Integrated Case-Based and Rule-Based reasoning approaches for Insurance

1
Integrated Case-Based and Rule-Based reasoning
approaches for Insurance
Presented BY Palwencha Nagraj Krishna (04329801)
Guided By Prof Rajendra M. Sonar
2
Content

• Introduction to Expert Systems
• Case Base Reasoning
• Hybrid Systems
• Different Integrated Approaches
• Insurance Domain Application
• Problem Definition
• Application- A Hybrid Expert System Framework

3
Expert Systems

• Expert systems are defined as an intelligent
  computer program that uses knowledge and
  inference procedures to solve problems those are
  difficult enough to require significant human
  expertise for their solution.
• Knowledge-based expert systems, or simply expert
  systems, use human knowledge to solve problems
  that normally would require human intelligence.

Dr. Peter R. Gillett, Associate Professor,
Department of Accounting Information Systems,
Faculty of Management, Rutgers University
4
ES Components
James P. Ignizio, Introduction to Expert Systems
The Development and Implementation of Rule-Based
Expert Systems, McGraw-Hill International
Editions, Computer Science Series, 2000.
5
Knowledge Acquisition and Validation

• Knowledge Engineering (KE)
• Acquire Knowledge
• Validate Knowledge
• Represent Knowledge
• Inferencing

Knowledge Representation

• KR Type
• OAV Triplet
• Semantic Network
• Frames
• Rules

6
Introduction to CBR

• Case base reasoning system use the technique to
  match a situation or problem description to a
  stored database.
• Input is given by the user on the current
  situation and the output is case retrieval to the
  most similar match to the database.
• The CBR engine first searches for case history
  that are similar to the given description.
• The main intention is to reuse previous
  experiences for actual problems.

. Diagnostic Stratrgies, Expert System
Development Series Introduction to Case- Base
Reasoning, www.DiagnosticStrategies.com.
7
The CBR cycle
Ian Watson Farhi Marir (1994), Case-Based
Reasoning A Review, Cambridge University Press,
1994. The Knowledge Engineering Review, Vol. 9,
No. 4 pp355-381
8
Different methods

• Nearest neighbor

The system would simply prefer cases that match
more features to a case that matched fewer.

• Induction

Inductive approaches to indexing are useful where
the retrieval goal or case outcome is well
defined.
The output of the induction process is in the
form of a decision tress.
9
Different methods cont..

• Knowledge guided

A knowledge-guided approach uses human knowledge
to the induction process by manually identifying
known case features that are considered important
10
Hybrid Intelligent Systems

• Hybrid Intelligent System is a combination of
  multiple techniques
• Almost every conceivable problem has been
  approached using some form of hybrid system.

Suran Goonatilake, Sukdev Khebbal, Intellegent
Hybrid Systems , Goonatilake Khebbal Editor
11
Integrated expert systems and case-based reasoning
Indexed Case Library
Indexing
CBR
Problem
RBR
Solution
Combination
Andrew R. Golding , Paul S. Rosenbloom,
Improving accuracy by combining rule-based and
case-based reasoning, ELSEVIER, Artificial
Intelligence, Issue November 1996, pages215-254
12
ES and CBR in Insurance

• It consist of three key process
• data entry,
• data revision and
• evaluation of data by the expert
• RuleMaster provides ways to develop
• the rules in the system.

Dr. Gary A. Wicklund and Ms. Roberta M. Roth,
Expert Systems in Insurance Underwriting Model
Development and Application, ACM ,Issue1987,
Pages 129 139.
13
Problem Definition
Field Officer
Risk Assessment
Agent
Advice Policy
Client
14
Hybrid approach for insurance
Risk Assessment Parameter
Indexed Case Library
Indexing
Problem
CBR
RBR
Solution
Combination
Andrew R. Golding , Paul S. Rosenbloom,
Improving accuracy by combining rule-based and
case-based reasoning, ELSEVIER, Artificial
Intelligence, Issue November 1996, pages215-254
15
Application format

• Age Date of birth -gtMajor, Minor -gt age limit -gt
  find available policy period
• Education 10, 12, ITI, Diploma, Graduate,
  Post-Graduate, PhD, Professional
  (engg/medical/lawer) Is education on
  questionnaire necessary
• Gender Male, Female -gt Female -gt Housewife
• Occupation
• Service Government, Non-Government, Private,
  Professional, Military, Navy, etc
• Business Consultant, Industry, Retailing,
  Agriculture
• Expected Period of Policy
• Purpose of Policy Investment, Child Education
• Income (Rs.) Take-home Monthly/ yearly income
• Assets (Rs.) Computer/House/Car/Bike etc -gt
  Tentative value of Assets
• Liabilities (Rs.) Loans and other financial
  liabilities
• Present LIC Installment (Rs.) monthly/quarterly/h
  alf-yearly/yearly
• Number of Dependents
• Physical Inability like handicapped/ Mental
  disorder
• Diseases HIV/ BP/ Diabetes
• Loan Facility required on Policy?
• Calculate Risk
• Calculate Installment

16
Risk Assessment

• Occupation
• Income
• Assets
• Liabilities
• Physical Inability
• Diseases

17
Application-A Hybrid Expert System Framework

• IIT has developed a Hybrid AI shell environment
  named as iKen Core
• This shell has four techniques
• Rule Based Reasoning
• Case Based Reasoning
• Genetic Algorithm
• Artificial Neural Network

18
First Stage Work Done

• Background Study Expert Systems and Case Base
  Reasoning
• Literature survey Related work
• Integrated approaches
• Study of Expert System working
• Analysis of Insurance Domain
• Studied the potential applications of insurance
  domain.
• Tried to define the prototype we are going to use

19
Future Study

• Devising methodology for knowledge acquisition,
  presentation and retrieval.
• Selection/customization of proper tool.
• Developing prototype systems.

20
Thank You