1 lecturer: dr mohammad nabil almunawar e-business decision support

26
1 Lecturer: Dr Mohammad Nabil Almunawar E-Business Decision Support

Upload: nicholas-thomas

Post on 14-Dec-2015

215 views

Category:

Documents


1 download

TRANSCRIPT

1

Lecturer: Dr Mohammad Nabil Almunawar

E-Business Decision Support

2

Learning Objectives

Identify the role and reporting alternatives of management information systems.

Explain the decision support system concept and how it differs from traditional management information systems.

Explain how executive information systems can support the information needs of executives and managers.

Explain the expert systems concept and how it differs from traditional MIS and DSS.

3

E-Business Decision Support Trends

E-commerce is expanding the use of information and decision support

Fast pace of new information technologies like PC hardware and software suites, client/server networks, and networked PC versions of DSS/EIS software, made EIS/DSS access available to lower levels of management, as well as to non-managerial individuals and self-directed teams of business professionals.

Dramatic growth of intranets and extranets that internetwork E-business enterprises and their stakeholders.

E-business decision support applications are being customized, personalized, and web-enabled for use in E-business and E-commerce.

4

Information, Decisions, and Management

5

Management Information System Reports

Periodic ScheduledReports

Periodic ScheduledReports

Exception ReportsException Reports

Demand Reportsand Responses

Demand Reportsand Responses

Push ReportsPush Reports

MajorManagementInformation Systems Reports

6

Online Analytical Processing

OLAP basic analytical operations:

Consolidation

Drill-Down

Slicing and Dicing

7

Decision Support Systems (DSS)

DSS are computer-based information systems that provide interactive information support to managers and business professionals during the decision-making process. Decision support systems use: Analytical models Specialized databases Decision maker’s own insights and judgments Interactive, computer-based modeling process to

support the making of semistructured and unstructured business decisions

8

DSS

What If-AnalysisWhat If-Analysis

Sensitivity AnalysisSensitivity Analysis

Goal-Seeking AnalysisGoal-Seeking Analysis

Optimization AnalysisOptimization Analysis

ImportantDecision SupportSystemsAnalytical Models

ImportantDecision SupportSystemsAnalytical Models

9

Conceptual Model for DSS

Data Management

Model Management

Knowledge manager

Dialog management

Manager(User)

Database: externaland internal

10

Data Mining for Decision Support The main purpose of data mining is knowledge discovery,

which will lead to decision support. Characteristics of data mining include: Data mining software analyzes the vast stores of historical

business data that have been prepared for analysis in corporate data warehouses.

Data mining attempts to discover patterns, trends, and correlations hidden in the data that can give a company a strategic business advantage.

Data mining software may perform regression, decision-tree, neural network, cluster detection, or market basket analysis for a business.

Data mining can highlight buying patterns, reveal customer tendencies, cut redundant costs, or uncover unseen profitable relationships and opportunities.

11

Executive information systems (EIS) EIS are information systems that combine many of the

features of MIS and DSS. The goal of EIS is to provide top executives with

immediate and easy access to information about a firm's critical success factors (CSFs).

Some features of EIS: Browsing capability. Source: formatted report, briefings, and

meetings Multiple presentation formats (text, tubular, graphics) Simple interface (touch screen, possible voice-based for

future ESS) Analytical and modeling features (what-if, why) Tailoring and customization to preserve preferences. Access to external data Data from multiple sources

12

Managing KnowledgeArtificial Intelligence (AI)

AI is a discipline in Computer Science to develop computer-based systems that behave as humans. The systems have the ability to learn natural languages, accomplish coordinated physical tasks (robotics), utilize a perceptual apparatus that inform their behavior and language, and emulate human expertise and decision making (expert systems).

13

Artificial Intelligence Applications

CognitiveScience

Applications

CognitiveScience

Applications

ArtificialIntelligenceArtificial

Intelligence

RoboticsApplications

RoboticsApplications

NaturalInterface

Applications

NaturalInterface

Applications

•Expert Systems•Fuzzy Logic•Genetic Algorithms•Neural Networks•Intelligent Agents

•Visual Perceptions•Locomotion•Navigation•Tactility

•Natural Language•Speech Recognition•Multisensory Interface•Virtual Reality

14

Human Intelligence Human Intelligence

is a way of reasoning (using rules such as if A then B, other rule types)

is a way of behaving includes the development and use of

metaphors and analogies. Includes the creation and use of concepts.

15

AI refers to an effort to develop machines that can reason, behave, compare, and conceptualize.

So far non of AI machines achieving those above dream, however simple and domain specific machines successfully built.

Expert systems is one of IA branch that gaining popular in business applications to solve some unstructured problems.

16

Expert Systems An expert system is a knowledge-intensive

program that solves a problem by capturing the expertise of a human in a limited domain of knowledge and experience.

An expert system can assist decision making by asking relevant questions and explaining the reasons for adopting certain actions.

Expert systems are never to be general problem solver (they work for very specific problems)

17

Basic Concept of ES

User

Knowledge-Base

Inference Engine

ES

Facts

Expertise

18

Capability of human expert

Recognizing and formulating the problem Solving the problem quickly and properly Explaining the solution Learning from experience Restructuring knowledge breaking rules determining relevance degrading gracefully (awareness of limitation)

19

Some facts about expertise Expertise is usually associated with a high degree

of intelligence but is not always connected to the smartest person

Expertise is usually associated with quantity of knowledge

Experts learn from past successes and mistakes Experts’ knowledge is well-stored, organized, and

retrievable quickly Experts can call up patterns from their experience

(excellent recall).

20

Objective of ES To transfer expertise from an expert or

experts to a computer and then on to others humans (nonexperts).

The process involve four activities: knowledge acquisition (from experts or other

sources) knowledge representation (in computer) knowledge inferencing knowledge transfer to user.

21Structure of ES

Knowledge acquisition

Knowledge base

Facts: What is known about domain area

Rules: Logical reference e.g., between symptoms & causes

KnowledgeEngineer

ExpertKnowledge

KnowledgeRefinement

Blackboard (Workplace)Plan AgendaSolution Problem Description

Inference EngineDraw Conclusions

•Interpreter•Scheduler•Consistency Enforcer

RecommendedAction

User Interface

User

ExplanationFacility

Facts aboutThe specificincident

Consultation Environment Development Environment

22

Some categories of ES

Category Problem AddressedInterpretation Inferring situation descriptions from observationPrediction Inferring likely consequences of given situationsDiagnosis Inferring system malfunctions from observationPlanning Developing plan to achieve goal(s)Monitoring Comparing observations to plans, flagging exceptionsDebugging Prescribing remedies for malfunctionsRepair Executing a plan to administer a prescribed remedyInstruction Diagnosing, debugging, and correcting student performanceControl Interpreting, predicting, repairing and monitoring system behaviors

23

Some Advantages of ES

Increase availability Reduced cost Reduced danger Permanence Multiple expertise Increase reliability Explanation

Fast response Steady, unemotional,

and complete response all the time

Intelligent tutor Intelligent database

24

Limits of ES Best used to augment experts' capabilities; ES may

not be able to replace the expert. Not truly intelligent; cannot learn new concepts

and rules. Not good for problems that lack focus/careful

definition. ES demonstrate no common sense. Exhibit limited use in areas where humans are

unwilling to let the ES be accountable for actions, e.g., in making final medical diagnosis decisions.

25

Intelligent Agents

InterfaceTutors

InterfaceTutors

PresentationAgents

PresentationAgents

NetworkNavigation

Agents

NetworkNavigation

Agents

Role-PlayingAgents

Role-PlayingAgents

UserInterfaceAgents

InformationManagement

Agents

SearchAgentsSearchAgents

InformationBrokers

InformationBrokers

InformationFilters

InformationFilters

An intelligent agent (also called intelligentassistants/wizards) is a software surrogatefor an end user or a process that fulfils astated need or activity. An intelligentagent uses a built-in and learnedknowledge base about a person or processto make decisions and accomplish tasks ina way that fulfils the intentions of a user.

26

Summary Decision support systems in business are changing. The

growth of corporate intranets, extranets, and other web technologies have increased the demand for a variety of personalized, proactive, web-enabled analytical techniques to support DSS.

Information systems must support a variety of management decision-making levels and decisions.

Decision support systems are interactive computer-based information systems that use DSS software and a model base to provide information to support semi-structured and unstructured decision making.

The Objective of ES is to transfer expertise from an expert or experts to a computer and then on to others humans (nonexperts). ES is capbale to support unstructured decision making.