objective of the present study is to explore the potentials of developing multicriteria decision aid models for reproducing, as accurately as possible, the auditors opinion on the financial statements of the firms. A sample of 625 company audited years with qualified statements and 625 ones with unqualified financial statements over the period 1998-2003 from 823 manufacturing private and public companies is being used in contrast to most of the previous works in the UK that have mainly focused on very small or very large public companies. Furthermore, the models are being developed and testing using the walk-forward approach as opposed to previous studies that employ simple holdout tests or resampling techniques. Discriminant analysis and logit analysis are also used for comparison purposes. The out-of-time and out-of-sample testing results indicate that the two multicriteria decision aid techniques achieve almost equal classification accuracies and are both more efficient than discriminant and logit analysis.

A Comparison of Nearest Neighbours, Discriminant and Logit Models for Auditing Decisions

This study investigates the efficiency of k-Nearest Neighbours (k-NN) in developing models for estimating auditors opinion, as opposed to models developed with discriminant and logit analyses. The sample consists of 5,276 financial statements, out of which 980 received a qualified audit opinion, obtained from 1,455 private and public UK companies operating in the manufacturing and trade sectors. We develop two industry-specific models and a general one using data from the period 1998-2001, which are then tested over the period 2002-2003. In each case, two versions of the models are developed. The first includes only financial variables. The second includes both financial and non-financial variables. The results indicate that the inclusion of credit rating in the models results in a considerable increase both in terms of goodness of fit and classification accuracies. The comparison of the methods reveals that the k-NN models can be more efficient, in terms of average classification accuracy, than the discriminant and logit models. Finally, the results are mixed as it concerns the development of industry-specific models as opposed to general ones.

Financial Characteristics of Banks Involved in Acquisitions: Evidence from Asia

This study examines the financial characteristics of 52 targets and 47 acquirers that were involved in acquisitions in the Asian commercial banking sector over the period 1998 to 2004 and a control sample of non-merged banks matched by country and year. Three logistic regression models are estimated to determine the factors that influence the probability of being involved in an acquisition either as a target or as an acquirer. The results indicate that more asset risky portfolios increase this probability. Higher liquidity also increases the probability of being acquired. The probability of being involved in an acquisition as acquirer also increases with size and cost efficiency. Finally, more profitable banks are more likely to be involved in acquisitions as acquirers rather than as targets. When we partition our sample in two sub-periods we find that only the higher loan loss provisions of targets and the higher size of acquirers remain robust over time.

Explaining Qualifications in Audit Reports Using a Support Vector Machine Methodology

The verification of whether the financial statements of a firm represent its actual position is of major importance for auditors, which should provide a qualified report if they conclude that the financial statements fail to meet this requirement. This paper implements support vector machines (SVM) to develop models that may support auditors in this task. Linear and non-linear models are developed and their performance is analyzed using training samples of different size and out-of-sample/out-of-time data. The results show that all SVM models are capable of distinguishing between qualified and unqualified financial statements with satisfactory accuracy. The performance of the models over time is also explored.

Multicriteria Classification Models for the Identification of Targets and Acquirers in the Asian Banking Sector

The purpose of the present study is the development of classification models for the identification of acquirers and targets in the Asian banking sector. We use a sample of 52 targets and 47 acquirers that were involved in acquisitions in 9 Asian banking markets during 1998-2004 and match them by country and time with an equal number of non-involved banks. The models are developed and validated through a tenfold cross-validation approach using two multicriteria decision aid techniques. For comparison purposes we also develop models through discriminant analysis. The results indicate that the multicriteria decision aid models are more efficient that the ones developed through discriminant analysis. Furthermore, in all the cases the models are more efficient in distinguishing between acquirers and non-involved banks than between targets and non-involved banks. Finally, the models with a binary outcome achieve higher accuracies than the ones which simultaneously distinguish between acquirers, targets and non-involved banks.