Expert Systems in Economics, Banking and Management

Expert systems in management and administration - are they really different from Decision Support Systems?

Expert systems (ES) are computer programs which make recommendations and draw conclusions from heuristic rules and from relationships derived out of human experience. A decision support system (DSS) is a computer-based management information system (MIS) linking one or more data bases to computer software for exploration and analysis of the data. Combined in a single system an ES and a DSS comprise an expert support system. A simple expert support system for use in fishery stock assessment and management is described. It demonstrates a number of practical benefits of the use of expert systems technology to implement and integrate some simple tasks, i.e., bioeconomic modelling, cost/benefit sampling analyses, and technical interpretation, namely: (1) the effects of different population structures and patterns of fishing on modelling results can be examined under the programmed guidance of the expert system; (2) the effects of different levels of sampling precision on modelling results can be similarly examined; (3) cost/benefit analyses of different sampling budgets can be examined; and (4) management advice specific to each sampling, surplus production (four different models), and net present value (NPV) case is given. An examination of the future of expert support systems in fishery stock assessment and management considers four possible levels of support, as follows: (1) to provide technical explanations, (2) to manage and catalog repetitive processes, (3) to guide “low-level decisions”, and (4) to contribute directly to strategic and policy decisions. Currently, movement in expert systems usage is toward so-called “embedded systems”, for example, an expert support system which comprises, in addition to computational models and databases, one or more expert systems. Problems related to the design and development of ESS for fishery stock assessment and management are challenging conceptual problems; the construction and programming of ESS are reasonably tractable tasks. Determining what an ESS will do is often the principle conceptual question. Expert support systems provide another tool for fishery stock assessment scientists and managers to increase their productivity.

Expert systems in agriculture and resource management

This paper looks at expert systems in management, by using a business game as an experimental vehicle. An expert system called EXGAME was developed to play a business game, which is normally played by students, with minimal human intervention. This paper concentrates on the effectiveness of EXGAME as compared with human players for tasks at different levels. EXGAME was able to replace human players in decision making at the operational level, and indeed outperform them. However, it proved to be impractical to replace human input at the strategic level. The paper also sheds some light on the problems of trying to build an expert system when there is no real expert. A combination of a modular knowledge-base structure and a process of ‘learning by experimentation’ was effective in this case; it is suggested that this may be an appropriate development strategy in other similar situations. © 1998 John Wiley & Sons, Ltd.

Applications for expert systems are finding their way into every imaginable use. The expert system is a valuable tool, however, not to the exclusion of computer modeling techniques. Computer modeling and expert systems in water management have been used for over ten years to develop appropriate treatment recommendations and monitoring/control functions. Chemical treatment program development in recirculating cooling water, once-through scale inhibition, once-through corrosion control, and on-line real-time system monitoring play an increasingly important role in cooling water management practices.

Chapter 16 - Intelligent and knowledge-based waste management: smart decision-support system

Our paper describes the principles for constructing the leading expert information systems for managing the quality of an economic entity and its products based on the example of an industrial enterprise and its products. Expert quality management systems represent a unique solution for optimization and improving the operation of any company. However, their role in industrial enterprises is indispensable and should not be underestimated. Within the framework of our research and its main findings, we provide and scrutinize the systematization of modern scientific ideas about information technologies for building expert systems in the context of highlighting the subject field of their application. Our results show that the implementation of expert quality management systems in the industrial enterprises in Russia (as well as in the other countries) would lead to the considerable improvement in product quality with the reduced costs for these products. We also note that the enterprise productivity rises, and cost recovery period of invested funds shortens as a result of the deployment of these systems.

India is basically an agriculture country and the dairy sector plays a significant role in supplementing family income and generating employment in the rural areas, particularly among the landless, small and marginal farmers and farm women, besides providing cheap and nutritious food to millions of people. In India, the total milk production is extremely poor in terms of productivity in the world due to lack of proper extension system. Even though, information on various aspects of dairy cattle management is available, they are not reaching the required area of the farm units / farmers. To address this problem, a rule based expert system for dairy cattle management was developed with user friendly menus. This system interacts with users in two ways. As a decision support tool, the user can interact with the system using some arranged rules which are collection of if / then rules, collected from experts in the veterinary field. Using these rules, a knowledge base was designed for the expert system and programming codes were writeen in VB. Net. The proposed expert system provides instant access of the required knowledge on selected parameters, viz. feeding, breeding, diseases, cattle shed management, milking, fodder cultivation and health management. This expert system is useful as an online guide to the users who are involved in animal husbandry and dairy management.

An integrated expert decision support system for agricultural management

Expert System Tools for Construction Planning and Control

Auditing of information security constitutes a key part of security operations taken inside organizations. Often information security problems must be addressed as quickly as possible. The purposes of this work are to provide an insight to information security management and suggest some of solutions of developing expert system. This paper discusses the development of an application, which is based on international standards on information security and protection tools. The expert system is accompanied by web-based application module, which serves as an instrument for solving various security-related problems.

The use and development of expert systems in public and private organizations continue to increase. Many of these systems are being developed for production and operations management. Unfortunately, the impacts that these systems are having in these environments have, for the most part, not been investigated. Most studies on expert systems to date centre either on the technical aspects or validation issues. No one has taken a systemic view that takes into account both the technical issues and the human issues that will have to be addressed in implementing these systems. This paper seeks to stimulate research into the overall impact of expert systems implementation in production. To this end, fourteen research propositions are developed and presented. In addition, the major variables associated with these propositions are combined into a causal model to show the relationships between them and to reveal an overall perspective of the impacts of expert systems implementation on the production process.

The object of research is the banking system as an economic system of micro-level, characterized by such features as: complexity, dynamism and ability to self-organization. One of the most problematic places is an understanding of the peculiarities of the steady development of the banking system from the standpoint of the synergetic approach, which allows to explain the transformational processes that were previously considered accidental, unpredictable and not subject to conceptualization.\n\nDuring the study, methods of abstract-logical and system analysis were used in the theoretical substantiation of the features of the modern banking system. And the method of logical generalizations in identifying features of the characteristics of a complex economic system. The study of the functioning of a modern banking system should be based on the use of the theory of systems, the theory of complex systems and the theory of dynamic systems. It is proved that the processes of self-organization can occur only in those economic systems that have a high level of complexity, are dynamic and unpredictable in the long run, which should include the banking system.\n\nIt is proposed to understand the banking system as a complex, dynamic economic system:\n• which has the mechanisms of self-organization;\n• which can be described by integration, thermodynamic parameters, which fully reflect the exchange of material and financial resources with the environment;\n• which is distinguished by the dynamism and unevenness of its development.\n\nThis provides an opportunity to understand the laws of the functioning of the banking system, which is a prerequisite for ensuring its viability and sustainability under the influence of various exogenous and endogenous factors. Compared with the well-known system analysis, the proposed use of synergetics makes it possible to explain the progressive development of the banking system to a certain extent by fluctuations that are difficult to predict, but which are inherent to the system itself. It is in the conditions of the existence of such fluctuations that spontaneous formation of new structures in the banking system occurs, that is, self-organization takes place.

Expert systems have been proposed for a wide range of civil engineering applications. They have been applied most successfully in situations governed by simple rules. Many civil engineering decisions, however, must be made in environments in which simple rules are not possible, but rather large amounts of data must be analyzed and evaluated. This paper presents a methodology in which an expert system shell (INSIGHT 2+) is used to evaluate and display information on drought management planning. A linear programming model is used to generate optimal operating policies as a function of numerous past drought experiences. These policies are incorporated into an expert system where the user is required to identify the degree to which the current drought situation is similar to past events. The expert system then aids the user in developing appropriate management policies based on time of year, descriptions of drought intensity, and other system characteristics.

This article provides a computational framework to model self‐adaptive expert systems using the Petri net (PN) formalism. Self‐adaptive expert systems are understood here as expert systems with the ability to autonomously learn from external inputs, like monitoring data. To this end, the Bayesian learning principles are investigated and also combined with the Plausible PNs (PPNs) methodology. PPNs are a variant within the PN paradigm, which are efficient to jointly consider the dynamics of discrete events, like maintenance actions, together with multiple sources of uncertain information about a state variable. The manuscript shows the mathematical conditions and computational procedure where the Bayesian updating becomes a particular case of a more general basic operation within the PPN execution semantics, which enables the uncertain knowledge being updated from monitoring data. The approach is general, but here it is demonstrated in a novel computational model acting as expert system for railway track inspection management taken as a case study using published data from a laboratory simulation of train loading on ballast. The results reveal self‐adaptability and uncertainty management as key enabling aspects to optimize inspection actions in railway track, only being adaptively and autonomously triggered based on the actual learnt state of track and other contextual issues, like resource availability, as opposed to scheduled periodic maintenance activities.