Fundamentals of DSS Components of DSS Major capabilities of the DSS components Major DSS categories What-If Analysis Sensitivity

Analysis and Goal Seeking Analysis

B.B.Mishra

Accessing Organizational Information:

Decision Support System :
Components of DSS (Model, Data, User
interface Management)

DSS Technology level and tools WhatWhat -If Analysis Sensitivity Analysis and Goal Seeking Analysis

B.B.Mishra

Definition of DSS - A DSS is an interactive, flexible, and adaptable CBIS, specially developed for supporting the solution of a non-structured management problem for improved decision making. It utilizes data, it provides easy user interface, and it allows for the decision makers own insights DSS may utilize models, is built by an interactive process (frequently by end-users), supports all the phases of the decision making, and may include a knowledge component

Decision Support Methodology Technology Components Development

Capabilities Structure Classifications

Supports individuals and teams Used repeatedly and constantly Two major components: data and models Web-based Uses subjective, personal, and objective data Has a simulation model Used in public and private sectors Has what-if capabilities Uses quantitative and qualitative models

1. 2. 3. 4. 5. 6. 7.

8.
9.

10.
11.

12.
13.

Provide support in semi-structured and unstructured situations, includes human judgment and computerized information Support for various managerial levels Support to individuals and groups Support to interdependent and/or sequential decisions Support all phases of the decision-making process Support a variety of decision-making processes and styles Are adaptive Have user friendly interfaces Goal: improve effectiveness of decision making The decision maker controls the decision-making process End-users can build simple systems Utilizes models for analysis Provides access to a variety of data sources, formats, and types Decision makers can make better, more consistent decisions in a timely manner

1. 2. 3.

4.
5.

Data Management Subsystem Model Management Subsystem Knowledge-based (Management) Subsystem User Interface Subsystem The User

 DSS database
Database management system Data directory

Query facility

 Data Warehouse

Data Mining

Special independent DSS databases

Extraction of data from internal, external, and private

sources Web browser data access Web database servers Multimedia databases Special GSS databases (like Lotus Notes / Domino Server) Online Analytical Processing (OLAP) Object-oriented databases Commercial database management systems (DBMS)

 Analog of the database management subsystem

Model base Model base

management system Modeling language Model directory Model execution, integration, and command processor

Strategic Models: Non routine mergers, impact analysis, capital budgeting Tactical Models: Allocation & Control labor requirements, sales promotion planning Operational Models: Routine-day-to-day production scheduling, inventory control, quality control Analytical Models: SAS, SPSS, OR, Data Mining

 Model level: Strategic, managerial (tactical), and

operational Modeling languages Lack of standard MBMS activities. WHY? Use of AI and fuzzy logic in MBMS

 Provides expertise in solving complex unstructured and

semi-structured problems Expertise provided by an expert system or other intelligent system Advanced DSS have a knowledge based (management) component Leads to intelligent DSS Example: Data Mining

Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th edition Copyright 2001, Prentice Hall, Upper Saddle River, NJ

15

 Includes all

communication between a user and the MSS Graphical user interfaces (GUI) Voice recognition and speech synthesis possible
To most users, the user

interface is the system

Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th edition Copyright 2001, Prentice Hall, Upper Saddle River, NJ

16

Different usage patterns for the user, the manager, or the

decision maker

Managers Staff specialists Intermediaries

1. Staff assistant 2. Expert tool user 3. Business (system) analyst 4. GSS Facilitator

17

Evolved with computer hardware and software technologies

Mainframe Workstation Personal computer Web server system

Internet Intranets Extranets

Major Hardware Options

DSS is a problem-solving tool and is frequently used to address ad hoc and unexpected problems Different than MIS DSS evolve as they develop Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th edition
Copyright 2001, Prentice Hall, Upper Saddle River, NJ

18

19

20

Alters Output Classification (1980) Degree of action implication of system outputs (supporting decision)
Holsapple and Whinstons Classification

1. 2. 3. 4. 5. 6.

Text-oriented DSS Database-oriented DSS Spreadsheet-oriented DSS Solver-oriented DSS Rule-oriented DSS Compound DSS

Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th edition Copyright 2001, Prentice Hall, Upper Saddle River, NJ

21

22

 Descriptive
Procedural

Reasoning Linguistic
Presentation

Assimilative

Symbiotic

Expert-system based
Adaptive Holistic
Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th edition Copyright 2001, Prentice Hall, Upper Saddle River, NJ

23

Institutional DSS vs. Ad Hoc DSS Institutional DSS deals with decisions of a recurring nature Ad Hoc DSS deals with specific problems that are usually neither anticipated nor recurring Degree of nonprocedurality (Bonczek et al., 1980) Personal, group, and organizational support (Hackathorn and Keen, 1981) Individual versus group support systems (GSS) Custom-made versus ready-made systems

For DSS Success

Management Support Users Involved in Design

Support Users Ignored in Design & & Development Development Early Benefits Shown Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th edition No Early Benefits Shown Copyright 2001, Prentice Hall, Upper Saddle River, NJ

For DSS Failure Lack of Management

24

Prototyping Iterative design Evolutionary development Middle out process Adaptive design Incremental design

Short steps

Immediate stakeholder feedback Iterative

In development of prototype Within the system in general Evaluation integral part

Planning Analysis Design Prototype

Control mechanism

 Problems are semi-structured or unstructured

Managers and developers may not completely

understand problem Use prototyping

Users and managers involved in every phase and iteration Learning is part of design

Prototyping bypasses the information requirement definition

(7 steps) Short interval between iterations Initial prototype must be low cost

 Advantages

Disadvantages

User and management

involvement Learning explicitly integrated Prototyping bypasses information requirement Short intervals between iterations Low cost Improved user understanding of system

Changing requirements May not have thorough

understanding of benefits and costs Poorly tested Dependencies, security, and safety may be ignored High uncertainty Problem may get lost Reduction in quality Higher costs due to multiple productions

Three Levels of DSS Technology

Specific DSS [the application] DSS integrated tools (generators) [Excel] DSS primary tools [programming languages]

Plus
DSS integrated tools

Specific DSS
DSS Generators (Spreadsheets, )

Now all with Web hooks and easy GUI interfaces Relationships among the three levels

DSS Tools (Languages, )

DSS primary tools

Fundamental elements Programming languages, graphics, editors, query systems

DSS generator (engine) Specific DSS

Integrated software package for building specific DSS Modeling, report generation, graphics, risk analysis DSS application that accomplishes the work

DSS primary tools are used to construct integrated tools that are used to construct specific tools

General-purpose programming language Fourth-generation language (4GL) OLAP with a data warehouse or large database DSS integrated development tool (generator, engine) Domain-specific DSS generator Use the CASE methodology Substantial effort Integrate several of the above Extensive planning and organization Some generic activities

Group of people to build and to manage it Size depends on

Effort Tools

1. Information services (IS) department 2. Highly placed executive staff group 3. Finance or other functional area 4. Industrial engineering department 5. Management science group 6. Information center group

Personal computers Computer communication networks PCPC -mainframe communication Friendly development software Reduced cost of software and hardware Increased capabilities of personal computers EnterpriseEnterprise -wide computing Easy accessibility to data and models Client/server architecture Now OLAP

1. Short delivery time 2. Eliminate extensive and formal user requirements specifications 3. Reduce some DSS implementation problems 4. Low cost 1. Poor Quality 2. Quality Risks
Substandard or inappropriate tools and facilities

Development process risks

Data management risks

3. Increased Security Risks 4. Problems from Lack of Documentation and Maintenance Procedures

Hardware PCs to multiprocessor mainframes Software Involves multiple criteria Develop in house, outsource, or buy off the shelf Off the shelf software rapidly updated; many on market Prices fluctuate Different tools available Team developed DSS requires substantial effort to build and manage End user developed DSS Decision-makers and knowledge workers develop to solve problems or enhance productivity Advantages

Risks

Short delivery time User requirements specifications are eliminated Reduced implementation problems Low costs

Quality may be low May have lack of documentation Security risks may increase

DSS is much more than just a DBMS, MBMS, GUI, interface, and knowledge Component

Manager

User Interface (Display)

Decision Models

Database

Statistics & Manipulation

DSS Environment

Database It can be used to capture the data that can be used with other Database: components of DSS to make decisions. The objective is to centralize all data so that it is accessible for decision-making. Decision Models Models: These are complicated computer driven mathematical equations or models which are derived from previous instances or situations. The model expresses perceptions as to what data and variables are important and how the variables are related. Ex: Financial Model, Graphical Model, Mathematical Model etc. Statistics & Manipulation Manipulation: It produces meaningful information by relating the data into the models. General managerial models such as P/L statements, budget statement etc and more complex models such as product portfolio analysis, new product launch are aspects of data analysis in this process. Display: It is the interface between the business manager and the DSS. Display

 Database & its Management

Model-base & its Hardware of DSS

Management

User System Interface

Database & its Management

A database is a collection of data that is organized in such a way that it corresponds to needs and structure of a company and can be used for more than one application. DBMS: It is a series of software programs which has the following features:

Capabilities of obtaining answers to queries Quick retrieval and update of data Data security

 Model-base is divided into two major parts:

Pre-written computer program which include mathematical models

such as linear programming, regression analysis. This also include various other models such as strategic models, financial models, statistical models along with simulation program. Model building block are pre-written programs that can be used to construct new models for the present problem looking into various other models that already exists.

Model-base Management System (MBMS)

It is a software system that generates new routines and reports, model updates and changes and data manipulation. It is also capable of inter-relating models with the appropriate linkages through database.

Mainframe Computer Micro-computers GUI Display in the form of charts, graphs, diagrams which may be 3-D.

User System Interface

There are two parts in this component:

Query Language: It is a non-procedural language which means that statements in the models describe the desired results only and they may be entered in any order.

Example: Interactive Financial Planning System (IFPS)

Display: GUI screen for entering the problem or situation in any form and getting the desired results.

 Can

update or manipulate the database and also select data from database. Create special reports in a desired format. These reports once constructed may be stored in the model base for future reference. Perform calculations and execute aggregation of data. Construct mathematical models that describe a problem or a situation visualized by the user. Perform simulation. Perform analysis on various mathematical models such as regression analysis, time series analysis etc.

Major Functions of DSS

It is slow as compared to the high speed mainframes. The cost of building a DSS is considerably higher than other systems used in the organization.

Predicting decision outcomes. Developing models for business processes. Computing optimum mixes. Facilitate group communication.

Three Distinct Elements of DSS

DSS Tools DSS Generators Specific DSS

Specific DSS application can be constructed with a DSS generator, infrequently supported by special DSS tools.
DSS Tools DSS for specific application DSS Generator

DSS Generators

DSS Generators is a software package used to build specific DSS application.

Example: IBMs GADS (Geodata Analysis & Display System) which displays a map showing the location of equipment, machines etc. Other Examples: Lotus 1-2-3, Quattro etc

Construction of DSS application and creation of DSS generator is facilitated by special software elements called DSS Tools. The tools include:

Color Graphics Software Packages Special editors Random number generators

Database Software
SQL
Oracle

Model-base software
Lotus

Data Analysis Display software software

SAS
SPSS

MS-Access
FOCUS

1-2-3 Foresight Omnicalc

ChartMaster
SAS-GRAPH

MS-Excel

TELL-A-

GRAPH

More AI Faster, more powerful computers The Web - interfaces and DB and model access More and better GSS ERM/ERP Knowledge management Better GUI Better telecommunications More research on theories More research on methods

Decision-Support System, such as BostonCoachs, models information to support Managers & Business Professionals during the decision-making process The Three Quantitative Models, used by DSS are What What-If Analysis Sensitivity Analysis and Goal Seeking Analysis

Market competition & recent progress in data collection and storage techniques have increased the importance of quantitative modelling. Modelling has become an important part of R&D across many fields of study. The quantitative analysis methods & models, as quantitative modelling enables banks & insurance companies to devise their own specific risk models. It facilitates them to model changing economic & regulatory landscapes quickly & economically. Modelling framework & software tools enhance the performance of business. It provides a diagramming techniques to document business process for growth.

Demo using Ms-Excel

What-If Analysis tools in Microsoft Office Excel, facilitates the use of several different sets of values in one or more formulas to explore all the various results. It analyses the process of changing the values in cells to see how those changes will affect the outcome of formulas on the worksheet. What-If Analysis checks the impact of a change in an assumption on the processed solution. For example, What will

happen to the supply chain if a natural calamity reduces holding inventory from 30 percent to 10 percent? Users repeat this analysis until they understand all the effects at various situations. What-If analysis is done by using Microsoft Excel. The tool is calculating the net effect of a 20 percent increase in sales on the companys bottom line.

 Three kinds of what-if analysis tools come with Excel: Scenarios Data Tables and Goal Seek Scenarios

and data tables take sets of input values and determine possible results. A data table works only with one or two variables, but it can accept many different values for those variables. A scenario can have multiple variables, but it can accommodate only up to 32 values. Goal Seek works differently from scenarios and data tables in that it takes a result and determines possible input values that produce that result.

 Sensitivity

Analysis is the study of the impact that changes in one (or more) parts of the model have on other parts of the model. Typically, users change the value of one variable repeatedly and observe the resulting changes in other variables. Sensitivity analysis (SA) is the study of how the uncertainty in the output of a model (numerical or otherwise) can be apportioned to different sources of uncertainty in the model input. A related practice is uncertainty analysis which focuses rather on quantifying uncertainty in model output. Ideally, uncertainty and sensitivity analysis should be run in tandem.

 In

more general terms uncertainty and sensitivity analysis investigate the robustness of a study when the study includes some form of statistical modeling. Sensitivity analysis can be useful to computer modelers for a range of purposes, including: Support decision making or the development of recommendations for decision makers (e.g. testing the robustness of a result); Enhancing communication from modelers to decision makers
Increased

understanding or quantification of the system (e.g. understanding relationships between input and output variables); and Model development (e.g. searching for errors in the model).

(e.g. by making recommendations more credible, understandable, compelling or persuasive);

 In

computing, goal seeking is the ability to calculate backward to obtain an input that would result in a given output. This can also be called what-if analysis or backsolving. It can either be attempted through trial and improvement or more logical means. Basic goal seeking functionality is built into most modern spreadsheet packages such as Microsoft Excel. According to O'Brien and Marakas, optimization analysis is a more complex extension of goal-seeking analysis. Instead of setting a specific target value for a variable, the goal is to find the optimum value for one or more target variables, given certain constraints. Then one or more other variables are changed repeatedly, subject to the specified constraints, until you discover the best values for the target variables.

 Goal Seeking Analysis finds the inputs necessary to

achieve a goal such as a desired level of output. Instead of observing how changes in a variable affect other variables as in what-if analysis, goalseeking analysis sets a target value (a goal) for a variable and then repeatedly changes other variables until the target value is achieved. For example, How many customers are required to purchase our new product line to increase gross profit to 5 million?