Decision Support Systems

1
Decision Support Systems

• MBA 820
• Information Technology
• for Decision Making

2
Web-based Data Analysis at Shopko

• Problem
• The information systems that supported ShopKos
  business in the past were highly fragmented,
  ineffective, and inflexible.
• Forecasts were inaccurate, and wrong decisions
  were frequently made.
• Solution
• The company installed comprehensive decision
  support system (DSS) software (DSS Agent, from
  MicroStrategy).
• This system includes a data warehouse and online
  analytical processing.
• Results
• ShopKos investment into sophisticated web-based
  data analysis enabled stores to carry the right
  merchandise at the right place time.

3
Lessons from the Case

• A solution to complex decisions can be enhanced
  with the use of computer programs called a
  decision support system (DSS).
• Decisions are supported both in the sales and
  inventory areas.
• Much of the support is based around the concepts
  of data warehousing and online analytical
  processing.
• The Web is playing an increasing role in
  facilitating purchasing.

4
Need for Decision Making Support

• Number of alternatives is increasing
• Shortened time frame for decision making
• Increased environmental fluctuation and
  uncertainty

5
Decision Support Systems DSS

• Decision Support System (DSS) a computer-based
  information system that combines models and data
  in an attempt to solve semistructure problems
  with extensive user involvement.
• DSS can be viewed as an approach or a philosophy
  rather than a precise methodology.
• Designed to deliver capabilities, not simply to
  respond to information needs

6
Case Using DSS to Determine Risk

• Problem
• Houston Oil Minerals Corporation was interested
  in a proposed joint venture but requried a risk
  analysis.
• Solution
• Houston Oil built a DSS by means of a specialized
  planning language. The results suggested that the
  project be accepted.
• Results
• The executive vice president, using his
  experience, judgment, and intuition, decided to
  reverse the decision and rejected the project.
• The DSS was flexible and responsive enough to
  allow managerial intuition and judgment to be
  incorporated into the analysis.

7
Characteristics of DSSs
.

• Provides support for decision makers at all
  management levels, whether individuals or groups,
  by bringing together human judgment and objective
  information.
• Supports several interdependent and/or sequential
  decisions.
• Supports all phases of the decision-making
  process intelligence, design, choice, and
  implementationas well as a variety of
  decision-making processes and styles.
• Is adaptable by the user over time to deal with
  changing conditions.

8
Characteristics of DSSs (cont.)

• Is easy to construct and use in many cases.
• Promotes learning, which leads to new demands
  refinement of the application, which leads to
  additional learning, and so forth.
• Utilizes quantitative models (standard and/or
  custom made).
• Advanced DSSs are equipped with a knowledge
  management component that allows the efficient
  and effective solution of very complex problems.
• Can be disseminated for use via the Web.
• Allows the easy execution of sensitivity
  analyses.

9
Components of a DSS System

• Data Management Subsystem
• Model Management Subsystem
• Standard software with financial, statistical,
  management science, or other quantitative models.
  
• Model Base Management System (MBMS) creates DSS
  models easily and quickly, either from scratch,
  existing models, or building blocks.

10
DSS vs. MIS Differences
11
Developing a DSS

• How structured is the problem?
• Are data required for the analysis available from
  automated databases?
• How often do managers encounter this problem?
• Who will use the system?
• Is time available for development?

12
Using Spreadsheets for DSS

• Spreadsheet Analysis for
• Base case
• What-if
• Breakeven
• Best decision
• Excel Spreadsheet Tools
• Data Table, GoalSeek, Solver

13
Building the Spreadsheet

• Predict outcome of formula
• Build one module at a time
• Reduce Potential Errors
• Copy and paste formulas
• Use relative/absolute addressing
• Use Function Wizard

14
Testing Spreadsheet Design

• Check plausibility of numerical results
• Check formulas
• Use auditing tools to trace logic
• Test extreme cases
• Test sensitivities

15
DSS Example Advertising Budget

• Parameters
• Product sells for 40/unit
• Product costs 25/unit to produce
• Sales are seasonal
• Overhead is 15 of revenue
• Qtr Unit Sales 35 x SF x SQRT(3000Adv)
• Last year advertising budget was 40,000

From The Art of Modeling with Spreadsheets,
Powell Baker, Wiley Publishers (in press)
16
Sample Questions

• Impact on profits if
• 1 change in unit cost?
• 1000 change in Q1 advertising? Q2?
• With a fixed budget of 40,000, is it desirable
  to allocate the budget equally?
• Should the budget be increased?

From The Art of Modeling with Spreadsheets,
Powell Baker, Wiley Publishers (in press)
17
Managerial Challenges

• Measuring Benefits of DSS Against Cost
• Controlling User Developed DSSs
• Data Integrity
• Quality
• Documentation
• Security of DSS Information