For financial institutions, the ability to predict or forecast business failures is crucial, as incorrect decisions can have direct financial consequences. Bankruptcy prediction and credit scoring are the two major research problems in the accounting and finance domain. In the literature, a number of models have been developed to predict whether borrowers are in danger of bankruptcy and whether they should be considered a good or bad credit risk. Since the 1990s, machine-learning techniques, such as neural networks and decision trees, have been studied extensively as tools for bankruptcy prediction and credit score modeling. This paper reviews 130 related journal papers from the period between 1995 and 2010, focusing on the development of state-of-the-art machine-learning techniques, including hybrid and ensemble classifiers. Related studies are compared in terms of classifier design, datasets, baselines, and other experimental factors. This paper presents the current achievements and limitations associated with the development of bankruptcy-prediction and credit-scoring models employing machine learning. We also provide suggestions for future research.

Machine Learning in Financial Crisis Prediction: A Survey

Developing an early warning system to predict currency crises

We review the contemporary theory of financial intermediation. The focus is on contributions in the past 15 years or so that have advanced our understanding of why financial intermediaries exist, the credit allocation and other services they provide in spot and forward credit markets, the contractual nature and allocational consequences of the claims they issue, and the optimal design of bank regulation. Journal of Economic Literature Classification Numbers: 310, 312, and 314.

Contemporary Banking Theory

The share of gross domestic product from the service industry reflects the competitiveness of a nation; the service industry in the USA accounts for around 80% of its gross domestic product, and it has been increasing gradually. Continual innovations and advances in enabling technologies for the service industry are crucial for developed countries to sustain their leading positions in the globalized economy. To clarify future research directions of operations research (OR) in the service industry, the state of art of OR has been examined systematically, the new requirements of OR are identified for its applications in service industries in comparison with those in manufacturing industries, and the limitations of existing methodologies and tools have been discussed. This paper was intended to provide an updated review on how OR has been applied in the service sector in recent years and what directions the study of OR will be carried forward in the near future. Under a proposed research framework, recent OR-related articles were collected from 17 leading OR journals and classified into the five most active sectors, that is, transportation and warehousing, information and communication, human health and social assistance, retails and wholesales, and financial and insurance services. The conclusions on the limitations of existing studies and the demanding ORs in the service have been drawn from our summaries and observations from a comprehensive review in this field. Copyright © 2013 John Wiley & Sons, Ltd.

Operations Research (OR) in Service Industries: A Comprehensive Review

risk. The book is organized into five sections. The first section applies multivariate data and multicriteri a analyses to the problem of portfolio selection. Articles in thi s section combine classical approaches with newer methods. The second section expands the analysis in the firs t section to a variety of financial problems: busin ess failure, corporate performance and viability, bankruptcy, et c. The third section examines the mathematical prog ramming techniques including linear, dynamic, and stochasti c programming to portfolio management's. The fourth section introduces fuzzy set and artificial intelligence te chniques to selected types of financial decisions. The final section explores the contribution of several multic riteria methodologies in the assessment of country financial risk. In total, this book is a systematic examinati on of an emerging methodology for managing financial risk in business.

/pdf/operational-tools-in-the-management-of-financial-risks-4l1urjxsh1.pdf

Operational Tools in the Management of Financial Risks presents an array of new tools drawn from a var iety of research areas, including chaos theory, expert syst ems, fuzzy sets, neural nets, risk analysis, stocha stic programming and multicriteria decision making. Applications cover, but are not limited to, bankruptcy, credit granting, capital budgeting, corporate performance and viability, portfolio selection/management, and country

Rough sets and the role of the monetary policy in financial stability (macroeconomic problem) and the prediction of insolvency in insurance sector (microeconomic problem)

In this paper we try to evaluate the asymptotic fairness of bonus-malus systems, assuming the simplest case when there is no hunger for bonus. The asymptotic fairness has to be understood as the bonus-malus system ability in assessing the individual risks in the long run. Firstly we define the asymptotic fairness of a bonus-malus system following an expression that can be found in J. Lemaire [1985]: Automobile Insurance. Actuarial Models. Dordrecht: Kluwer-Nijhoff Publishing, p. 168. Secondly, we define a measure of the global asymptotic fairness considering the structure function of the risk group. Finally we try to calculate, for each set of transition rules and a given structure function, the scale of premiums that brings the global asymptotic fairness closest to the ideal situation where each insured pays in the long run a premium corresponding to its own claim frequency. This is possible thanks to the application of a multiobjective optimization technique named Goal Programming.

/pdf/asymptotic-fairness-of-bonus-malus-systems-and-optimal-1pmdu2zzki.pdf

Asymptotic Fairness of Bonus-Malus Systems and Optimal Scales of Premiums

Linear goal programming can be used as a complementary technique when local moment matching method up to the second moment gives some negative mass. This could happen when manipulating a discrete or mixed type severity distribution. In that case we can avoid a simple retreat to the first moment and look for an arithmetic distribution with equal mean and the second moment closest to that of the original distribution.

Arithmetization of distributions and linear goal programming

In this paper we calculate premiums which are based on the minimization of the Expected Tail Loss or Conditional Tail Expectation (CTE) of absolute loss functions. The methodology generalizes well known premium calculation procedures and gives sensible results in practical applications. The choice of the absolute loss becomes advisable in this context since its CTE is easy to calculate and to understand in intuitive terms. The methodology also can be applied to the calculation of the VaR and CTE of the loss associated with a given premium.

Conditional Tail Expectation and Premium Calculation

The purpose of this paper is to show how linear programming methodology can help us to design Bonus-Malus premium scales with some interesting theoretical and practical attributes. Examples of these properties are the financial equilibrium of the system, the monotonicity and proper variability of the premium scale, and the improvement of some efficiency measures such as the RSAL and the elasticity of the system. We will conclude that the use of the linear programming methodology makes possible a high degree of interaction between the designer and the mathematical model.

/pdf/an-application-of-linear-programming-to-bonus-malus-system-2xasrnjywm.pdf

José L. Vilar

Papers

Rough sets and the role of the monetary policy in financial stability (macroeconomic problem) and the prediction of insolvency in insurance sector (microeconomic problem)

Asymptotic Fairness of Bonus-Malus Systems and Optimal Scales of Premiums

Arithmetization of distributions and linear goal programming

Conditional Tail Expectation and Premium Calculation

An Application of Linear Programming to Bonus Malus System Design