A preference disaggregation decision support system for financial classification problems

Classification is one of the most extensively studied problems in the fields of multivariate statistical analysis, operations research and artificial intelligence. Decisions involving a classification of the alternative solutions are of major interest in finance, since several financial decision problems are best studied by classifying a set of alternative solutions (firms, loan applications, investment projects, etc.) in predefined classes. This paper proposes an alternative approach to the classical statistical methodologies that have been extensively used for the study of financial classification problems. The proposed methodology combines the preference disaggregation approach (a multicriteria decision aid method) with decision support systems. More specifically, the FINancial CLASsification (FINCLAS) multicriteria decision support system is presented. The system incorporates a plethora of financial modeling tools, along with powerful preference disaggregation methods that lead to the development of additive utility models for the classification of the considered alternatives into predefined classes. An application in credit granting is used to illustrate the capabilities of the system.     

An integrative evaluation framework for intelligent decision support systems

Evaluation of the overall effectiveness of decision support systems (DSS) has been a research topic since the early 1980s. As artificial intelligence methods have been incorporated into systems to create intelligent decision support systems (IDSS), researchers have attempted to quantify the value of the additional capabilities. Despite the useful and relevant insights generated by previous research, existing evaluation methodologies offer only a fragmented and incomplete view of IDSS value and the contribution of its technical infrastructure. This paper proposes an integrative, multiple criteria IDSS evaluation framework through a model that links the decision value of an IDSS to both the outcome from, and process of, decision making and down to specific components of the IDSS. The proposed methodology provides the designer and developer specific guidance on the intelligent tools most useful for a specific user with a particular decision problem. The proposed framework is illustrated by evaluating an actual IDSS that coordinates management of urban infrastructures.     

Executive views concerning decision support tools

Support tools for strategic-level decision-making have become increasingly popular. This study investigates the role of OR/MS tools in today’s strategic-level decision support tool market. Executives working in Finland’s 500 largest companies were asked about the decision support tools they use when making major decisions. The responses received indicated that executives actively use a variety of tools, and an average of five different strategic-level tools. Approximately 10% of the tools used could be identified as OR/MS type, these often suit the needs of larger companies with strategic logistical or production functions and compared to other tools, have a specific profile. Executives see advantages in using tools that provide cognitive, collaboration and communication possibilities, and also in using tools that make processes more efficient. OR methodologies have influenced some of the other tools on the market, but ‘soft OR’ tool usage could not be identified. Tools which support creativity are needed.     

Forty years of discrete-event simulation—a personal reflection

Discrete-event simulation first emerged in the late 1950s and it has grown in popularity steadily to be now recognized as the most frequently used of the classical Operational Research techniques across a range of industries—manufacturing, travel, finance, health and beyond. I have been engaged with such simulation from 1964 up to the present day. This paper reviews the history and evolution of discrete-event simulation from his personal perspective, with a particular interest in software development up to 1992. Extrapolating from that history, the paper goes on to comment on the prospective continuing evolution of simulation and its software.     

Risk analysis techniques and their application to software development

The past decade has seen a dramatic change in the emphasis of software to hardware. Whereas a project may have comprised 80% hardware and 20% software, the reverse is now generally more realistic. This has resulted in a great deal of interest focusing around the areas of quality metrics and reliability growth applied to the software lifecycle. Risk analysis has to date seen many applications in the assessment of hardware but little in the software area. This paper reviews the risk analysis techniques that have been developed in a range of industries. Progress in this area has been most apparent in the chemical and nuclear power industries where probabilistic risk assessment has been used to estimate the total risk associated with the whole plant. A discussion of the appropriateness of the techniques to software safety assessment is included together with an outline of the methods currently being used to detect software faults. Suggestions are made for a new methodology in analysing software safety.     

MCDA and preference disaggregation in group decision support systems

Within the frame of decision aid literature, group decision making has drawn the attention of researchers from a wide spectrum of disciplines. Group Decision Support Systems (GDSS) can play a critical role, in decision situations with multiple individuals, each having his/her own private point of view on the handling of the decision problem. In such an environment, the conflict between the members of the group is not a seldom situation. Multiple criteria decision aid (MCDA) methods can be proven as invaluable tools in handling such interpersonal conflicts where the aim is to achieve consensus between the group members or at least reduce the amount of conflict among participating individuals. This paper reviews some of the past approaches in the multiple criteria–multiple decision makers context.     

A technological,organisational, and environmental analysis of decision making methodologies and satisfaction in the context of IT induced business transformations

Although Operational Research (OR) has successfully provided many methodologies to address complex decision problems, in particular based on the rationality principle, there has been too little discussion regarding their limited consideration in IT evaluation practice and associated decision making satisfaction levels in an organisational context. The aim of this paper is to address these issues through providing a current account of diffusion and infusion of OR methodologies in IT decision making practice, and by analysing factors affecting decision making satisfaction from a Technological, Organisational, and Environmental (TOE) framework in the context of IT induced business transformations. We developed a structural equation model and conducted an empirical survey, which supported four out of five developed research hypotheses. Our results show that while Decision Support Systems (DSSs), holistic IT evaluation methods, and management support seem to positively affect individual satisfaction, legislative regulation has an adverse effect. Results also revealed a persistent methodology diffusion and infusion gap. The paper discusses implications in each of these aspects and presents opportunities for future work.     

SIMULEX — a multiattribute DSS to solve rescheduling problems

Knowledge-based systems (KBS) can help to make simulation available to a large group of users. We want to exemplify this by describing a decision support system (DSS) for short term rescheduling in manufacturing called SIMULEX. It couples expert systems, simulation, and a multiattribute decision making (MADM) procedure to assist the production manager. After an introduction to simulation as a problem solving tool, the current problems in production control and the goals of the project are described. Then, the various components of SIMULEX are explained in some detail. Some results and a short outlook conclude the article.     

The development of a hybrid intelligent maintenance optimisation system (HIMOS)

This paper reports on the development of a hybrid intelligent maintenance optimisation system (HIMOS) for decision support. It is a follow-up to an earlier paper published in the Journal of the Operational Research Society in 1995. Both papers refer to systems where there are very many components which may break down independently. When a component breaks down, corrective action (CO) is required. The problem is to determine the optimal maintenance policy, essentially the frequency of preventive maintenance (PM) which minimises the sum of down time due to PM and CO.HIMOS, like its predecessor IMOS, uses an ‘intelligent’ decision support system to carry out an automated analysis of the maintenance history data. Maintenance data are presented to the system and the most suitable mathematical model from a model-base is identified utilising a hybrid knowledge/case based system (KBS/CBR). Thus initially a rule base is applied to select a model, as in the case of IMOS. If no model is matched, the system reverts to its historical case-base to match the current case with a similar case that has been previously modelled. This double reasoning adds to the system's true learning capabilities (intelligence) and increases the rate of success of model selection. A prototype system is written in Visual Basic® for an IBM compatible PC. The study results include optimal PM intervals for a sample of industrial data sets. The results of the validation exercise of HIMOS against expert advice has shown that the system functions satisfactorily.     

The development of computer software for risk analysis: A decision support system development case study

Over the past eight years the Projects Department of BP's Group Engineering and Technical Centre has evolved a risk analysis methodology which is applied during the project appraisal phase to all major engineering construction projects. The computational methods in current use are based on the Common Interval and Memory (CIM) approach, which allows the direct enumeration of distribution combinations rather than the more common Monte Carlo simulation approach. Computer software has been developed in-house to apply these techniques. The programs are written in Fortran and are designed to be used interactively. This paper reviews the general framework of risk analysis applications on BP projects and the lessons learned in developing the first generation of computer software, used until 1985. Some of these lessons may be relevant to decision support system development by others. The development of a new generation of software, now implemented, is also discussed briefly.     

THE FAO PRECAUTIONARY APPROACH AFTER ALMOST 10 YEARS: HAVE WE PROGRESSED TOWARDS IMPLEMENTING SIMULATION‐TESTED FEEDBACK‐CONTROL MANAGEMENT SYSTEMS FOR FISHERIES MANAGEMENT?

ABSTRACT. It is almost ten years since the FAO Technical Consultation on the Precautionary Approach to Capture Fisheries took place in Lysekil, Sweden. One outcome from this Technical Consultation was a set of guidelines on the precautionary approach to capture fisheries and species introductions. These guidelines include the need to incorporate harvest control rules in management plans. Harvest control rules should specify what action is to be taken when specified deviations from the operational targets and constraints are observed. The specification should include minimum data requirements for the types of assessment methods to be used for decision‐making. Combinations of harvest control rules, assessment methods and data collection schemes are referred to as management procedures. It is now well‐recognized that using management procedures is likely to lead to improved conservation of fishery resources, and that they should be evaluated to assess whether they are likely to achieve the goals for fishery management given the types of uncertainties that are likely to frustrate this venture. In general, evaluation of management procedures has been based on simulation modeling. This paper reviews the progress that has been made in various fisheries jurisdictions in terms of implementing management procedures, and why and where it has proved difficult or even impossible to implement management procedures.     

Financial modelling: Where to go? With an illustration for portfolio management

The definition of Financial Modelling chosen by the EURO working group on financial modelling is ‘the development and implementation of tools supporting firms, investors, intermediaries, governments and others in their financial-economic decision making, including the validation of the premises behind these tools and the measurement of the effectivity of the use of these tools’. Clearly, in this definition, the decision and its solution is central. Unlike financial modelling in our definition, the theory of finance is not so much concerned with individual decisions, but rather with the effects of the decisions and actions of many individuals on the formation of prices in financial markets. It is therefore no wonder that the assumptions underlying financial theory, which at best describe ‘average individuals’ and ‘average decision situations’, are not suited to describe specific individual decision problems. In our view it is the role of financial modelling to support individual decision making, taking account of the peculiarities of the actual case, where possible taking benefit from the results of the financial theory. This philosophy towards financial modelling is illustrated by a framework for portfolio management.     

Community facilitation of problem structuring and decision making processes: Experiences from the EU LEADER+ programme

This paper reports on the work carried out supporting a rural community in Denmark under the LEADER+ programme. This is a programme that supports development in particularly vulnerable rural regions of the European countries members of EU. It supports creative and innovative projects that can contribute to long-term and sustainable development in these regions. The main tasks have been the organisation and facilitation of conferences and workshops to structure the problematic situation of identifying and designing innovative projects for the development of the community and to support decision making processes related to the agreement on action plans. Learning to design, plan, manage and facilitate conferences and workshops have also being another central activity. The main purpose of these conferences and workshops was not only problem structuring and decision making in connection with community development but also the transfer of facilitation skills and appropriate methods to the community.     

The Validation of Expert Systems — Contrasts with Traditional Methods

Recent research has demonstrated that little validation is carried out during and after the building of operational research models for decision support. In a subject area that has been of great interest for more than a decade, this reflects the fact that validation is not yet firmly embedded into the methodology of mathematical modelling that underpins conventional decision support systems. With the interest now being shown in expert systems, it is important to devise an appropriate methodology of validation for such systems. This paper contributes to this development by describing the types of validation that should be performed with decision support systems, and compares and contrasts the features found in the validation of mathematical models with those required of validation of expert systems.     

A naïve approach for solving MCDM problems: the GUESS method

We present a simple multiple criteria decision making solution technique called the GUESS method. This method has been used in MCDM experiments where different solution methods have been compared. The GUESS method is an interactive solution method designed to be used with continuous multiple criteria decision problems. It is based on a class of solution methods called reference point methods whereby the decision maker generates a sequence of solutions based on a sequence of guesses or aspiration vectors. In this paper we explain the basic concepts of the GUESS method and describe the algorithm of the solution method. An illustrative example is provided, along with a discussion of the method from a behavioural decision making perspective.     

Using soft OR principles for collaborative simulation: a case study in the Dutch airline industry

Collaborative simulation is a method to handle problem situations that are technologically and socially complex. It combines discrete event simulation with methods, techniques and tools designed to help groups progress with their problems. Discrete event simulation and group support both appear to have clear promises in embedding soft OR principles, yet also contain limitations. Furthermore, simulation and group support appear to be complementary, balancing each other's limitations. Therefore, the combination of group support and discrete event simulation seems to be a fruitful vehicle for the application of soft OR principles. Through experiences in a case study at the cargo department of a major airline, we examine how collaborative simulation can be applied in practice as problem structuring method. We conclude that collaborative simulation has definite potential as a soft OR technique, but further research is required to speed up different steps of simulation to fully use simulation in interactive decision making sessions with multiple stakeholders.     

Visual-interactive decision modeling (VIDEMO) in policy management: Bridging the gap between analytic and conceptual decision modeling

Policy decision making is a process, rather than a means to an end, stretching over a long time span in a dynamic environment. The advent of easily accessible modeling paradigms promotes the use of sophisticated tools to support policy decision making. It is argued, however, that to be successful in practice, the analytic approaches must be flexible and their role in the problem solving process transparent. In this paper we discuss the concept of visual interactive decision modeling (VIDEMO) in policy management. After positioning decision modeling in the context of problem solving, a generic modeling environment is proposed. It provides the necessary flexibility at the structural level coupled with the required transparency at the formal and resolution levels. The system is based on the premise that policy decision makers can only benefit from the power of analytic modeling if they are supported where and how they want to be supported, without having the analytic tool posing a frame to problem perception, problem analysis, and decision making. In its final version, the proposed VIDEMO approach bridges the gap between analytic and conceptual decision modeling.     

Intelligent management systems in operations: a review

Operations management is an area that has recently started to benefit from the use of AI techniques such as expert systems, neural networks and genetic algorithms. These techniques can extend the usefulness of OR modelling and enable new types of decision tasks to be supported by computer-based systems. This paper attempts to review ‘intelligent’ decision support systems and their potential to address some of the problems faced in various areas of operations management. Some useful techniques developed in the field of artificial intelligence are outlined and examples of attempts to use these approaches to support decision making in various areas of operations management are described. Recognising the scale of a complete review of all these areas, emphasis has been given to the most significant and more recent publications.     

Modeling uncertainty in multi-criteria decision analysis

his paper provides a review of multiple criteria decision analysis (MCDA) for cases where attribute evaluations are uncertain. The main aim is to identify different tools which can be used to represent uncertain evaluations, and to broadly survey the available decision models that can be used to support uncertain decision making. The review includes models using probabilities or probability-like quantities; explicit risk measures such as quantiles and variances; fuzzy numbers, and scenarios. The practical assessment of uncertain outcomes and preferences associated with these outcomes is also discussed.