EXPERT SYSTEMS

ARTIFICIAL INTELLIGENCE:-Computers with the ability to mimic or

duplicate the functions of the human brain.

Definition of Expert System:

Expert Systems (ES) are an Information System Applications that captures the
knowledge or expertise of a Specialist and then simulates the ‘Thinking’ of that
expert for those with less or no experience.

Expert system is a type of Artificial Intelligence. Expert systems attempt to

mimic human experts.ES can either support decision makers or completely
replace them .
In this system expertise is transferred from an expert to computer.

IDEA BEHIND EXPERT SYSTEMS

 Expertise is transferred from an expert to the computer.

 The knowledge is organized and stored in the computer.
 Users can call on the computer for specific advice as needed.
 The computer can make inferences & arrive at a conclusion.
 It then advised the non experts and explains if necessary the logic behind
the advice.

EXPERTISE & KNOWLEDGE

 Expertise is the extensive ,task specific knowledge acquired from training, reading and
experience.
 Enables experts to make faster and better decisions
 Takes a long time to acquire
 Is distributed in organizations in an uneven manner
 Transfer of expertise from a computer & then to a user involves 4 activities :
I. Knowledge Acquisition.
II. Knowledge Representation.
III. Knowledge Inferencing.
IV. Knowledge transfer.
KNOWLEDGE

 Acquired from experts and/or from documented resources

 Through the activity of knowledge representation, acquired knowledge is organized as
rules/frames & stored electronically in KNOWLEDGE BASE.
 Given the necessary expertise stored in the knowledge base the computer is
programmed so that it can make inferences which is performed in a component called
“INFERENCE ENGINE” which is the brain of the ES
 A unique feature of ES is its ability to explain its recommendations.
 The explanation & justification is done in a subsystem called “JUSTIFIER” or “THE
EXPLANATION SUBSYSTEM”

COMPONENTS OF EXPERT SYSTEMS

 Knowledge base
 Stores all relevant information, data, rules, cases, and relationships used by the
expert system
 Inference engine
 Seeks information and relationships from the knowledge base and provides
answers, predictions, and suggestions in the way a human expert would
 Rule
 A conditional statement that links given conditions to actions or outcomes
 Explanation facility
 A part of the expert system that allows a user or decision maker to understand
how the expert system arrived at certain conclusions or results
 Knowledge acquisition facility
 Provides a convenient and efficient means of capturing and storing all components
of the knowledge base

PARTICIPANTS IN EXPERT SYSTEMS DEVELOPMENT & USE

 Domain expert
 The individual or group whose expertise and knowledge is captured for use in an
expert system

 Knowledge user
 The individual or group who uses and benefits from the expert system

 Knowledge engineer
 Someone trained or experienced in the design, development, implementation,
and maintenance of an expert system
CASE-STUDY ON EXPERT SYSTEM
1.LOAN AND CREDIT TRANSACTIONS AT THE CHINA EVERBRIGHT BANK

 The CHINA EVERBRIGHT BANK has more than 350 branches in 36 cities
 It has assets of USD 41 billions and outstanding loans totaling USD 24 billion
 EVERBRIGHT BANK provides commercial loan in a wide range of industries
throughout China
 However as the Chinese economy has grown, the banks diverse client base created a level
of process complexity that became difficult to manage effectively.
 Loans approvals were particularly complex requiring the evaluation of multiple factors
such as CUSTOMER PREFERENCES,CREDIT HISTORY and CAPACITY,
REGULATIONS, BUSINESS OPERATIONS and INDUSTRIAL RISK.
 Credit Risk managers had to collect information from different sources before manually
assessing each risk profile to determine eligibility and terms of the loans.
 This process created a backlog in loan processing which could take weeks or even months
for approval.
 CHINA EVERBRIGHT BANK has selected ILOG IRULES, a key offering in ILOGS
business rule management systems product line, to create an automated loan and credit
decision platform replacing the inflexible manual process.
 The new system allows EVERBRIGHT BANK to process loan applications in one day
instead of several weeks.
 Since ILOG IRULES ensures loan servicing with timely tracking of repayments , it
reduces losses from delayed payment which contributes to the overall financial health of
the bank.

2. Failure of expert systems at MARY KAY(Marykay.com) MULTINATIONAL

COSMETICS company.
(EVEN AN INTELLIGENT SYSTEM CAN FAIL)

 Mary Kay marykay.com , the multinational cosmetics company uses teams of managers
and analysts to plan its product.
 This process attempted to iron out potential weaknesses before production.
 However the company still faced costly errors such as PRODUCT- CONTAINER
INCOMPATIBILITY, INTERACTION OF CHEMICAL COMPOSITIONS and Market
requirements with regard to packaging and distribution.
 A group of Mary Kay Managers representing various functional areas used to meet every
six weeks to make product decisions.
 This group decisions making process was loosely structured.
 The marketing team would give its requirements to the product formulator and the process
engineer at the same time.
  Marketing design requests often proved to be beyond the allocated budget or technical
possibilities and other problems arose as a result of not knowing the ultimate product
formulations.
 The result was more meetings and redesign.
 In an effort to keep costs to minimum, it engaged the services of a research university that
developed a system that consisted of a DECISION SUPPORT SYSTEM….. TOOL plus
two EXPERT SYSTEM COMPONENTS.
 The DECISION SUPPORT tool was able to select COMPATIBLE PACKAGES for a
given cosmetic product and to test and PACKAGE SUITABILITY.
 At first the system was a tremendous success. There was a clear match..? between the
abilities of the system technology and nature of the problem.
 By reducing the time required for new product development, executives were freed for
other tasks and the team met only rarely to ratify the recommendations of the ES.
 However , without support staff to maintain the ES,no one knew how to add or modify
decision rules.
 Even the firms IT unit was unable to help and so the system fell in disuse.
 More importantly when the director of package design left the firm so did the enthusiasm
for ES

ADVANTAGES OF EXPERT SYSTEMS

 Increased quality
 Reliability
 Increased capabilities of other systems
 Decreased decision making time
 Reduced downtime

LIMITATIONS OF EXPERT SYSTEMS

 Not always effective

 Conclusions are not always drawn.
 Possibility of error.

APPLICATIONS OF EXPERT SYSTEMS

 AI and expert systems embedded in products

 Loan analysis
 Virus detection
 Repair and maintenance
 Shipping
 Marketing