SCMS-MIS-UNIT-3-A

DECISION-MAKING
J.K.OKE
 UNIT-3
DECISION-MAKING
• TYPES OF DECISIONS, STAGES, LEVELS AND
ENVIRONMENTS –
• DECISION MAKING PROCESS –
• OVERVIEW OF DM MODELS – MODELING DECISION
SITUATION.
• DECISION MAKING TOOLS:
• DSS: CONCEPT AND PHILOSOPHY, CHARACTERISTICS AND
COMPONENTS OF DSS –
 UNIT-3
DECISION-MAKING

• DECISION MAKING TOOLS (CONTD….):

• PAYOFF MATRIX,
• DECISION TREE AND DECISION TABLES,
• MANAGING KNOWLEDGE AND COLLABORATION,
• ENHANCING DECISION-MAKING
 UNIT-3-A
DECISION-MAKING

• TYPES OF DECISIONS, STAGES, LEVELS AND

ENVIRONMENTS –
• DECISION MAKING PROCESS
 DECISION-MAKING

• DECISION-MAKING IS A VITAL PART OF ANY

BUSINESS.
• THIS IS BECAUSE MAJOR OPERATIONS IN AN
ORGANISATION ARE DEPENDENT ON
DECISIONS MADE BY THE MANAGEMENT AND
OTHER KEY STAKEHOLDERS.
 DECISION-MAKING

• IN ORDER FOR A DECISION TO BE EFFECTIVE, A

GOOD INFORMATION SYSTEM IS CRUCIAL.
• MIS IS CRUCIAL FOR DECISION-MAKING AS IT
FACILITATES EFFECTIVE AND EFFICIENT
DECISION-MAKING.
• DECISIONS ARE TO BE TAKEN BY THE
MANAGER OR MANAGEMENT.
 MANAGEMENT &
DECISION-MAKING

•MANAGEMENT, IS DEFINED AS
•“THE PROCESS OF PLANNING, LEADING,
ORGANISING AND CONTROLLING THE
RESOURCES OF AN ORGANISATION IN THE
EFFECTIVE AND EFFICIENT PURSUIT OF
SPECIFIED ORGANISATIONAL GOALS”.
 MANAGEMENT &
DECISION-MAKING
•MANAGEMENT IS RESPONSIBLE FOR SURVIVAL,
SUCCESS, PROSPERITY & SUSTAINABILITY OF AN
ORGANISATION.
•HOWEVER, IN DISCHARGING ITS FUNCTIONS,
MANAGEMENT FACES A LOT OF PROBLEMS IN
TODAY’S DYNAMIC / “VUCA” AND FIERCELY
COMPETITIVE WORLD.
 MANAGEMENT &
DECISION-MAKING
•THE MANAGEMENT HAS TO PROCURE/OBTAIN,
ALLOCATE & UTILISE THE RESOURCES – HUMAN,
FINANCIAL AND PHYSICAL – EFFECTIVELY
(DOING THE RIGHT THINGS) & EFFICIENTLY
(‘DOING THE THINGS RIGHT’), AND GET THE
THINGS ‘DONE’ AND ‘DELIVER GOODS/RESULTS’.
•THIS INVOLVES MANAGING THE WORK,
MANAGING PEOPLE AND MANAGING THE
OPERATIONS.
 MANAGEMENT &
DECISION-MAKING

•UTILISATION OF RESOURCES, IN TURN,

INVOLVES EXERCISING CHOICES AND HENCE THE
BASIC JOB OF THE MANAGEMENT COULD BE
CONSIDERED TO BE ‘DECISION-MAKING’ IN
DISCHARGING VARIOUS FUNCTIONS ASSIGNED
TO IT.
 WHAT IS A DECISION?

•A DECISION IS A CHOICE MADE FROM

AVAILABLE ALTERNATIVES, AND AS SUCH ALL
DECISIONS HAVE SOME IMPACT/INFLUENCE ON
THE PERFORMANCE OF ORGANISATIONS.
•IT IS THE QUALITY OF DECISIONS WHICH
MAKE, DEVELOP, SURVIVE, STRIVE AND HELP
THE ORGANISATIONS PROSPER, EXPAND AND
MAKE FORAYS INTO DIVERSIFIED FIELDS.
MANAGERS & DECISION-MAKING
•MANAGERS, THEREFORE, HAVE TO DEVELOP
DECISION-MAKING SKILLS AS MANAGERS ARE
EVALUATED/ REWARDED ON THE BASIS OF THE
IMPORTANCE, NUMBERS AND RESULTS OF
THEIR DECISIONS.
•THE YARDSTICK OF MANAGERS’
EFFECTIVENESS AND VALUE TO THE
ORGANISATION IS DETERMINED BY THE
QUALITY OF DECISIONS TAKEN.
 DECISION-MAKING
ENVIRONMENT

•DECISIONS COULD BE MADE UNDER

DIFFERENT TYPES OF ENVIRONMENT I.E.,
AMBIGUITY, CERTAINTY, UNCERTAINTY AND
RISK.
 DECISION-MAKING
ENVIRONMENT

•AN ENVIRONMENT IS AMBIGUOUS WHEN THE

PROBLEM IS NOT CLEAR, THE GOAL IS NOT
CLEAR AND HENCE THE OUTCOME IS UNCLEAR.
• THE CERTAINTY ENVIRONMENT IS ONE WHERE
THE RELATIONSHIP BETWEEN INPUTS AND
OUTPUTS IS KNOWN AND HENCE THE RESULT IS
ALSO KNOWN.
 DECISION-MAKING
ENVIRONMENT
•THE UNCERTAINTY ELEMENT IS ONE WHERE
THERE IS UNAWARENESS ABOUT RESOURCES,
INPUT/OUTPUT RELATIONS AND THE OUTCOME
IS UNCERTAIN OR UNPREDICTABLE.
•THE RISK ENVIRONMENT IS ONE WHERE THE
RESULT IS UNKNOWN; IT MIGHT RESULT IN
PROFITS, BUT IT MIGHT LEAD TO INCURRING
LOSSES AS WELL.
 DECISION-MAKING
ENVIRONMENT
• THE DECISION-MAKING ENVIRONMENT WOULD
ALSO VARY DEPENDING UPON THE OWNERSHIP:
• PROPRIETORSHIP / PARTNERSHIP / LLP
• PUBLIC TRUST / SOCIETY
• PVT/PUBLIC LIMITED
• PUBLIC SECTOR / GOVERNMENT UNDERTAKING
• MNC (NATIONALITY
MATTERS-GERMAN/JAPANESE/CHINESE-UK/USA
ETC)
 DECISION-TYPES

•THEN AGAIN, DECISIONS COULD BE DIVIDED INTO TWO

CATEGORIES I.E.,
•PROGRAMMED DECISIONS AND NON-PROGRAMMED
DECISIONS.
 DECISION-TYPES
PROGRAMMED DECISIONS
{CHARACTERISTICS}
• THE MAJOR CHARACTERISTICS OF PROGRAMMED
DECISIONS ARE:
1. THEY ARE ROUTINE/STRUCTURED
2. THEY ARE REPETITIVE/SHORT-TERM
3. DEFINITE PROCEDURE IS TO BE FOLLOWED
4. THERE ARE LAID DOWN NORMS
5. THE SITUATIONS ARE KNOWN
6. THEY ARE TAKEN AT THE LOWER/OPERATING LEVELS
IN AN ORGANISATION
 DECISION-TYPES
PROGRAMMED DECISIONS
{TECHNIQUES USED}

•THE TECHNIQUES USED FOR TAKING PROGRAMMED

DECISIONS ARE:
1. HABIT
2. STANDARD OPERATING PROCEDURE (SOP)
3. ORGANISATIONAL HIERARCHY/STRUCTURE
4. OPERATIONAL RESEARCH
5. COMPUTERS
 DECISION TYPES
NON-PROGRAMMED
DECISIONS{CHARACTERISTICS}
• THE MAJOR CHARACTERISTICS OF NON-PROGRAMMED
DECISIONS ARE AS GIVEN BELOW.
1. NOVEL, NOT CUT-AND-DRIED
2. INNOVATIVE
3. NEW/COMPLEX SITUATIONS
4. IMPORTANT AND CRITICAL
5. STRATEGIC
6. LONG-TERM
 DECISION TYPES
NON-PROGRAMMED DECISIONS
{TECHNIQUES USED}
THE TECHNIQUES USED FOR TAKING NON-
PROGRAMMED DECISIONS ARE:
1. JUDGEMENT
2. INTUITION
3. BUSINESS ACUMEN
4. CREATIVITY
5. COMPLEX/SPECIALLY DESIGNED COMPUTER
PROGRAMMES
6. TRAINING EXECUTIVES
• WE MUST REMEMBER THAT WHILE AT THE LOWER
LEVEL, THE DECISIONS ARE PROGRAMMED; AT THE
HIGHER LEVEL THEY ARE UNSTRUCTURED, AS
ILLUSTRATED BELOW:
 Non-Programmed
Management

Broad, Unstructured, Infrequent

Top

and Unstructured
Middle Both Structutured

Lower Routine Structured Frequent

Programmed
Unstructured

Policy
Planning

Tactical
Planning

Operational
Planning

Transaction Structured
Planning
 STEPS IN DECISION-MAKING
PROCESS

1.DETERMINE EXISTENCE OF PROBLEMS AND/OR

OPPORTUNITIES.
2.GENERATE ALTERNATIVE COURSES OF ACTION.
3.ANALYSE/CHOOSE/SELECT A COURSE OF ACTION.
4.IMPLEMENT THE COURSE OF ACTION.
5.MONITOR, FOLLOW UP AND INITIATE COURSE-
CORRECTIVE ACTION.
• THE VARIOUS STEPS IN THE DECISION-MAKING PROCESS
HAVE BEEN BEAUTIFULLY ILLUSTRATED BY GRIFFIN, AS
SHOWN IN THE ACCOMPANYING TABLE.
 THE VARIOUS STEPS IN THE
DECISION-MAKING PROCESS
BY GRIFFIN
STEP DETAIL
1. RECOGNISING AND DEFINING SOME STIMULUS INDICATES
THE SITUATION: THAT A DECISION MUST BE
MADE. THE STIMULUS MAY BE
POSITIVE OR NEGATIVE.

2. IDENTIFYING ALTERNATIVES: BOTH OBVIOUS AND CREATIVE

ALTERNATIVES ARE DESIRED.
IN GENERAL, THE MORE
SIGNIFICANT THE DECISION,
THE MORE ALTERNATIVES
SHOULD BE GENERATED.
 THE VARIOUS STEPS IN THE
DECISION-MAKING PROCESS
BY GRIFFIN
STEP DETAIL
3. EVALUATING ALTERNATIVES: EACH ALTERNATIVE IS
EVALUATED TO DETERMINE ITS
FEASIBILITY, ITS
SATISFACTORINESS AND ITS
CONSEQUENCES.

4. SELECTING THE BEST CONSIDER ALL SITUATIONAL

ALTERNATIVE: FACTORS AND CHOOSE THE
ALTERNATIVE THAT BEST FITS
THE MANAGER’S SITUATION
 THE VARIOUS STEPS IN THE
DECISION-MAKING PROCESS
BY GRIFFIN
STEP DETAIL
5. IMPLEMENTING THE CHOSEN THE CHOSEN ALTERNATIVE IS
ALTERNATIVE: IMPLEMENTED INTO
ORGANISATIONAL SYSTEMS.
6. FOLLOW-UP AND AT SOMETIME IN THE FUTURE,
EVALUATION: THE MANAGER SHOULD
ASCERTAIN THE EXTENT TO
WHICH THE ALTERNATIVE
CHOSEN IN STEP 4 AND
IMPLEMENTED IN STEP 5 HAS
WORKED.
 Identify and Define the
problem
Revise

Develop alternative
solutions

Evaluate alternative
solutions

Revise

Certainty Risk Uncertainty

Conditions Conditions Conditions

Select
Alternative

Revise

Implement
Decision

Evaluate and
Control
 DECISIONS…..

•DECISIONS COULD BE TAKEN BY VARIOUS FUNCTIONAL

EXECUTIVES THAT WOULD INCLUDE:
1.INDIVIDUAL MANAGER
2.CONSULTATIVE DECISIONS – EITHER FORMAL OR
INFORMAL CONSULTATIONS
3.GROUP DECISIONS
 GROUP DECISIONS
1.GROUP DECISIONS BY
• CO-ACTIONS
• TASK GROUPS
• INTERACTING GROUPS
• BRAIN STORMING
• DELPHI TECHNIQUES
• NOMINAL GROUPING TECHNIQUE
• CONSENSUS MAPPING
• SYNECTICS
 DECISION-MAKING TOOLS

•THERE ARE VARIOUS DECISION-MAKING TOOLS, SOME OF

WHICH ARE AS FOLLOWS:
1.PAYOFF MATRIX
2.DECISION TREE
3.DECISION RULES
4.DECISION TABLES
5.WE WOULD DISCUSS THESE, AFTER WE DISCUSS
DECISION-MAKING MODELS.
SCMS-MIS-UNIT-3-B
DECISION-MAKING
J.K.OKE
 UNIT-3-B
DECISION-MAKING

• OVERVIEW OF DM MODELS –
• MODELING DECISION SITUATION.
 THE CLASSICAL MODEL
•EVERY MANAGER HAS TO TAKE DECISIONS
AND, IN A WAY, EVERY MANAGER IS A MODEL
OF DECISION-MAKING HIMSELF.
•HOWEVER, WE WOULD NOTE THE FOLLOWING
DECISION-MAKING MODELS:
1.THE CLASSICAL MODEL
2.THE ADMINISTRATIVE MODEL
3.THE HERBERT SIMON MODEL
 THE CLASSICAL MODEL

• AS PER THE CLASSICAL MODEL OF DECISION-

MAKING, A MANAGER, WHEN CONFRONTED
WITH A DECISION-MAKING SITUATION,
WOULD COLLECT ALL THE INFORMATION
THAT IS REQUIRED FOR THAT ACTIVITY AND
WOULD TAKE A DECISION WHICH WOULD BE
IN THE BEST INTERESTS OF THE
ORGANISATION.
 THE ADMINISTRATIVE MODEL

•UNDER THE ADMINISTRATIVE MODEL, THE

MANAGER IS MORE CONCERNED ABOUT
HIMSELF / HERSELF, RATHER THAN THE
ORGANISATIONAL INTERESTS.
•EXPEDIENCY AND OPPORTUNISM ARE THE
HALLMARKS OF THE ADMINISTRATIVE MODEL.
 THE ADMINISTRATIVE MODEL

•AS SUCH, WHEN CONFRONTED WITH A

DECISION-MAKING SITUATION, THE MANAGER
WOULD COLLECT WHATEVER INFORMATION
COULD BE AVAILABLE AND TAKE A DECISION
WHICH MAY NOT BE IN THE BEST INTERESTS OF
THE ORGANISATION, BUT WOULD CERTAINLY
BE IN THE BEST INTEREST OF THE MANAGER.
•
 THE ADMINISTRATIVE MODEL
•IN ORGANISATIONS, ADMINISTRATIVE
DECISION-MAKING REFERS TO THE PROCESS
USED TO MAKE KEY OR STRATEGIC DECISIONS
BY A SINGLE INDIVIDUAL OR A SMALL GROUP.
• IN DEMOCRATIC SYSTEMS, THESE DECISION-
MAKERS ARE USUALLY EXPECTED TO GET
ADVICE FROM AFFECTED PARTIES AND THEN TO
MAKE A DECISION THAT ADVANCES THE
INTERESTS OF THE WHOLE ORGANISATION.
 THE ADMINISTRATIVE MODEL

•SUCH DECISIONS ARE ALSO EXPECTED TO

RESOLVE THE INTERESTS OF COMPETING
STAKEHOLDERS.
•ADMINISTRATIVE DECISION-MAKERS MAY BE
BUSINESS OWNERS, DEPARTMENT HEADS,
GOVERNMENT OFFICIALS, MAYORS, OR
GOVERNORS.
 THE ADMINISTRATIVE MODEL

•WHILE ADMINISTRATIVE DECISION-MAKING

PROCESSES ARE WIDELY USED AND CAN BE
VERY EFFICIENT, THE EFFECTIVENESS OF THE
PROCESSES DEPENDS UPON THE SKILL, WISDOM
AND CONCERN OF THE DECISION-MAKER(S).
 LET US NOW DISCUSS
THE HERBERT SIMONS MODEL
 THE HERBERT SIMON MODEL

•THE HERBERT SIMON MODEL IS RELATED TO

THE DECISION-MAKING PROCESS.
•THE SIMON MODEL DESCRIBES THE CORE OF
THE DECISION-MAKING PROCESS AND IS
GENERALLY USED AS THE BASIS FOR
DESCRIBING THE DECISION-MAKING PROCESS.
 THE HERBERT SIMON MODEL

• ACCORDING TO THE HERBERT SIMON MODEL,

THE DECISION-MAKING PROCESS CONSISTS OF
THE FOLLOWING THREE INTER-RELATED
PHASES:
1.THE INTELLIGENCE PHASE
2.THE DESIGN PHASE
3.THE CHOICE PHASE
 THE HERBERT SIMON MODEL

• THE THREE PHASES ARE INTERRELATED AS

THERE IS A FLOW OF ACTIVITIES FROM THE
INTELLIGENCE PHASE, TO THE DESIGN PHASE
TO THE CHOICE PHASES. HOWEVER, THERE
CAN/MAY BE A RETURN TO THE PREVIOUS
PHASE, AS ILLUSTRATED HERE UNDER
THE HERBERT SIMON MODEL

Intelligence

Design

Choice
 THE HERBERT SIMON MODEL

INTELLIGENCE PHASE

DESIGN PHASE

CHOICE PHASE
 THE INTELLIGENCE PHASE

•IT CONSISTS OF PROBLEM-FINDING ACTIVITIES

RELATED TO SEARCHING OF THE
OPERATING/BUSINESS ENVIRONMENT, FOR
IDENTIFYING CONDITIONS CALLING FOR
DECISIONS.
•THIS IS IMPERATIVE AS THERE CANNOT BE
ANALYSIS/DESIGN/CHOICE UNLESS THE PROBLEM IS
IDENTIFIED OR CLEARLY FORMULATED/ STATED.
 THE INTELLIGENCE PHASE

•THE INTELLIGENCE PHASE REQUIRES AN

EXTENSIVE AND COMPREHENSIVE DATA BASE.
• IT, THEREFORE, INVOLVES SEARCHING OR
SCANNING OF THE ENVIRONMENT – BOTH
INTERNAL AS WELL AS EXTERNAL – FOR
CONDITIONS, WHICH INDICATE OR SUGGEST A
PROBLEM OR OPPORTUNITY.
 THE INTELLIGENCE PHASE

•THE ACTIVITY OF SEARCH FOR

PROBLEM/OPPORTUNITY IS ILLUSTRATED LATER.
 INTELLIGENCE PHASE
SEARCHING THE ENVIRONMENT
Societal Competitive Organisational
Environment Environment Environment

Intelligence

Problem Opportunity

Risk Risk Reduction

Performance Profit
Demand for
Societal Service
Product
 THE OPERATING ENVIRONMENT
THE ENVIRONMENT, FOR THE
PURPOSE OF DISCUSSION ON THE HERBERT
SIMON MODEL, IS DIVIDED INTO :
1.1. SOCIETAL ENVIRONMENT
2.2. COMPETITIVE ENVIRONMENT
3.3. ORGANISATIONAL
ENVIRONMENT
 THE SOCIETAL ENVIRONMENT

1.THE SOCIETAL ENVIRONMENT WOULD

INCLUDE THE ECONOMIC, LEGAL AND SOCIAL
ENVIRONMENT IN WHICH THE
ORGANISATION OPERATES.
 THE COMPETITIVE ENVIRONMENT

1.THE COMPETITIVE ENVIRONMENT WOULD

INCLUDE UNDERSTANDING AND ANALYSING
THE CHARACTERISTICS, TRENDS AND
BEHAVIOUR OF/AT THE MARKET PLACE IN
WHICH THE ORGANISATION OPERATES.
 THE ORGANISATIONAL
ENVIRONMENT

1.THE ORGANISATIONAL ENVIRONMENT

WOULD INCLUDE THE CAPABILITIES,
STRENGTHS, WEAKNESSES, CONSTRAINTS
AND OTHER FACTORS AFFECTING THE ABILITY
OF THE ORGANISATION TO
DISCHARGE/CARRY OUT/PERFORM ITS
FUNCTIONS/ACTIVITIES.
 SEARCHING & SCANNING
LEADS TO…..
• THE SEARCH/SCANNING OF THE
ENVIRONMENT LEADS TO
IDENTIFICATION/RECOGNITION OF THE
PROBLEM AS REGARDS RISK, PERFORMANCE,
DEMAND FOR PROFIT ETC.,
• &, OPPORTUNITY AS REGARDS RISK
MITIGATION / REDUCTION, PROFITS, SOCIETAL
SERVICE ETC.
 WE THEN MOVE TO…..

• THE SEARCH/SCANNING OF THE

ENVIRONMENT LEADS TO
IDENTIFICATION/RECOGNITION OF THE
PROBLEM/OPPORTUNITY WHICH THEN LEADS
TO THE NEXT PHASES I.E. THE DESIGN AND
CHOICE OF THE DECISION-MAKING PROCESS.
 THE DESIGN PHASE

• THE DESIGN PHASE

INVOLVES/INCLUDES/CONSISTS OF
INVENTING, DEVELOPING AND ANALYSING
LIKELY/PROBABLE/POSSIBLE
ALTERNATIVES/COURSES OF
ACTION/RESPONSES TO THE PROBLEM/
OPPORTUNITY SITUATION.
 THE DESIGN PHASE {USES}

(B)GENERALLY, THE FOLLOWING TYPICAL

REPETITIVE STEPS ARE USED/RESORTED TO:
1.SUPPORT IN UNDERSTANDING THE
PROBLEM. A CORRECT MODEL OF THE
SITUATION NEEDS TO BE CREATED/APPLIED
AND THE ASSUMPTIONS OF THE MODEL
TESTED.
 THE DESIGN PHASE {USES}

(B) SUPPORT FOR GENERATING SOLUTIONS BY:

a.MANIPULATING THE MODEL TO
DEVELOP INSIGHTS.
b.CREATING/USING A DATABASE
RETRIEVAL SYSTEM WHICH MAY HELP IN
GENERATING SOLUTIONS.
 THE DESIGN PHASE {USES}

(B) SUPPORT FOR TESTING FEASIBILITY OF

SOLUTIONS, BY ANALYSING IT IN TERMS OF
THE ENVIRONMENT IT AFFECTS. THE
ENVIRONMENT WOULD INCLUDE, AS STATED
EARLIER, PROBLEM AREAS, THE
ORGANISATION ITSELF, COMPETITORS AND
SOCIETY.
 THE DESIGN PHASE

(B)THE DESIGN PHASE THEN LEADS TO THE

THIRD AND FINAL PHASE OF THE SIMON
MODEL VIZ. THE CHOICE PHASE.
 THE CHOICE PHASE

• THE CHOICE PHASE LEADS TO THE SELECTION OF A

SPECIFIC ALTERNATIVE OR COURSE OF ACTION FROM
THE ONES GENERATED AND CONSIDERED DURING THE
DESIGN PHASE.
• THE DESIGN PHASE REQUIRES THE APPLICATION OF A
CHOICE PROCEDURE AND THE IMPLEMENTATION OF THE
CHOSEN ALTERNATIVE.
 LIMITATIONS OF THE SIMON
MODEL

• WHILE, UNDOUBTEDLY, THE SIMON MODEL

PROVIDES THE CORE OF THE DECISION-MAKING
PROCESS, IT MUST BE NOTED THAT IT DOES NOT
GO BEYOND THE CHOICE PHASE.
 LIMITATIONS OF SIMON MODEL

•THE SIMON MODEL THEREBY EXCLUDES OR

DOES NOT TAKE COGNISANCE OF THE
IMPLEMENTATION AND THE FEEDBACK
ASPECTS, WHICH ARE INSEPARABLE PARTS OF
THE DECISION-MAKING PROCESS, AS IN VOGUE
NOW.
 LIMITATIONS OF THE SIMON
MODEL

•IN THIS CONTEXT, IT WOULD BE BOTH

RELEVANT AND PERTINENT TO KEEP IN MIND
THE FOLLOWING STEPS OF A DECISION-MAKING
PROCESS, SUGGESTED BY THE RUBENSTEIN AND
HERBERTSON MODEL:
 RUBENSTEIN & HERBERTSON
MODEL:

1.RECOGNITION OF PROBLEM OR NEED FOR DECISION.

2.ANALYSIS AND STATEMENT OF ALTERNATIVES.
3.CHOICE AMONG THE ALTERNATIVES.
4.COMMUNICATION AND IMPLEMENTATION OF
DECISION.
5.FOLLOW UP AND FEEDBACK OF RESULTS OF DECISION.
RELEVANCE OF THE SIMON MODEL

•NOTWITHSTANDING THE LIMITATION OF THE

SIMON MODEL, THE FACT REMAINS THAT IT IS
RELEVANT TO THE DESIGN OF INFORMATION
SUPPORT FOR DECISION-MAKING WITHIN THE
MANAGEMENT INFORMATION SYSTEM,
PARTICULARY FOR THE DSS & EIS/ESS.
5. DECISION SUPPORT
SYSTEMS
SCMS-MIS-UNIT-3-C
DECISION-MAKING
J.K.OKE
 UNIT-3-C
DECISION-MAKING

• DECISION MAKING TOOLS: DSS: CONCEPT AND

PHILOSOPHY, CHARACTERISTICS AND COMPONENTS OF
DSS -
 DECISION SUPPORT SYSTEMS
(DSS)
CONCEPT AND PHILOSOPHY

•IN THE 1970S, A NUMBER OF BUSINESS ORGANISATIONS

BEGAN DEVELOPING INFORMATION SYSTEMS, WHICH WERE
SIGNIFICANTLY DIFFERENT FROM THE INFORMATION
SYSTEMS THEN IN USE.
•THE NEW SYSTEMS INVOLVED SPENDING FEWER
RESOURCES – BOTH HUMAN AND FINANCIAL.
 DECISION SUPPORT SYSTEMS
(DSS)
CONCEPT AND PHILOSOPHY
•THE NEW SYSTEMS WERE INTERACTIVE AND WERE
DESIGNED TO HELP SPECIFIC END-USERS, PARTICULARLY THE
MIDDLE MANAGEMENT, TO SUPPORT NON-ROUTINE
DECISION-MAKING.
•DSS FOCUS ON PROBLEMS THAT ARE UNIQUE & RAPIDLY
CHANGING, FOR WHICH THE PROCEDURE FOR ARRIVING
AT SOLUTION MAY NOT BE FULLY PRE-DEFINED IN
ADVANCE.
 DECISION SUPPORT SYSTEMS
(DSS)
CONCEPT AND PHILOSOPHY
•DSS HELP CREATE SCENARIO OR “WHAT-IF-ANALYSIS” &
TRY TO ANSWER QUESTIONS SUCH AS : WHAT WOULD BE
THE IMPACT ON PRODUCTION SCHEDULES IF WE WERE TO
DOUBLE SALES IN THE MONTH OF DECEMBER? OR, WHAT
WOULD HAPPEN TO OUR “ROI” IF A FACTORY SCHEDULE
WERE DELAYED BY / FOR SIX MONTHS?
•DSS UTILISE DATA AND MODELS TO DISCUSS, DIVIDE &
SOLVE, SEMI-STRUCTURED AND UNSTRUCTURED
PROBLEMS.
 DECISION SUPPORT SYSTEMS
(DSS)
CONCEPT AND PHILOSOPHY
•THESE SYSTEMS WERE CALLED THE DECISION SUPPORT
SYSTEMS AND BY THE END OF THE 1980S, WERE EXTENDED
TO GROUPS AND ENTIRE ORGANISATIONS.
• THE DECISION SUPPORT SYSTEMS ARE INTERACTIVE
INFORMATION SYSTEMS THAT RELY ON AN INTEGRATED SET
OF USER-FRIENDLY HARDWARE AND SOFTWARE TOOLS TO
PRODUCE AND PRESENT INFORMATION THAT IS TARGETED
TO SUPPORT MANAGEMENT IN THE DECISION-MAKING
PROCESS.
 DECISION SUPPORT SYSTEMS
(DSS)
CONCEPT AND PHILOSOPHY
•THE DECISION SUPPORT SYSTEMS ASSIST MANAGEMENT
DECISION-MAKING BY COMBINING DATA, SOPHISTICATED
ANALYTICAL MODELS AND USER-FRIENDLY SOFTWARE
INTO A SINGLE POWERFUL SYSTEM THAT CAN SUPPORT
SEMI-STRUCTURED OR UNSTRUCTURED DECISION-
MAKING.
 DECISION SUPPORT SYSTEMS
(DSS)
CONCEPT AND PHILOSOPHY
•THE DECISION SUPPORT SYSTEM IS UNDER USER CONTROL,
FROM EARLY INCEPTION TO FINAL IMPLEMENTATION AND
DAILY USE.
•THE DECISION SUPPORT SYSTEM HELPS TO CLOSE THE
INFORMATION GAP TO ENABLE MANAGERS TO IMPROVE
QUALITY OF THEIR DECISIONS.
•DSS ARE SOMETIMES REFERRED TO AS “BUSINESS
INTELLIGENCE SYSTEMS” BECAUSE THEY FOCUS ON
HELPING USERS MAKE BETTER BUSINESS DECISIONS.
 DECISION SUPPORT SYSTEMS
(DSS)
CONCEPT AND PHILOSOPHY

•WHILE MIS IS CONSIDERED USEFUL FOR STRUCTURED

DECISIONS, DECISION SUPPORT SYSTEM (DSS) IS
CONSIDERED TO BE MORE USEFUL FOR DECISIONS AT THE
TACTICAL/STRATEGIC LEVELS, WHERE DECISION- MAKERS
ARE OFTEN CONFRONTED WITH COMPLEX DECISIONS
WHICH ARE BEYOND THEIR HUMAN ABILITIES TO
SYNTHESIZE PROPERLY THE FACTORS INVOLVED.
 DECISION SUPPORT SYSTEMS
(DSS)
CHARACTERISTICS
1. DSS SHOULD AID THE DECISION-MAKER IN DECISION-
MAKING.
2. DSS SHOULD BE ABLE TO ADDRESS SEMI/UN-
STRUCTURED DECISION-MAKING SITUATIONS.
3. DSS SHOULD SUPPORT DECISION-MAKERS PARTICULARLY
AT TACTICAL/STRATEGIC LEVELS.
 DECISION SUPPORT SYSTEMS
(DSS)
CHARACTERISTICS
4. DSS SHOULD BE ABLE TO CREATE GENERAL PURPOSE
MODELS, SIMULATION CAPABILITIES AND OTHER
ANALYTICAL TOOLS AVAILABLE TO A DECISION-MAKER.
5. DSS SHOULD ENABLE USERS TO USE DSS WITHOUT
ASSISTANCE FROM MIS PROFESSIONALS.
6. DSS SHOULD BE READILY ADAPTED TO MEET
INFORMATION REQUIREMENT FOR ANY DECISION
ENVIRONMENT.
 DECISION SUPPORT SYSTEMS
(DSS)
CHARACTERISTICS
7. DSS SHOULD PROVIDE MECHANISM TO ENABLE RAPID
RESPONSE TO A DECISION-MAKER’S REQUEST FOR
INFORMATION.
8. DSS SHOULD HAVE CAPABILITY TO INTERFACE WITH THE
CORPORATE DATABASE.
9. DSS SHOULD BE FLEXIBLE TO ACCOMMODATE VARIETY OF
MANAGEMENT STYLES.
 DECISION SUPPORT SYSTEMS
(DSS)
CHARACTERISTICS

10. DSS SHOULD FACILITATE COMMUNICATION

BETWEEN/AMONG VARIOUS LEVELS OF DECISION MAKING.
11. DSS SHOULD HAVE IN-BUILT FLEXIBILITY AND ABILITY TO
EVOLVE AS USER SOPHISTICATION GROWS.
12. ITERATIVE METHODS ARE BETTER ADVISED.
 DECISION SUPPORT SYSTEMS
(DSS)
COMPONENTS OF DSS -

•THE DSS HAS THE FOLLOWING MAJOR COMPONENTS:

1. THE DATABASE
2. A MODEL BASE
3. DSS SOFTWARE SYSTEM, &,
4. DSS USER INTERFACE
 DSS COMPONENTS
1. THE DATABASE
•THE DSS DATABASE IS A COLLECTION OF CURRENT OR
HISTORICAL DATA FROM A NUMBER OF APPLICATIONS OR
GROUPS.
•IT MAY BE A SMALL DATABASE RESIDING ON A PC THAT
CONTAINS A SMALL SUBSET OF CORPORATE DATA THAT HAS
BEEN DOWNLOADED & POSSIBLY COMBINED WITH
EXTERNAL DATA.
•IT COULD ALSO BE DATA WAREHOUSE, BEING
CONTINUOUSLY UPDATED BY CORPORATE “TPS” OR WEB
SITE TRANSACTIONS.
 DSS COMPONENTS
1. THE DATABASE

•THE DSS DATABASE IS ORGANISED IN SUCH A MANNER

THAT IT PROVIDES EASY ACCESS FOR A RANGE OF
APPLICATIONS.
•ADEQUATE PRECAUTION IS TAKEN TO ENSURE THE DATA
INTEGRITY WHILE CONTROLLING THE PROCESSING THAT
KEEPS THE DATA CURRENT.
 DSS COMPONENTS
1. THE DATABASE

•DSS DO NOT CREATE OR UPDATE DATA, BUT RATHER USES

LIVE ORGANISATIONAL DATA TO ENABLE DECISIONS TO BE
TAKEN BASED UPON ACTUAL CONDITIONS.
•IT WOULD ALSO BE IMPERATIVE TO REMEMBER THAT
MOST DSS DO NOT HAVE DIRECT ACCESS TO
ORGANISATIONAL DATA BUT USUALLY USE DATA THAT HAVE
BEEN EXTRACTED FROM RELEVANT DATABASES, BOTH
INTERNAL AND EXTERNAL, AND STORED SPECIFICALLY FOR
THE DSS.
 DSS COMPONENTS
2. THE MODEL BASE

A MODEL IS AN ABSTRACT REPRESENTATION THAT

ILLUSTRATES THE COMPONENTS OR RELATIONSHIPS OF A
PHENOMENON. A MODEL CAN BE A PHYSICAL MODEL, A
MATHEMATICAL MODEL OR A VERBAL MODEL.
DSS CAN AND DOES MAKE USE OF DIFFERENT TYPES OF
MODELS. THE MODELS COULD BE BROADLY CLASSIFIED INTO
THREE TYPES AS FOLLOWS:
 MODELS USED IN DSS

BEHAVIOURAL MODEL

MANAGEMENT SCIENCE-BASED MODELS

OPERATIONS RESEARCH MODEL

 1. BEHAVIOURAL MODEL

THE FOCUS OF BEHAVIOURAL MODELS OF DSS IS ON

STUDYING/ UNDERSTANDING THE BEHAVIOUR/TRENDS
AMONGST THE VARIABLES. DECISIONS COULD THEN BE
ARRIVED AT WITH DUE REGARDS TO SUCH BEHAVIOURAL
RELATIONSHIPS.
•TREND ANALYSIS, FORECASTING, CO-RELATION,
REGRESSION ARE EXAMPLES OF THE BEHAVIOURAL MODEL
OF DSS.
 2. MANAGEMENT SCIENCE MODEL

THESE MODELS ARE DEVELOPED BASED UPON THE

PRINCIPLES OF MANAGEMENT, MANAGEMENT
ACCOUNTING AND ECONOMETRICS, AMONG OTHERS.
•BUDGETARY SYSTEMS, COST ACCOUNTING, CAPITAL
BUDGETING, INVENTORY MANAGEMENT ETC. ARE
EXAMPLES OF THE MANAGEMENT SCIENCE MODEL OF DSS
AMONG OTHERS.
 3. OPERATIONS RESEARCH MODEL

(a)OPERATIONS RESEARCH IS BASICALLY APPLICATION OF

MATHEMATICAL FORMULAE FOR ARRIVING AT
OPTIMUM SOLUTIONS. AS SUCH OPERATIONS
RESEARCH MODELS ARE MAINLY MATHEMATICAL
MODELS. THESE MODELS REPRESENT REAL LIFE
PROBLEMS/SITUATIONS IN TERMS OF VARIABLES AND
PARAMETERS EXPRESSED IN ALGEBRAIC EQUATION
FORMS.
 OPERATIONS RESEARCH
TECHNIQUES example

•SOME OF THE EXAMPLES OF THE OPERATIONS

RESEARCH TECHNIQUES USED IN O.R.-BASED MODELS
ARE:
•LINEAR PROGRAMMING,
•ABC ANALYSIS,
•MATHEMATICAL PROGRAMMING TECHNIQUES,
•MATERIAL REQUIREMENT PLANNING
 DSS COMPONENTS
3. THE DSS SOFTWARE SYSTEM
• THE DSS SOFTWARE SYSTEM PERMITS EASY
INTERACTION BETWEEN THE USERS OF THE SYSTEM AND
THE DSS DATABASE AND MODEL BASE.
• THE DSS SOFTWARE SYSTEM MANAGES THE CREATION,
STORAGE AND RETRIEVAL OF MODELS IN THE MODEL
BASE AND INTEGRATES THEM WITH THE DATA IN THE
DSS DATABASE.
• THE DSS SOFTWARE SYSTEM ALSO PROVIDES A GRAPHIC,
EASY TO USE, FLEXIBLE USER INTERFACE THAT SUPPORTS
THE DIALOGUE BETWEEN THE USERS AND THE DSS.
 DSS COMPONENTS
3. THE DSS SOFTWARE SYSTEM

• THE DSS SOFTWARE SYSTEM CONTAINS SOFTWARE

TOOLS THAT ARE USED FOR DATA ANALYSIS.
• IT MAY CONTAIN VARIOUS “OLAP” TOOLS, DATA
MINING TOOLS, OR A COLLECTION OF MATHEMATICAL
& ANALYTICAL MODELS THAT ARE ACCESSIBLE TO THE
DSS USER.
 DSS COMPONENTS
4. THE DSS USER INTERFACE

• THE DSS USER INTERFACE PERMITS / FACILITATES

EASY INTERACTION BETWEEN USERS OF THE
SYSTEM& THE DSS SOFTWARE TOOLS.
• MANY DSS TODAY HAVE WEB INTERFACES TO TAKE
ADVANTAGE OF GRAPHICAL DISPLAYS,
INTERACTIVITY & EASE OF USE.
 BEFORE WE CLOSE OUR
DISCUSSIONS ABOUT DSS,
LET US COMPARE MIS & DSS
 MIS & DSS COMPARISON
MIS
• THE FOCUS IS ON STRUCTURED
TASKS AND ROUTINE DECISIONS.
• IDENTIFIES INFORMATION
REQUIREMENT.
DSS
• FOCUS IS ON SEMI
/UNSTRUCTURED TASKS, WHICH
REQUIRE MANAGERIAL
JUDGEMENT.
• ESTABLISHES TOOLS TO BE USED
FOR DECISION PROCESS.
 MIS & DSS COMPARISON

MIS DSS
• EMPHASIS IS ON DATA • EMPHASIS IS ON
STORAGE. DATA MANIPULATION.
• DELIVERS SYSTEMS BASED • FOLLOWS ITERATIVE PROCESS
HENCE CURRENT DATA CAN BE
ON FROZEN REQUIREMENT.
USED.
 MIS & DSS COMPARISON
MIS
• PROVIDES ONLY INDIRECT
ACCESS TO DATA BY MANAGERS.
• RELIANCE ON COMPUTER
EXPERT.
• EMPHASIS IS ON EFFICIENCY.
DSS
• MANAGERS HAVE DIRECT ACCESS
TO DATA.
• RELIANCE ON MANAGERIAL
JUDGEMENT.
• EMPHASIS IS ON EFFECTIVENESS
 MIS & DSS COMPARISON

MIS DSS
• ACCESS TO DATA POSSIBLY • DIRECT ACCESS TO COMPUTER
REQUIRING A 'WAIT' FOR AND DATA, HENCE NO WAITING.
MANAGER'S TURN. (THE “197”
SYNDROME)
• MIS MANAGER MAY NOT
• MANAGER KNOWS THE NATURE
OF DECISION AND DECISION-
COMPLETELY UNDERSTAND THE
MAKING ENVIRONMENT.
NATURE OF DECISION.
GDSS
 GDSS
• EARLIER WE HAVE DISCUSSED THE VARIOUS ASPECTS OF
DECISION SUPPORT SYSTEM (DSS), WHERE THE RESPECTIVE
EXECUTIVE/DECISION-MAKER ARRIVES AT EFFECTIVE
DECISIONS BY USING A SPECIALLY DEVELOPED DECISION
SUPPORT SYSTEM FOR THE EXECUTIVE/DECISION-MAKER
CONCERNED. THUS, THE DSS IS DESIGNED FOR AND USED
MORE BY THE INDIVIDUAL DECISION-MAKER.
• IT WAS HOWEVER FELT THAT IN THE CONTEMPORARY
BUSINESS ENVIRONMENT, DECISION-MAKERS HAVE TO
INCREASINGLY WORK IN GROUPS AS GROUP-WORKING AND
GROUP DECISION-MAKING HAS MORE OR LESS BECOME A
NORM & ACCEPTED PRACTICE, DUE TO ITS ADVANTAGES.
 GROUP WORKING & GROUP-
DECISION-MAKING ADVANTAGES
(a)MORE COMPREHENSIVE CONSIDERATION OF THE
PROBLEMS AND RELATED ISSUES.
(b)BETTER GROUP UNDERSTANDING OF THE PROBLEM AND
RATIONALE FOR THE DECISION.
(c)REDUCED LIKELIHOOD OF “QUIBBLING” USING “20/20
HINDSIGHT”.
(d)GREATER GROUP COMMITMENT TO THE DECISION.
(e)IMPROVED COMMUNICATION TO/WITH THE
IMPLEMENTERS ENSURING BETTER IMPLEMENTATION.
 GDSS GROUP DECISION SUPPORT
SYSTEM (GDSS).
•HENCE, THE DSS APPLICATION WAS SUITABLY
EXTENDED/EXPANDED TO FACILITATE GROUP DECISION
ENVIRONMENT AND THE DSS FOR A GROUP CAME TO BE
KNOWN AS THE GROUP DECISION SUPPORT SYSTEM
(GDSS).
•IT IS ALSO REFERRED TO AS A GROUP SUPPORT SYSTEM
OR A COMPUTERISED COLLABORATIVE WORK SYSTEM
(CCWS). WE WOULD, HOWEVER, REFER TO THIS
EXTENDED/EXPANDED FORM OF DSS AS THE GDSS.
 GDSS OR
COMPUTERISED COLLABORATIVE
WORK SYSTEM (CCWS)
•UNDER THE GDSS ENVIRONMENT, THE MEMBERS OF THE
GROUP UTILISE THE DSS AS A GROUP AND THE USER-
INTERFACE IS EXPANDED TO INCLUDE THE COMPUTERS
WHICH ARE SUITABLY CONNECTED/ NETWORKED.
•IN THIS WAY, UNDER THE GDSS, MEMBERS OF THE GROUP
CAN COMMUNICATE USING THEIR COMPUTERS WITH DSS
OR WITH OTHER MEMBERS OF THE GROUP TO FACILITATE
OPTIMAL DECISION- MAKING.
•
 GDSS

• WE HAVE DISCUSSED WHAT A GDSS IS LIKE. LET US NOW

NOTE THE SPECIFIC DEFINITION OF GDSS.
• ACCORDING TO DESANCTIS AND GALLUPE (1987),
•“GDSS IS AN INTERACTIVE COMPUTER-BASED SYSTEM
THAT FACILITATES THE SOLUTION OF UNSTRUCTURED
PROBLEMS BY A SET OF DECISION-MAKERS WORKING
TOGETHER AS A GROUP”.
 GDSS COMPONENTS

• THE GDSS COMPONENTS ARE :

• 1. HARDWARE
• 2. SOFTWARE
(GROUPWARE / WORKGROUP SOFTWARE)
• 3. PEOPLE & PROCEDURE
• 4. COMMUNICATION TECHNOLOGY.
 GDSS

•AS THE GDSS IS A GROUP DECISION-FACILITATOR AND

EXTENSION/EXPANSION OF DSS,
•MOST OF THE FEATURES/CHARACTERISTICS OF THE GDSS
ARE SIMILAR TO THAT OF THE DSS.
•
 GDSS {IMPORTANT}

•IN ADDITION, GDSS MUST PROVIDE FOR –

(a)ANONYMOUS INPUTS WITHOUT IDENTIFYING THE SOURCE OF
INPUTS TO ENABLE GROUP DECISION-MAKERS TO CONCENTRATE ON
THE MERITS OF THE INPUT WITHOUT CONSIDERING WHO GAVE IT.
(b)PARALLEL COMMUNICATION(S) TO ENABLE EVERY GROUP MEMBER
TO ADDRESS ISSUES OR MAKE COMMENTS/SUGGESTIONS
SIMULTANEOUSLY.
(c)AUTOMATED RECORD KEEPING BY ANONYMOUSLY RECORDING
EACH COMMENT THAT IS ENTERED INTO THE PC BY THE GROUP
MEMBER, FOR FUTURE REVIEW AND ANALYSIS.
 GDSS

• THE SUCCESS OF GDSS WOULD DEPEND UPON THE

QUALITY OF THE MEETINGS/DISCUSSIONS/ INTERFACE
BEING “PRODUCTIVE”, ENSURING MORE EFFECTIVE AND
EFFICIENT USE OF TIME AND ABILITY OF THE GROUP-
MEMBERS TO PRODUCE THE DESIRED RESULTS IN FEWER
MEETINGS/INTERFACES.
•
GDSS {NECESSARY CONDITION}

• FOR GDSS TO BE SUCCESSFUL, IT WOULD BE NECESSARY

TO ENSURE :
1. IMPROVED PRE-PLANNING.
2. INCREASED PARTICIPATION.
3. OPEN, COLLABORATIVE MEETING(S) ATMOSPHERE.
4. CRITICISM-FREE IDEA GENERATION (BRAIN-STORMING).
5. IDEA, ORGANISATION AND EVALUATION.
 GDSS

• FOR THIS, FOLLOWING ELEMENTS WOUL BE NECESSARY:

6. SETTING PRIORITIES AND MAKING DECISIONS
ACCORDINGLY.
7. DOCUMENTATION/RECORD-KEEPING OF MEETINGS.
8. ACCESS TO EXTERNAL INFORMATION, IF AND WHEN
REQUIRED.
9. PRESERVATION OF 'ORGANISATION MEMORY'.
WHILE WE HAVE DISCUSSED
DSS, I WOULD ALSO ADD
EIS/ESS, ES & AI-BASED
SYSTEMS
 EIS / ESS
• EIS/ESS IS DEVELOPED TO SUPPORT DECISION-MAKING
ACTIONS/PROCESSES AT THE TOP
EXECUTIVE/MANAGEMENT LEVEL. EIS/ESS IS USED BY THE
TOP EXECUTIVES AS THEY REQUIRE SPECIALISED SUPPORT
WHEN/WHILE MAKING STRATEGIC DECISIONS. EIS/ESS IS
ALSO REQUIRED AND USED AT FAIRLY SENIOR LEVEL
INCLUDING MEMBERS OF THE BOARD OF DIRECTORS AND
EXECUTIVES WITH THE TITLES OF CHIEF EXECUTIVE OFFICER
(CEO), CHIEF OPERATING/OPERATIONS OFFICER (COO),
CHIEF FINANCE OFFICER (CFO) AND THE LIKE.
 EIS / ESS

•WHILE, EARLIER, MOST OF THE TOP EXECUTIVES WERE

RELUCTANT USERS OF INFORMATION TECHNOLOGY, THE
NEW GENERATION OF TECH-SAVVY TOP EXECUTIVES IS NOT
ONLY OPEN TO, BUT ACTUALLY EXPECT, SUPPORT FROM
COMPUTER-BASED INFORMATION SYSTEMS LIKE EIS/ESS.
ACCORDINGLY, MANY ORGANISATIONS HAVE GONE IN FOR
DEVELOPMENT OF EIS/ESS TO ASSIST TOP EXECUTIVES
DECISION-MAKING.
 EIS / ESS
•AN EIS IS “A COMPUTER-BASED SYSTEM THAT SERVES THE
INFORMATION NEEDS OF THE TOP EXECUTIVES. IT
PROVIDES RAPID ACCESS TO TIMELY INFORMATION AND
DIRECT ACCESS TO MANAGEMENT REPORTS. IT IS VERY
USER-FRIENDLY AND IS SUPPORTED BY GRAPHICS,
PROVIDING EXCEPTION REPORTING AND DRILL DOWN
CAPABILITIES. IT CAN ALSO BE EASILY CONNECTED WITH
ON-LINE INFORMATION SERVICES AND ELECTRONIC MAIL”.
• (DRILL DOWN CAPABILITY ENABLES THE USERS TO BREAK
DOWN DATA IN DETAILS & IDENTIFY BOTH PROBLEMS AND
OPPORTUNITIES).
 EIS / ESS
•AN EIS IS “A COMPUTER-BASED INFORMATION SYSTEM
THAT COMBINES THE DECISION-MAKER'S IMAGINATION
AND JUDGEMENT WITH THE COMPUTER'S ABILITY TO
STORE, RETRIEVE, MANIPULATE, COMPUTE AND REPORT
INTERNAL AND EXTERNAL INFORMATION”.
• AN ESS IS “A COMPREHENSIVE EXECUTIVE SUPPORT
SYSTEM THAT GOES BEYOND THE EIS TO INCLUDE
COMMUNICATIONS, OFFICE AUTOMATION, ANALYSIS
SUPPORT AND INTELLIGENCE”.
 EIS / ESS CAPABILITIES

1. IT PROVIDES ACCESS TO AGGREGATED/MACRO/GLOBAL

INFORMATION.
2. IT ENABLES TO USE EXTERNAL DATA EXTENSIVELY.
3. IT ENABLES TO ADDRESS AD HOC QUERIES/ANALYSIS.
4. IT INCORPORATES GRAPHICS AND TEXT IN THE SAME
DISPLAY TO PROVIDE BETTER VIEW.
5. IT SHOWS TRENDS, RATIOS AND DEVIATIONS.
6. IT PROVIDES ACCESS TO HISTORICAL AS WELL AS THE
LATEST DATA.
 EIS / ESS CAPABILITIES
7. IT HIGHLIGHTS PROBLEM INDICATORS AND SUPPORTS
OPEN-ENDED PROBLEM EXPLANATION WITH WRITTEN
INTERPRETATIONS.
8. IT IS ORGANISED AROUND CRITICAL SUCCESS FACTORS
AND PROVIDES “MANAGEMENT BY EXCEPTION”
REPORTS.
9. THE INFORMATION CAN BE PRESENTED IN A
HIERARCHICAL STRUCTURE, THEREBY FACILITATING
DETAILED INFORMATION AT VARIOUS LEVELS, ALONG
WITH “DRILL DOWN” CAPABILITIES.
 EIS / ESS CAPABILITIES

10. IT FILTERS, COMPRESSES AND TRACKS CRITICAL DATA

AND ALSO PROVIDES FORECASTING CAPABILITY.
11. IT CAN UTILISE HYPERTEXT AND HYPERMEDIA.
12. IT PROVIDES A GENERALISED COMPUTING AND
TELECOMMUNICATIONS CAPACITY THAT CAN BE APPLIED TO
A CHANGING ARRAY OF PROBLEMS.
 EIS / ESS BENEFITS

1. FACILITATES THE ATTAINMENT OF ORGANISATIONAL

OBJECTIVES.
2. FACILITATES ACCESS TO INFORMATION BY INTEGRATING
MANY SOURCES OF DATA AND PROVIDES BROAD, HIGHLY
AGGREGATED INFORMATION. THIS, IN TURN, FACILITATES
BROAD, AGGREGATED 'PERSPECTIVE' AND 'CONTEXT’.
3. IMPROVES THE USERS 'PRODUCTIVITY' BY ENABLING
MORE EFFECTIVE DECISION-MAKING.
 EIS / ESS BENEFITS

4. ALLOWS THE ANTICIPATION OF

PROBLEMS/OPPORTUNITIES AND FACILITATES PROACTIVE
RATHER THAN A REACTIVE RESPONSE.
5. INCREASES COMMUNICATION CAPABILITY AND QUALITY.
6. FACILITATES BETTER STRATEGIC PLANNING AND CONTROL.
7. FACILITATES FINDING THE CAUSE OF A PROBLEM IN A
“ROOT CAUSE ANALYSIS” MODE RATHER THAN 'FIX-IT'
MODE.
 EIS / ESS BENEFITS

8. MEETS THE NEEDS OF THE EXECUTIVES IN A TIME-

EFFECTIVE AND TIME-EFFICIENT MANNER.
9. THE EIS/ESS PROVIDES COMPETITIVE ADVANTAGE.
10. EIS/ESS ENCOURAGES THE DEVELOPMENT OF A MORE
OPEN AND ACTIVE INFORMATION CULTURE, AS EIS/ESS
IMPROVES THE USE OF THE STRATEGIC INFORMATION
RESOURCE THAT ARE AT THE DISPOSAL OF THE
ORGANISATION FOR WORKING OUT BOTH STRATEGIC
AND TACTICAL DECISIONS.
 EIS / ESS BENEFITS
11. EIS/ESS ALSO HELPS IN PROVIDING ANSWERS TO
QUESTIONS LIKE:
(a)WHAT BUSINESS THE ORGANISATION SHOULD BE IN?
(b)WHAT ARE THE COMPETITORS DOING?
(c)WHAT NEW ACQUISITIONS/ACTIVITIES WOULD
PROTECT THE ORGANISATION FROM BUSINESS
CYCLES/BUSINESS SWINGS?
(d)WHICH UNITS SHOULD THE ORGANISATION
DIVERT/SPIN OFF TO RAISE CASH FOR FURTHER
EXPANSION/DIVERSIFICATION, ACQUISITION?
 EXPERT/KNOWLEDGE-BASED
SYSTEMS
• EXPERT SYSTEMS ARE AMONG THE MOST EXCITING
COMPUTER APPLICATIONS TO EMERGE DURING THE 1980S.
•THE FIRST ACCLAIMED COMMERCIAL 'EXPERT SYSTEM',
DEC'S 'XCON', WAS PUT INTO USE IN 1981.
•THE 1990S WITNESSED INCREASING ACCEPTANCE AND
APPLICATION/USE OF EXPERT SYSTEM TO TRANSFORM THE
WAY CORPORATIONS DEVELOPED THEIR SOFTWARE AND
USED COMPUTERS FOR MANAGING THEIR BUSINESS.
•
 EXPERT/KNOWLEDGE-BASED
SYSTEMS
•THE ES TECHNOLOGY BASICALLY DERIVES FROM THE
RESEARCH DISCIPLINE OF ARTIFICIAL INTELLIGENCE, A
BRANCH OF COMPUTER SCIENCE CONCERNED WITH THE
DESIGN AND IMPLEMENTATION OF PROGRAMMES WHICH
ARE CAPABLE OF EMULATING HUMAN COGNITIVE SKILLS
SUCH AS PROBLEM SOLVING, VISUAL PERCEPTION AND
LANGUAGE UNDERSTANDING.
• EXPERT SYSTEM MIMICS HUMAN EXPERTISE IN A
NARROW DOMAIN TO SOLVE SPECIFIC PROBLEMS IN A
WELL-DEFINED AREA.
 EXPERT/KNOWLEDGE-BASED
SYSTEMS DEFINITIONS

•ACCORDING TO PETER JACKSON, “AN EXPERT SYSTEM IS A

COMPUTER PROGRAMME THAT REPRESENTS AND REASONS
WITH KNOWLEDGE OF SOME SPECIALIST SUBJECT WITH A
VIEW TO SOLVING PROBLEMS OR GIVING ADVICE”.
• AN EXPERT SYSTEM, ACCORDING TO HOSSEIN BIDGOLI, “IS
A SERIES OF COMPUTER PROGRAMMES THAT ATTEMPT TO
MIMIC HUMAN THOUGHT, BEHAVIOUR IN A SPECIFIC AREA
THAT HAS SUCCESSFULLY BEEN SOLVED BY HUMAN
EXPERTS”.
 EXPERT/KNOWLEDGE-BASED
SYSTEMS DEFINITIONS
• ROBERT BOWERMAN AND DAVID GLOVER HAVE DEFINED
AN EXPERT SYSTEM AS, “HIGHLY SPECIALISED COMPUTER
SYSTEMS CAPABLE OF SIMULATING THAT ELEMENT OF A
HUMAN SPECIALIST'S KNOWLEDGE AND REASONING THAT
CAN BE FORMULATED INTO KNOWLEDGE CHUNKS,
CHARACTERISED BY A SET OF FACTS AND HEURISTIC RULES”.
(HEURISTIC RULES ARE RULES OF THUMB ACCUMULATED BY
A HUMAN EXPERT THROUGH INTENSIVE PROBLEM-SOLVING
IN THE DOMAIN OF A PARTICULAR TASK).
 EXPERT/KNOWLEDGE-BASED
SYSTEMS DEFINITIONS
•ACCORDING TO BRUCE BUCHANAN AND REID SMITH, AN EXPERT
SYSTEM IS A COMPUTER PROGRAMME THAT –
(a)REASONS WITH DOMAIN-SPECIFIC KNOWLEDGE THAT IS SYMBOLIC
AS WELL AS NUMERICAL.
(b)USES DOMAIN-SPECIFIC METHODS THAT ARE HEURISTIC (PLAUSIBLE)
AS WELL AS FOLLOWING PROCEDURES THAT ARE ALGORITHMIC
(CERTAIN).
(c)PERFORMS WELL IN THE PROBLEM AREA.
(d)EXPLAINS OR MAKES UNDERSTANDABLE BOTH WHAT IT KNOWS
AND THE REASONS FOR ITS ANSWERS.
(e)RETAINS “FLEXIBILITY”.
 EXPERT/KNOWLEDGE-BASED
SYSTEMS CAPABILITIES
•TO BE REALLY EFFECTIVE AND IMPROVE THE QUALITY OF
PROBLEM-SOLVING, AN EXPERT SYSTEM SHOULD POSSESS
THE FOLLOWING CAPABILITIES:
1. CAPTURING OF EXPERTISE.
2. CODIFYING THE EXPERTISE.
3. DUPLICATING AND TRANSFERRING THE EXPERTISE.
4. SAVING THE HUMAN EXPERT'S TIME.
5. SAVING ON MAINTENANCE AND UPDATING OF THE
KNOWLEDGE BASE.
ARTIFICIAL INTELLIGENCE-BASED
(AI-BASED)SYSTEMS

•ARTIFICIALINTELLIGENCE (AI, FOR SHORT) BEGAN IN

EARNEST WITH THE EMERGENCE OF THE COMPUTERS
DURING THE LATE 1940S.
•IT WAS THE ABILITY OF THESE MACHINES TO STORE LARGE
AMOUNT OF DATA AND PROCESS IT INTO INFORMATION AT
VERY HIGH SPEEDS, HITHERTO UNIMAGINABLE, THAT GAVE
RESEARCHERS, THE VISION OF BUILDING SYSTEMS WHICH
COULD IMITATE/EMULATE SOME, IF NOT ALL, HUMAN
ABILITIES.
•
ARTIFICIAL INTELLIGENCE-BASED
(AI-BASED)SYSTEMS
• WHILE SOME GROUND WORK HAD ALREADY BEEN
INITIATED EARLIER, IT WAS NOT UNTIL THE 1980S THAT AI
RECEIVED POPULAR ECONOMIC AND MANAGERIAL
ACCLAIM.
• IT WAS DURING THIS PERIOD THAT AI WENT THROUGH
THE TRANSITION FROM A PRIMARY RESEARCH AREA TO
POTENTIAL COMMERCIAL APPLICATIONS.
• IT WAS ONLY THEN THAT AI WAS ACCEPTED AS AN
EMERGING TECHNOLOGY AND AS SUCH ATTRACTED
CONSIDERABLE ATTENTION.
ARTIFICIAL INTELLIGENCE-BASED
(AI-BASED)SYSTEMS

• ACCORDING TO GEORGE LUGER AND WILLIAM

STUBBLEFIELD
•“AI IS A SERIES OF RELATED TECHNOLOGIES THAT
ATTEMPT TO SIMULATE AND REPRODUCE HUMAN
BEHAVIOUR, INCLUDING THINKING, SPEAKING, FEELING
AND REASONING”.
ARTIFICIAL INTELLIGENCE-BASED
(AI-BASED)SYSTEMS
–ACCORDING TO HOSSEIN BIDGOLI
• “AI IS A BRANCH OF COMPUTER SCIENCE CONCERNED
WITH THE STUDY AND CREATION OF COMPUTER
SYSTEMS THAT EXHIBIT SOME FORM OF INTELLIGENCE:
SYSTEMS THAT LEARN NEW CONCEPTS AND TASKS,
SYSTEMS THAT CAN REASON AND DRAW USEFUL
CONCLUSIONS ABOUT THE WORLD AROUND US,
SYSTEMS THAT CAN UNDERSTAND NATURAL
LANGUAGES AND PERCEIVE AND COMPREHEND A
VISUAL SCENE AND SYSTEMS THAT PERFORM OTHER
TYPES OF FEATS THAT REQUIRE HUMAN TYPES OF
INTELLIGENCE”.
 WHAT IS CORE OF
ARTIFICIAL INTELLIGENCE-
BASED (AI-BASED)SYSTEMS
•UNDERSTAND WHAT ‘COMMON SENSE’ IS.
•UNDERSTAND 'FACTS' AND RELATIONSHIPS AMONG
'FACTS'.
•BE ABLE TO MANIPULATE 'QUALITATIVE' DATA.
•BE ABLE TO DEAL WITH EXCEPTIONS AND DISCONTINUITY.
•BE ABLE TO INTERFACE WITH HUMANS IN A “FREE-
FORMAT” FASHION.
•BE ABLE TO DEAL WITH NEW SITUATIONS BASED ON
PREVIOUS LEARNING.
 AI ENCOMPASSES(SURROUNDS)
AREAS LIKE….

• EXPERT SYSTEMS
•FUZZY LOGIC
•INTELLIGENT AGENTS
•NATURAL LANGUAGE PROCESSING
•NEURAL NETWORKS / LEARNING SYSTEMS
•ROBOTICS
•SPEECH RECOGNITION / VISION-RECOGNISED SYSTEMS
 AI-APPLICATIONS

• MANUFACTURING/PRODUCTION PLANNING AND

SCHEDULING
• PROJECT MANAGEMENT
• FACTORY MANAGEMENT
• SALES, DISTRIBUTION AND FIELD SERVICES
• DIAGNOSIS AND TROUBLE-SHOOTING
• CRIMINOLOGY (MODUS OPERANDI)
• GEOLOGY (POTENTIAL DRILLING/OIL EXPLORATION SITES)
 AI-APPLICATIONS

• FINANCIAL MANAGEMENT
• CURRENCY/INTEREST RATES SWAPS
• PORTFOLIO MANAGEMENT
• ASSET LIABILITY MANAGEMENT
• READING/INTERPRETING FINANCIALS
 SCMS-MIS-UNIT-3-D
DECISION-MAKING TOOLS
(PAY-OFF MATRIX/DECISION
TREE/DECISION TABLE)
J.K.OKE
 DECISION MAKING
• GOOD MORNING, FRIENDS.
• WHILE DISCUSSING UNIT-3,
• WE HAVE SO FAR DISCUSSED:
• WHAT IS DECISION,
• TYPES OF DECISIONS,
• DECISION-MAKING ENVIRONMENTS, &,
• DECISION-MAKING MODELS
 UNIT-3-D
DECISION-MAKING
• IN TODAY’S SESSION, WE WOULD DISCUSS
CERTAIN DECISION-MAKING TOOLS LIKE:
• PAYOFF MATRIX,
• DECISION TREE, AND,
• DECISION TABLES,
LET US BEGIN WITH PAY-OFF MATRIX
 PAY-OFF MATRIX
• “PAY-OFF MATRIX” IS ONE OF THE MORE COMMONLY USED
AND ESSENTIAL QUANTITATIVE TECHNIQUES OF DECISION-
MAKING.
•IT HELPS IN SUMMARISING THE INTERACTIONS OF VARIOUS
ALTERNATIVE ACTIONS AND EVENTS.
•THE PAY-OFF MATRIX TAKES INTO ACCOUNT THE
‘PROBABILITY’ (I.E. THE DEGREE OF LIKELIHOOD THAT A
PARTICULAR EVENT WOULD OCCUR).
•PROBABILITIES RANGE IN VALUE FROM 0 (NO CHANCE OF
OCCURRING) TO 1 (CERTAIN CHANCE OF OCCURRING).
 PAY-OFF MATRIX
• THE PROBABILITIES ARE USUALLY EXPRESSED IN TERM OF
PERCENTAGES, OR AS THE NUMBER OF TIMES THE EVENT IS APT
TO OCCUR IN A HUNDRED TRIALS.
• A PAY-OFF MATRIX IS PREPARED BY USING PROBABILITIES,
WHICH PROVIDES THE DECISION-MAKER WITH QUANTITATIVE
MEASURES OF THE PAY-OFF FOR EACH POSSIBLE CONSEQUENCE
AND FOR EACH ALTERNATIVE UNDER CONSIDERATION.
•THIS IS KNOWN AS EXPECTED VALUE (EV).
•POSITIVE PAYOFF IMPLIES PROFIT,&,
•NEGATIVE PAY-OFF IMPLIES LOSS.
 PAY-OFF MATRIX {EXAMPLE}
•LET US ILLUSTRATE THE USE OF PAY-OFF BY THE FOLLOWING
EXAMPLE:
• A BUSINESSMAN WANTS TO INVEST ` 1,00,000 IN A NEW BUSINESS.
•HE HAS IDENTIFIED THREE ALTERNATIVES –
•ACTIVITY A, B AND C.
•THE BUSINESSMAN HAS WORKED OUT THE PROBABILITIES OF HIS
RETURN ON INVESTMENT.
•HE HAS ESTIMATED THAT THERE IS A PROBABILITY OF 0.40 THAT
SALES WILL BE HIGH AND A PROBABILITY OF 0.60 THAT THE SALES
WILL BE LOW.
 PAY-OFF MATRIX
ALTERNATIVES HIGH SALES LOW SALES
(PROBABILITY 0.40) (PROBABILITY 0.60)
ACTIVITY “A” + ` 45,000 – ` 10,000
ACTIVITY “B” + ` 80,000 – ` 25,000
ACTIVITY “C” + ` 30,000 – ` 5,000
 PAY-OFF MATRIX
•
FROM THE PAY-OFF MATRIX, THE EXPECTED VALUE OF THE INVESTMENT
IN ACTIVITY ‘A’ WILL BE AS FOLLOWS:
• EV = 0.40 (45,000) + 0.60 (– 10,000)
• = 18,000 – 6,000
• = 12,000
•THE EXPECTED VALUE FOR ACTIVITY ‘B’ WILL BE
• EV = 0.40 (80,000) + 0.60 (– 25,000)
• = 32,000 – 15,000
• = 17,000
•
 PAY-OFF MATRIX
• THE EXPECTED VALUE FOR ACTIVITY ‘C’
WILL BE

•
EV = 0.40 (30,000 + 0.60 (– 5,000)
• = 12,000 – 3,000
• = 9,000
 SO, TO SUMMARISE….
•THE EXPECTED VALUE FOR ACTIVITY ‘A’ WILL BE
12,000
•THE EXPECTED VALUE FOR ACTIVITY ‘B’ WILL BE
17,000
•THE EXPECTED VALUE FOR ACTIVITY ‘C’ WILL BE 9,000
•THE PAY-OFF MATRIX SHOWS THAT THE ACTIVITY ‘B’
CAN GIVE HIM THE BEST POSSIBLE RETURN, AMONG
THE THREE ALTERNATIVES.
 PAY-OFF MATRIX { LIMITATION}
• IT MUST, HOWEVER, BE REMEMBERED THAT THE PAY-OFF MATRIX HAS
AN OBVIOUS WEAKNESS.
•IT IS DEPENDENT ON THE DECISION-MAKER’S JUDGEMENT OF THE
POSSIBLE OUTCOMES FOR EACH ALTERNATIVE AND ALSO THE VALUES
THE DECISION-MAKER ASSIGNS TO EACH.
• AT THE SAME TIME, IT MUST ALSO BE REMEMBERED THAT THE PAY-OFF
MATRIX FORCES THE DECISION-MAKER TO MAKE A FIRM JUDGEMENT
ABOUT WHAT HE THINKS MAY HAPPEN AND THE WORTH TO HIM OF
THOSE OUTCOMES.
• THE PAY-OFF MATRIX DOES NOT MAKE A DECISION BUT IT DOES FORCE
THE DECISION-MAKER TO BE MORE REALISTIC ABOUT POSSIBLE
OUTCOMES.
DECISION TREE
 DECISION TREE
• IN BUSINESS LIFE, WHEN WE TAKE INVESTMENT
DECISIONS IN PRESENT,
• THEY HAVE FUTURE IMPLICATIONS.
• SUCH DECISIONS INVOLVE A SEQUENCE OF DECISIONS
OVER TIME.
• HENCE, WE CANNOT / SHOULD NOT VIEW
INVESTMENT DECISIONS AS ISOLATED PERIOD
COMMITMENTS,
• BUT AS LINKS IN A CHAIN OF FUTURE COMMITMENTS.
 DECISION TREE
• IT IS ARGUED THAT
• “SINCE PRESENT CHOICES MODIFY FUTURE
ALTERNATIVES,
• INDUSTRIAL ACTIVITY CANNOT BE REDUCED
TO A SINGLE DECISION &
• MUST BE VIEWED AS A SEQUENCE OF
DECISIONS EXTENDING FROM THE PRESENT
TIME INTO THE FUTURE”.
 DECISION TREE
• AN ANALYTICAL TECHNIQUE TO HANDLE THE
SEQUENTIAL DECISIONS IS TO EMPLOY
DECISION TREES.
• IT IS KNOWN AS “DECISION TREE”, AS
• THE SEQUENCE OF DECISIONS IS MAPPED
OUT OVER TIME IN A FORMAT SIMILAR TO
THE BRANCHES OF A TREE.
 DECISION TREE
• A DECISION TREE IS A TREE-LIKE FLOW CHART THAT
LISTS OUT EACH POSSIBLE OUTCOME OF A
DECISION,AND HELPS TO CHOOSE BETWEEN SEVERAL
COURSES OF ACTION.

• A DECISION TREE IS A GRAPHIC DISPLAY OF THE

RELATIONSHIP BETWEEN A PRESENT DECISION &
FUTURE EVENTS, FUTURE DECISIONS & THEIR
CONSEQUENCES.
 DECISION TREE
• A DECISION TREE IS A MAP OF THE POSSIBLE
OUTCOMES OF A SERIES OF RELATED CHOICES. ...
• A CHANCE NODE, REPRESENTED BY A CIRCLE,
SHOWS THE PROBABILITIES OF CERTAIN RESULTS.
• A DECISION NODE, REPRESENTED BY A SQUARE,
SHOWS A DECISION TO BE MADE, AND,
• AN END NODE SHOWS THE FINAL OUTCOME OF A
DECISION PATH.
LET US SEE HOW TO CREATE
DECISION TREE
STEPS CONSIDERED WHILE CONSTRUCTING
DECISION TREE
• WHILE CONSTRUCTING & USING DECISION
TREE, SOME IMPORTANT STEPS SHOULD BE
CONSIDERED:
• DEFINE INVESTMENT
• IDENTIFY DECISION ALTERNATIVES
• DRAW A DECISION TREE
• ANALYSE DATA
 HOW TO CREATE A DECISION TREE:
ALTERNATE APPROACH…..
• WE FIRST MAKE A LIST OF ATTRIBUTES THAT WE CAN
MEASURE
– THESE ATTRIBUTES (FOR NOW) MUST BE DISCRETE
• WE THEN CHOOSE A TARGET ATTRIBUTE THAT WE WANT
TO PREDICT
• THEN CREATE AN EXPERIENCE TABLE THAT LISTS WHAT
WE HAVE SEEN IN THE PAST
 USEFULNESS OF DECISION TREE
• DECISION TREE CAN BE USED TO HELP
PREDICT THE FUTURE
• THE TREE IS EASY TO UNDERSTAND
• DECISION TREE WORKS MORE EFFICIENTLY
WITH DISCRETE ATTRIBUTES
• THE TREE MAY SUFFER FROM ERROR
PROPAGATION
 USEFULNESS OF DECISION TREE
• THE DECISION TREE TECHNIQUE IS EXTREMELY
USEFUL IN HANDLING THE SEQUENTIAL
INVESTMENTS.
• THE MERITS OF DECISION TREE TECHNIQUE
ARE:
• 1. CLARITY:
• 2. GRAPHIC VISUALISATION:
 DECISION TREE TECHNIQUE : MERITS
• 1. CLARITY:
• IT CLEARLY BRINGS OUT THE IMPLICIT
ASSUMPTIONS & CALCULATIONS FOR ALL TO SEE,
QUESTION & REVISE.
• 2. GRAPHIC VISUALISATION:
• IT ALLOWS A DECISION MAKER TO VISUALISE
ASSUMPTIONS & ALTERNATIVES IN GRAPHIC FORM,
WHICH IS USUALLY MUCH EASIER TO UNDERSTAND
THAN THE MORE ABSTRACT, ANALYTICAL FORM.
 BUT, DO REMEMBER….. {LIMITATION}
• THE DECISION TREE DIAGRAMS CAN BECOME MORE &
MORE COMPLICATED AS THE DECISION-MAKER
DECIDES TO INCLUDE MORE ALTERNATIVES & MORE
VARIABLES & TO LOOK FARTHER & FARTHER IN TIME.
• IT CAN BECOME FURTHER COMPLICATED IF THE
ANALYSIS IS EXTENDED TO INCLUDE INTERDEPENDENT
ALTERNATIVES & VARIABLES THAT ARE DEPENDENT
ON ONE ANOTHER.
• (e.g.: SALES VOLUME / MARKET SHARE / PROMOTION
EXPENSES etc.)
WHEN TO CONSIDER DECISION TREE
• INSTANCES DESCRIBABLE BY ATTRIBUTE-VALUE
PAIRS
– E.G HUMIDITY: HIGH, NORMAL
• TARGET FUNCTION IS DISCRETE VALUED
– E.G PLAY TENNIS; YES, NO
• DISJUNCTIVE HYPOTHESIS MAY BE REQUIRED
– E.G OUTLOOK=SUNNY  WIND=WEAK
• POSSIBLY NOISY TRAINING DATA
• MISSING ATTRIBUTE VALUES
WHEN TO CONSIDER DECISION TREE
• APPLICATION EXAMPLES:
– MEDICAL DIAGNOSIS
– CREDIT RISK ANALYSIS
– OBJECT CLASSIFICATION FOR ROBOT
MANIPULATOR (TAN 1993)
LET US APPLY DECISION TREE TECHNIQUE
TO DECISION ABOUT COMMUTING TIME
 PREDICTING COMMUTE TIME

Leave At IF WE LEAVE AT
10 AM 9 AM 10 AM AND
8 AM
THERE ARE NO
Stall? Accident?
CARS STALLED
No Yes Long No Yes
ON THE ROAD,
WHAT WILL
Short Long Medium Long OUR
COMMUTE
TIME BE?
LET US APPLY DECISION TREE TECHNIQUE
TO DECISION ABOUT PLAYING TENNIS
 DECISION TREE FOR PLAY TENNIS
• ATTRIBUTES AND THEIR VALUES:
– OUTLOOK: SUNNY, OVERCAST, RAIN
– HUMIDITY: HIGH, NORMAL
– WIND: STRONG, WEAK
– TEMPERATURE: HOT, MILD, COOL

– TARGET CONCEPT - PLAY TENNIS: YES, NO

ICS320 169
 DECISION TREE FOR PLAY TENNIS
Outlook

Sunny Overcast Rain

Humidity Yes Wind

High Normal Strong Weak

No Yes No Yes

ICS320 170
 DECISION TREE FOR PLAY TENNIS
Outlook Temperature Humidity Wind PlayTennis
Sunny Hot High Weak ?
No
Outlook

Sunny Overcast Rain

Humidity Yes Wind

High Normal Strong Weak

No Yes ICS320
No Yes 171
 CONVERTING A TREE TO RULES
Outlook

Sunny Overcast Rain

Humidity Yes Wind

High Normal Strong Weak

No Yes No Yes

R1: If (Outlook=Sunny)  (Humidity=High) Then PlayTennis=No

R2: If (Outlook=Sunny)  (Humidity=Normal) Then PlayTennis=Yes
R3: If (Outlook=Overcast) Then PlayTennis=Yes
R4: If (Outlook=Rain)  (Wind=Strong) Then PlayTennis=No
R5: If (Outlook=Rain)  (Wind=Weak) Then PlayTennis=Yes
ICS320 172
LET US WORK ON AN APPLICATION
OF DECISION TREE
 HOME EXERCISE
• YOUR COMPANY PROPOSES TO LAUNCH AN
AGGRESSIVE MARKETING CAMPAIGN WITH DISCOUNT
INCENTIVES.
• THE CONSIDERATIONS ARE AS FOLLOWS:
• A) THE DISCOUNT WOULD BE AVAILABLE FOR BOTH
CASH & CREDIT PURCHASES.
• B) DISCOUNTS WOULD BE AVAILABLE ON CREDIT
PURCHASES, PROVIDED THERE ARE NO OVERDUES
OUTSTANDINGS AND/OR THE OUTSTANDINGS ARE
WITHIN PERMISSIBLE CREDIT LIMITS
 HOME EXERCISE
• C) THE DISCOUNT OFFERED IS AS FOLLOWS:
• UPTO RS. 2,50,000 CASH 3% CREDIT 1.5%
• 2,50,001 TO 5,00,000 CASH 3.5%
CREDIT 2%
• 5,00,001 TO 10,00,000 CASH 3.75% CREDIT 2%
• ABOVE 10,00,001 CASH 3.95% CREDIT 2.35%
 HOME EXERCISE
• DUE ATTENTION WOULD BE GIVEN TO THOSE
DEALERS / DISRTIBUTORS WHO ARE “LIVE”.
• ONLY THESE “LIVE” DEALERS / DISTRIBUTORS
WOULD BE ENTITLED FOR DISCOUNTS.
LET US NOW DISCUSS
DECISION TABLES
 DECISION TABLES
• DECISION TABLES ARE A CONCISE VISUAL
REPRESENTATION FOR SPECIFYING WHICH ACTIONS TO
PERFORM DEPENDING ON GIVEN CONDITIONS.
• THEY ARE ALGORITHMS WHOSE OUTPUT IS A SET OF
ACTIONS.
• THE INFORMATION EXPRESSED IN DECISION TABLES
COULD ALSO BE REPRESENTED AS DECISION TREES, OR,
• IN A PROGRAMMING LANGUAGE
• AS A SERIES OF IF-THEN-ELSE & SWITCH-CASE
STATEMENTS.
 DECISION TABLE
• IT IS A STRUCTURED WAY TO FORMULATE REQUIREMENTS
AND TEST CASES WHEN DEALING WITH COMPLEX BUSINESS
RULES.
• USING A DECISION TABLE WILL MAKE IT EASIER TO WRITE
REQUIREMENTS THAT COVER ALL ALTERNATIVE CONDITIONS
IN BUSINESS RULES.
• WHEN WRITING TEST CASES THE TABLE WILL HELP YOU
TO TEST ALL COMBINATIONS.
 DECISION TABLES
• TO MAKE THEM MORE CONCISE, MANY DECISION
TABLES INCLUDE IN THEIR CONDITION ALTERNATIVES
• A “DON’T CARE” SYMBOL.
• THIS CAN BE A HYPHEN OR BLANK, ALTHOUGH USING A
BLANK IS DISCOURAGED AS IT MAY MERELY INDICATE
THAT THE DECISION TABLE HAS NOT BEEN FINISHED.
• ONE OF THE USES OF DECISION TABLES IS TO REVEAL
CONDITIONS UNDER WHICH CERTAIN INPUT FACTORS
ARE IRRELEVANT ON THE ACTIONS TO BE TAKEN,
ALLOWING THESE INPUT TESTS TO BE SKIPPED AND
THEREBY STREAMLINING DECISION-MAKING
PROCEDURES.
 DECISION TABLES
• EACH DECISION CORRESPONDS TO A VARIABLE,
RELATION OR PREDICATE WHOSE POSSIBLE VALUES ARE
LISTED AMONG THE CONDITION ALTERNATIVES.
• EACH ACTION IS A PROCEDURE OR OPERATION TO
PERFORM, AND THE ENTRIES SPECIFY WHETHER (OR IN
WHAT ORDER) THE ACTION IS TO BE PERFORMED FOR
THE SET OF CONDITION ALTERNATIVES THE ENTRY
CORRESPONDS TO.
 WHAT ARE DECISION TABLES?
•DECISION TABLES ARE A SYSTEMATIC EXERCISE USED TO
REPRESENT COMPLEX BUSINESS RULES.
•FORMULATING A TABLE MAKES IT EASY TO SEE ALL OF THE
POSSIBLE COMBINATIONS OF REQUIREMENTS OR
CONDITIONS SO THAT YOU CAN ENSURE NO
COMBINATIONS ARE MISSED.
 WHAT ARE DECISION TABLES?
• THEY ARE USED TO SPECIFY WHAT ACTIONS SHOULD BE
PERFORMED UNDER CERTAIN CONDITIONS,
• WHICH ARE GENERALLY EXPRESSED AS TRUE (T) OR FALSE
(F).
• THE COLUMNS IN A DECISION TABLE REPRESENT THE
COMBINATIONS OF CONDITIONS OR RULES OF A BUSINESS
DECISION,
• WHICH WILL RESULT IN A CERTAIN ACTION DEPENDING ON
THE INPUT.
• THIS MEANS THAT EACH COLUMN REPRESENTS A TEST CASE.
 WHAT ARE DECISION TABLES?
• DECISION TABLES ARE EXCELLENT TOOLS TO USE FOR
REQUIREMENTS MANAGEMENT OR TESTING
• AS THEY MAKE IT EASY TO SEE WHEN CERTAIN
PATHWAYS HAVE BEEN MISSED.
• THIS THEN HELPS TESTERS TO WRITE BETTER, MORE
DETAILED TEST CASES.
• THEY ARE ALSO A GREAT WAY OF TRACKING THE
OUTPUTS OF VARIOUS COMBINATIONS.
 DECISION TABLE STRUCTURE
• A DECISION TABLE IS USUALLY DIVIDED INTO FOUR QUADRANTS.
•THE UPPER HALF OF THE TABLE LISTS THE CONDITIONS BEING
TESTED,
•WHILE THE LOWER HALF LISTS THE POSSIBLE ACTIONS TO BE
TAKEN.
•EACH COLUMN REPRESENTS A CERTAIN TYPE OF CONDITION OR
RULE.
•BASICALLY, “IF-THEN-GO-TO”, MEANING,
•IF A PARTICULAR CONDITION IS FULFILLED / SATISFIED,
•THEN GO TO A PARTICULAR ACTION
 TYPICAL DECISION TABLE STRUCTURE
CONDITIONS BEING CONDITION STATEMENTS CONDITION ENTRIES
TESTED
POSSIBLE ACTION TO BE ACTION STATEMENTS ACTION ENTRIES
TAKEN
ANOTHER VIEW
• CONDITION/S

• CONDITION ALTERNATIVES

• ACTION ENTRIES

• ACTIONS
• DECISION TABLES HAVE BEEN USED FOR MANY
YEARS IN DATA PROCESSING AND BUSINESS
APPLICATIONS TO SIMULATE COMPLEX RULE
SETS.
• SEVERAL COMPUTER LANGUAGES HAVE BEEN
DEVELOPED BASED ON RULE SYSTEMS AND THEY
ARE EASILY PROGRAMMED IN SEVERAL CURRENT
LANGUAGES.
 DECISION TABLES
• ASIDE FROM THE BASIC FOUR QUADRANT STRUCTURE,
DECISION TABLES VARY WIDELY IN THE WAY THE
CONDITION ALTERNATIVES AND ACTION ENTRIES ARE
REPRESENTED.
• SOME DECISION TABLES USE SIMPLE TRUE/FALSE VALUES
TO REPRESENT THE ALTERNATIVES TO A CONDITION
(SIMILAR TO IF-THEN-ELSE), OTHER TABLES MAY USE
NUMBERED ALTERNATIVES (SIMILAR TO SWITCH-CASE),
AND SOME TABLES EVEN USE FUZZY LOGIC OR
PROBABILISTIC REPRESENTATIONS FOR CONDITION
ALTERNATIVES.
 DECISION TABLES
• IN A SIMILAR WAY,
• ACTION ENTRIES CAN SIMPLY REPRESENT WHETHER AN
ACTION IS TO BE PERFORMED (CHECK THE ACTIONS TO
PERFORM),
• OR, IN MORE ADVANCED DECISION TABLES,
• THE SEQUENCING OF ACTIONS TO PERFORM (NUMBER
THE ACTIONS TO PERFORM).
 DECISION TABLES
• A DECISION TABLE IS CONSIDERED BALANCED OR
COMPLETE IF IT INCLUDES EVERY POSSIBLE
COMBINATION OF INPUT VARIABLES.
• IN OTHER WORDS, BALANCED DECISION TABLES
PRESCRIBE AN ACTION IN EVERY SITUATION WHERE
THE INPUT VARIABLES ARE PROVIDED.
 LET US TAKE A PRACTICAL EXAMPLE OF A
DECISION TABLE
•A COMPANY X SELLS MERCHANDISE TO WHOLESALE AND
RETAIL OUTLETS.
•WHOLESALE CUSTOMERS RECEIVE A TWO PERCENT DISCOUNT
ON ALL ORDERS.
•THE COMPANY ALSO ENCOURAGES BOTH WHOLESALE AND
RETAIL CUSTOMERS TO PAY CASH ON DELIVERY BY OFFERING A
TWO PERCENT DISCOUNT FOR THIS METHOD OF PAYMENT.
•ANOTHER TWO PERCENT DISCOUNT IS GIVEN ON ORDERS OF
50 OR MORE UNITS.
•EACH COLUMN REPRESENTS A CERTAIN TYPE OF ORDER.
 CONDITIONS / ACTIONS
• ARE YOU A WHOLESALE CUSTOMER?
(THEN 2% DISCOUNT ON ALL ORDERS).
• IS THE PAYMENT IN CASH ON DELIVERY?
(THEN 2% DISCOUNT ON ALL
ORDERS).
• IS THE ORDER FOR MORE THAN 50 UNITS?
(THEN ANOTHER 2% DISCOUNT)
ILLUSTRATIVE DECISION TABLE
 DECISION TABLE
• THE DECISION TABLE RECORDS THE CONDITIONS FOR
DISCOUNTS IN THE TOP LEFT QUADRANT ALONG WITH THE
RANGES FOR THE CONDITIONS IN THE TOP RIGHT
QUADRANT.
• THE BOTTOM HALF OF THE TABLE LISTS THE ACTIONS
TAKEN, I.E., THE DISCOUNT RATES THAT APPLY, BASED ON
THE CONDITIONS.
• EACH COLUMN REPRESENTS A CERTAIN TYPE OF ORDER.
• FOR EXAMPLE, COLUMN TWO REPRESENTS CASH ON
DELIVERY ORDERS OF LESS THAN 50 UNITS FROM
RETAILERS.