Book Contents

Ch. 10
Building Knowledge-Driven DSS and Mining Data

Chapter Contents
Previous Page
Next Page

Key Terms and Concepts

Holsapple and Whinston (1996) discuss artificially intelligent DSS that "make use of computer-based mechanisms from the field of artificial intelligence". These reasoning systems provide suggestions for business decision-makers and have the same general architecture as any other DSS. When a DSS uses artificial intelligence technologies including expert system technologies and some data mining tools to assist business decision-makers we will call the system a Knowledge-Driven Decision Support System. Every application of these technologies should not be called a decision support system. This section discusses key terms associated with Knowledge-Driven Decision Support Systems.

Knowledge-Driven DSS and Management Expert Systems

Knowledge-Driven Decision Support Systems store and apply knowledge for a variety of specific business problems. These problems include classification and configuration tasks such as Loan Credit Scoring, Fraud Detection and Investment Optimization.

Until recently, human experts had to perform this type of knowledge intensive task. Most of us identify a human expert as someone who is very knowledgeable in a particular area or subject. This human expert knows the appropriate questions to ask in order to draw a particular conclusion. In a similar way, one major type of expert system is a computer program that asks questions and reasons with the knowledge stored as part of the program about a narrow, specialized subject. This type of program attempts to solve a problem or give advice.

In general, expert systems are programs with specialized problem-solving expertise. The "expertise" consists of three components: 1) knowledge of symptoms related to a particular topic or domain, 2) understanding of the relations among symptoms, problems and solutions within that domain, and 3) "skill" or methods for solving some of the problems. An expert system is a knowledge-intensive program that captures the expertise of a human in a limited domain of knowledge and experience. It assists decision-makers by asking relevant questions in a problem domain and recommending actions and explaining reasons for adopting an action.

An expert system can explain the reasoning behind a conclusion it has reached. This explanation capability is extremely important in auditing and validating the results from a Knowledge-Driven DSS. It also helps ensure the system is in compliance with applicable policies, regulations or legal requirements.

Knowledge-Driven DSS and management expert systems have a number of benefits. Such systems can improve consistency in decision-making, enforce policies and regulations, distribute expertise to non-expert staff and retain valuable expertise for a company when experts retire or resign.

Data Mining and Knowledge Discovery

Data mining and knowledge discovery are "hot" topics in the Information Systems and Marketing trade press. For many years companies have been storing large amounts of data and more recently companies have built large data warehouses. Now managers want to take advantage of the data they have collected by analyzing it using statistical and artificial intelligence tools. Data mining techniques can help managers discover hidden relationships and patterns in data. Some analysts feel data mining can help a company gain a competitive advantage. Data mining tools can be used for both hypothesis testing and knowledge discovery. When vendors discuss data mining, they may be selling a set of end-user tools or a decision support capability or both. Managers and business analysts can perform data mining activities. Target users of these tools include financial analysts, statisticians and marketing researchers. People who use these DSS and tools should have experience interpreting data.


DSSResources.COMsm is maintained and all its pages are copyrighted (c) 1995-2002 by D. J. Power (see home page). Please contact This page was last modified Wednesday, May 30, 2007. See disclaimer and privacy statement.