Brought to you by EarthWeb
IT Library Logo

Click Here!
Click Here!

Search the site:
 
EXPERT SEARCH -----
Programming Languages
Databases
Security
Web Services
Network Services
Middleware
Components
Operating Systems
User Interfaces
Groupware & Collaboration
Content Management
Productivity Applications
Hardware
Fun & Games

EarthWeb Direct EarthWeb Direct Fatbrain Auctions Support Source Answers

EarthWeb sites
Crossnodes
Datamation
Developer.com
DICE
EarthWeb.com
EarthWeb Direct
ERP Hub
Gamelan
GoCertify.com
HTMLGoodies
Intranet Journal
IT Knowledge
IT Library
JavaGoodies
JARS
JavaScripts.com
open source IT
RoadCoders
Y2K Info

Previous Table of Contents Next


Chapter 29
Expert Systems for Marketing: From Decision Aid to Interactive Marketing

Sang-Kee Lee and Jae Kyu Lee


CONTENTS

1. Application Areas of Marketing Expert Systems
2. Problem Types and AI Techniques of Marketing Expert Systems
3. From Decision Aid to True Marketing
4. Expert System for Customized Purchasing Support
5. Architecture of Salesman Expert System
6. Menswear Case: Variables
7. Menswear Case: Constraints
7.1. Importance of Constraints
7.2. Types of Constraints
7.2.1. Value Compatibility Constraints
    7.2.2. Value Incompatibility Constraints
    7.2.3. Functional Assignment Constraints
    7.2.4. Algebraic Inequality Constraints
8. Rules in Menswear Case
8.1. Customer-Product Rules
8.2. Sales Strategic Rules for Variable and Value Ordering
8.2.1. Variable Ordering Rules
    8.2.2. Value Ordering Rules
9. Reasoning Procedure in Salesman Expert System
10. Trends of AI Research for Marketing
Acknowledgments
References

1. APPLICATION AREAS OF MARKETING EXPERT SYSTEMS

Marketing has been one of the most active areas of expert system research and applications (Murdoch, 1990). The functional areas of marketing to which an expert systems approach has been applied include:

  • Advertising design (RAD: McCann, Tadlaoui, and Gallagher, 1990; ADCAD: Burke, Rangaswamy, Wind and Eliashberg, 1990)
  • Advertising response prediction (ADDUCE: Burke, 1991)
  • Brand management (BMA: McCann, Lahti, and Hill, 1991)
  • Deal design (DEALMAKER: McCann and Gallagher, 1990)
  • Financial marketing (FAME: Apte et al., 1992)
  • Marketing negotiation (NEGOTEX: Rangaswamy, Eliasberg, Burke, and Wind, 1989)
  • Market share analysis (SHANEX: Alpar, 1991)
  • Media planning (Mitchell, 1987)
  • New product pricing (Casey and Murphy, 1994) and transfer pricing (TRANSFER: Kirsh et al., 1991)
  • News search using scanner data (INFER: Rangaswamy, Harlam, and Lodish, 1991; CoverStory: Schmitz, Armstrong, and Little, 1990; SalesPartner: Schmitz, 1994; SCAN*EXPERT: Bayer and Harter, 1991)
  • Product configuration (UNIK-SES: Lee, Lee, and Lee, 1996)
  • Promotion evaluation (Poh and Jasic, 1995; PROMOTIONSCAN: Abraham and Lodish, 1993)
  • Retail sales forecasting (Mcintyre, Achabal, and Miller, 1993)
  • Retail space allocation (Resource-opt: Singh, Cook, and Corstjens, 1988)

2. PROBLEM TYPES AND AI TECHNIQUES OF MARKETING EXPERT SYSTEMS

The research can be classified according to problem type as follows:

  • Consulting (McCann, Tadlaoui, and Gallagher, 1990; Casey and Murphy, 1994; Burke, Rangaswamy, Wind, and Eliashberg, 1990; Burke, 1991; Rangaswamy, Eliasberg, Burke, and Wind, 1989)
  • Data analysis and mining (Alpar, 1991; Bayer and Harter, 1991; Rangaswamy, Harlam, and Lodish, 1991; Abraham and Lodish, 1993; Poh and Jasic, 1995, Schmitz, Armstrong, and Little, 1990; Schmitz, 1994; Rangaswamy, Harlam, and Lodish, 1991)
  • Forecasting (Mcintyre, Achabal, and Miller, 1993)
  • Planning and control (McCann, Lathi, and Hill, 1991; Apte et al., 1992)
  • Configuration (Lee, Lee, and Lee, 1996)
  • Resource allocation (Singh, Cook, and Corstjens, 1988)

As we can see from the above, two major problem types are consulting and data analysis and mining. This reflects the need of many marketing activities to be supported by consulting activities, and the motivation that the existence of enormous amounts of scanner data provided to research and development of expert systems that analyze and mine them for marketing success. For marketing research, expert system concepts, paradigms, techniques, and tools provide new ways to build models that apply marketing knowledge. Besides the rule-based approach, which is the most popular, case-based approaches (Mcintyre, Achabal, and Miller, 1993; Burke, 1991), model-based approaches (McCann and Gallagher, 1990; McCann, Lahti, and Hill, 1991), and neural networks (Poh and Jasic, 1995) have also been used as AI techniques for marketing decision-making.

Mitchell et al. (Mitchell, Russo, and Wittink, 1991) compared the use of human judgment, expert systems, and statistical/optimization models for marketing decisions and claimed that the construction of expert systems in marketing poses problems that are either quantitatively or qualitatively more difficult than those faced by expert systems builders in non-human domains. Some systems, for instance, had to use hybrid techniques such as knowledge-based techniques with algorithmic techniques (Singh, Cook, and Corstjens, 1988), knowledge-based techniques with statistical methods (Abraham and Lodish, 1993; Rangaswamy, Harlam, and Lodish, 1991), and constraint-and rule-based techniques (Lee, Lee, and Lee, 1996).


Previous Table of Contents Next

footer nav
Use of this site is subject certain Terms & Conditions.
Copyright (c) 1996-1999 EarthWeb, Inc.. All rights reserved. Reproduction in whole or in part in any form or medium without express written permission of EarthWeb is prohibited. Please read our privacy policy for details.