Published on

Published in: Business, Technology, Education
  • Be the first to comment

  • Be the first to like this

No Downloads
Total views
On SlideShare
From Embeds
Number of Embeds
Embeds 0
No embeds

No notes for slide
  • 1
  • 3
  • 2
  • 5
  • 8
  • 10
  • 11
  • 12
  • 13
  • 14
  • 15
  • 2
  • 3
  • 4
  • 5
  • 6
  • 7
  • 8
  • 9
  • 10
  • 12
  • 13
  • 14
  • 15
  • 16
  • 21
  • 23
  • 30
  • 31
  • 32
  • 33
  • 35
  • 36
  • 35
  • Chap13

    1. 1. Chapter 13 <ul><li>Decision Support Systems </li></ul>MANAGEMENT INFORMATION SYSTEMS 8/E Raymond McLeod, Jr. and George Schell Copyright 2001 Prentice-Hall, Inc. 13-
    2. 2. Simon’s Types of Decisions <ul><li>Programmed decisions </li></ul><ul><ul><li>repetitive and routine </li></ul></ul><ul><ul><li>have a definite procedure </li></ul></ul><ul><li>Nonprogrammed decisions </li></ul><ul><ul><li>Novel and unstructured </li></ul></ul><ul><ul><li>No cut-and-dried method for handling problem </li></ul></ul><ul><li>Types exist on a continuum </li></ul>13-
    3. 3. Simon’s Problem Solving Phases <ul><li>Intelligence </li></ul><ul><ul><li>Searching environment for conditions calling for a solution </li></ul></ul><ul><li>Design </li></ul><ul><ul><li>Inventing, developing, and analyzing possible courses of action </li></ul></ul><ul><li>Choice </li></ul><ul><ul><li>Selecting a course of action from those available </li></ul></ul><ul><li>Review </li></ul><ul><ul><li>Assessing past choices </li></ul></ul>13-
    4. 4. Definitions of a Decision Support System (DSS) <ul><li>General definition - a system providing both problem-solving and communications capabilities for semistructured problems </li></ul><ul><li>Specific definition - a system that supports a single manager or a relatively small group of managers working as a problem-solving team in the solution of a semistructured problem by providing information or making suggestions concerning specific decisions. </li></ul>13-
    5. 5. The DSS Concept <ul><li>Gorry and Scott Morton coined the phrase ‘DSS’ in 1971, about ten years after MIS became popular </li></ul><ul><li>Decision types in terms of problem structure </li></ul><ul><ul><li>Structured problems can be solved with algorithms and decision rules </li></ul></ul><ul><ul><li>Unstructured problems have no structure in Simon’s phases </li></ul></ul><ul><ul><li>Semistructured problems have structured and unstructured phases </li></ul></ul>13-
    6. 6. Degree of problem structure The Gorry and Scott Morton Grid Management levels Structured Semistructured Unstructured Operational control Management control Strategic planning Accounts receivable Order entry Inventory control Budget analysis-- engineered costs Short-term forecasting Tanker fleet mix Warehouse and factory location Production scheduling Cash management PERT/COST systems Variance analysis-- overall budget Budget preparation Sales and production Mergers and acquisitions New product planning R&D planning 13-
    7. 7. Alter’s DSS Types <ul><li>In 1976 Steven Alter, a doctoral student built on Gorry and Scott-Morton framework </li></ul><ul><ul><li>Created a taxonomy of six DSS types </li></ul></ul><ul><ul><li>Based on a study of 56 DSSs </li></ul></ul><ul><li>Classifies DSSs based on “degree of problem solving support.” </li></ul>13-
    8. 8. Levels of Alter’s DSSs <ul><li>Level of problem-solving support from lowest to highest </li></ul><ul><ul><li>Retrieval of information elements </li></ul></ul><ul><ul><li>Retrieval of information files </li></ul></ul><ul><ul><li>Creation of reports from multiple files </li></ul></ul><ul><ul><li>Estimation of decision consequences </li></ul></ul><ul><ul><li>Propose decisions </li></ul></ul><ul><ul><li>Make decisions </li></ul></ul>13-
    9. 9. Importance of Alter’s Study <ul><li>Supports concept of developing systems that address particular decisions </li></ul><ul><li>Makes clear that DSSs need not be restricted to a particular application type </li></ul>13-
    10. 10. Retrieve information elements Analyze entire files Prepare reports from multiple files Estimate decision consequen-ces Propose decisions Degree of problem solving support Degree of complexity of the problem-solving system Little Much Alter’s DSS Types Make decisions 13-
    11. 11. Three DSS Objectives <ul><li>1. Assist in solving semistructured problems </li></ul><ul><li>2. Support, not replace, the manager </li></ul><ul><li>3. Contribute to decision effectiveness, rather than efficiency </li></ul>Based on studies of Keen and Scott-Morton 13-
    12. 12. GDSS software Mathematical Models Other group members Database GDSS software Environment Individual problem solvers Decision support system Environment Legend : Data Information Communication A DSS Model Report writing software 13-
    13. 13. Database Contents <ul><li>Used by Three Software Subsystems </li></ul><ul><ul><li>Report writers </li></ul></ul><ul><ul><ul><li>Special reports </li></ul></ul></ul><ul><ul><ul><li>Periodic reports </li></ul></ul></ul><ul><ul><ul><li>COBOL or PL/I </li></ul></ul></ul><ul><ul><ul><li>DBMS </li></ul></ul></ul><ul><ul><li>Mathematical models </li></ul></ul><ul><ul><ul><li>Simulations </li></ul></ul></ul><ul><ul><ul><li>Special modeling languages </li></ul></ul></ul><ul><ul><li>Groupware or GDSS </li></ul></ul>13-
    14. 14. Group Decision Support Systems <ul><li>Computer-based system that supports groups of people engaged in a common task (or goal) and that provides an interface to a shared environment. </li></ul><ul><li>Used in problem solving </li></ul><ul><li>Related areas </li></ul><ul><ul><li>Electronic meeting system (EMS) </li></ul></ul><ul><ul><li>Computer-supported cooperative work (CSCW) </li></ul></ul><ul><ul><li>Group support system (GSS) </li></ul></ul><ul><ul><li>Groupware </li></ul></ul>13-
    15. 15. How GDSS Contributes to Problem Solving <ul><li>Improved communications </li></ul><ul><li>Improved discussion focus </li></ul><ul><li>Less wasted time </li></ul>13-
    16. 16. GDSS Environmental Settings <ul><li>Synchronous exchange </li></ul><ul><ul><li>Members meet at same time </li></ul></ul><ul><ul><li>Committee meeting is an example </li></ul></ul><ul><li>Asynchronous exchange </li></ul><ul><ul><li>Members meet at different times </li></ul></ul><ul><ul><li>E-mail is an example </li></ul></ul><ul><li>More balanced participation. </li></ul>13-
    17. 17. GDSS Types <ul><li>Decision rooms </li></ul><ul><ul><li>Small groups face-to-face </li></ul></ul><ul><ul><li>Parallel communication </li></ul></ul><ul><ul><li>Anonymity </li></ul></ul><ul><li>Local area decision network </li></ul><ul><ul><li>Members interact using a LAN </li></ul></ul><ul><li>Legislative session </li></ul><ul><ul><li>Large group interaction </li></ul></ul><ul><li>Computer-mediated conference </li></ul><ul><ul><li>Permits large, geographically dispersed group interaction </li></ul></ul>13-
    18. 18. Smaller Larger GROUP SIZE Face-to- face Dispersed Decision Room Local Area Decision Network Legislative Session Computer- Mediated Conference MEMBER PROXIMITY Group Size and Location Determine GDSS Environmental Settings 13-
    19. 19. Groupware <ul><li>Functions </li></ul><ul><ul><li>E-mail </li></ul></ul><ul><ul><li>FAX </li></ul></ul><ul><ul><li>Voice messaging </li></ul></ul><ul><ul><li>Internet access </li></ul></ul><ul><li>Lotus Notes </li></ul><ul><ul><li>Popular groupware product </li></ul></ul><ul><ul><li>Handles data important to managers </li></ul></ul>13-
    20. 20. Main Groupware Functions IBM TeamWARE Lotus Novell Function Workgroup Office Notes GroupWise X = standard feature O = optional feature 3 = third party offering 13-
    21. 21. Artificial Intelligence (AI) The activity of providing such machines as computers with the ability to display behavior that would be regarded as intelligent if it were observed in humans. 13-
    22. 22. History of AI <ul><li>Early history </li></ul><ul><ul><li>John McCarthy coined term, AI, in 1956, at Dartmouth College conference. </li></ul></ul><ul><ul><li>Logic Theorist (first AI program. Herbert Simon played a part) </li></ul></ul><ul><ul><li>General problem solver (GPS) </li></ul></ul><ul><li>Past 2 decades </li></ul><ul><ul><li>Research has taken a back seat to MIS and DSS development </li></ul></ul>13-
    23. 23. Areas of Artificial Intelligence Expert systems AI hardware Robotics Perceptive systems (vision, hearing) Neural networks Natural language Learning Artificial Intelligence 13-
    24. 24. Appeal of Expert Systems <ul><li>Computer program that codes the knowledge of human experts in the form of heuristics </li></ul><ul><li>Two distinctions from DSS </li></ul><ul><ul><li>1. Has potential to extend manager’s problem-solving ability </li></ul></ul><ul><ul><li>2. Ability to explain how solution was reached </li></ul></ul>13-
    25. 25. Know- ledge base User User interface Instructions & information Solutions & explanations Knowledge Inference engine Problem Domain Expert and knowledge engineer Development engine Expert system An Expert System Model 13-
    26. 26. Expert System Model <ul><li>User interface </li></ul><ul><ul><li>Allows user to interact with system </li></ul></ul><ul><li>Knowledge base </li></ul><ul><ul><li>Houses accumulated knowledge </li></ul></ul><ul><li>Inference engine </li></ul><ul><ul><li>Provides reasoning </li></ul></ul><ul><ul><li>Interprets knowledge base </li></ul></ul><ul><li>Development engine </li></ul><ul><ul><li>Creates expert system </li></ul></ul>13-
    27. 27. User Interface <ul><li>User enters: </li></ul><ul><ul><li>Instructions </li></ul></ul><ul><ul><li>Information </li></ul></ul><ul><li>Expert system provides: </li></ul><ul><ul><li>Solutions </li></ul></ul><ul><ul><li>Explanations of </li></ul></ul><ul><ul><ul><li>Questions </li></ul></ul></ul><ul><ul><ul><li>Problem solutions </li></ul></ul></ul>} Menus, commands, natural language, GUI 13-
    28. 28. Knowledge Base <ul><li>Description of problem domain </li></ul><ul><li>Rules </li></ul><ul><ul><li>Knowledge representation technique </li></ul></ul><ul><ul><li>‘IF:THEN’ logic </li></ul></ul><ul><ul><li>Networks of rules </li></ul></ul><ul><ul><ul><li>Lowest levels provide evidence </li></ul></ul></ul><ul><ul><ul><li>Top levels produce 1 or more conclusions </li></ul></ul></ul><ul><ul><ul><li>Conclusion is called a Goal variable. </li></ul></ul></ul>13-
    29. 29. Evidence Conclusion Conclusion Evidence Evidence Evidence Evidence Evidence Evidence Evidence Conclusion A Rule Set That Produces One Final Conclusion 13-
    30. 30. Rule Selection <ul><li>Selecting rules to efficiently solve a problem is difficult </li></ul><ul><li>Some goals can be reached with only a few rules; rules 3 and 4 identify bird </li></ul>13-
    31. 31. Inference Engine <ul><li>Performs reasoning by using the contents of knowledge base in a particular sequence </li></ul><ul><li>Two basic approaches to using rules </li></ul><ul><ul><li>1. Forward reasoning (data driven) </li></ul></ul><ul><ul><li>2. Reverse reasoning (goal driven) </li></ul></ul>13-
    32. 32. Forward Reasoning (Forward Chaining) <ul><li>Rule is evaluated as: </li></ul><ul><ul><li>(1) true, (2) false, (3) unknown </li></ul></ul><ul><li>Rule evaluation is an iterative process </li></ul><ul><li>When no more rules can fire, the reasoning process stops even if a goal has not been reached </li></ul>Start with inputs and work to solution 13-
    33. 33. Rule 1 Rule 3 Rule 2 Rule 4 Rule 5 Rule 6 Rule 7 Rule 8 Rule 9 Rule 10 Rule 11 Rule 12 IF A THEN B IF C THEN D IF M THEN E IF K THEN F IF G THEN H IF I THEN J IF B OR D THEN K IF E THEN L IF K AND L THEN N IF M THEN O IF N OR O THEN P F IF (F AND H) OR J THEN M The Forward Reasoning Process T T T T T T T T T F T Legend: First pass Second pass Third pass 13-
    34. 34. Reverse Reasoning Steps (Backward Chaining) <ul><li>Divide problem into subproblems </li></ul><ul><li>Try to solve one subproblem </li></ul><ul><li>Then try another </li></ul>Start with solution and work back to inputs 13-
    35. 35. T Rule 1 Rule 2 Rule 3 Rule 9 Rule 11 Legend: Problems to be solved Step 4 Step 3 Step 2 Step 1 Step 5 IF A THEN B IF B OR D THEN K IF K AND L THEN N IF N OR O THEN P IF C THEN D IF M THEN E IF E THEN L IF (F AND H) OR J THEN M IF M THEN O IF M THEN O The First Five Problems Are Identified Rule 7 Rule 10 Rule 12 Rule 8 13- T
    36. 36. If K Then F Legend: Problems to be solved If G Then H If I Then J If M Then O Step 8 Step 9 Step 7 Step 6 Rule 4 Rule 5 Rule 11 Rule 6 T IF (F And H) Or J Then M T Rule 9 T T Rule 12 T If N Or O Then P The Next Four Problems Are Identified 13-
    37. 37. Forward Versus Reverse Reasoning <ul><li>Reverse reasoning is faster than forward reasoning </li></ul><ul><li>Reverse reasoning works best under certain conditions </li></ul><ul><ul><li>Multiple goal variables </li></ul></ul><ul><ul><li>Many rules </li></ul></ul><ul><ul><li>All or most rules do not have to be examined in the process of reaching a solution </li></ul></ul>13-
    38. 38. Development Engine <ul><li>Programming languages </li></ul><ul><ul><li>Lisp </li></ul></ul><ul><ul><li>Prolog </li></ul></ul><ul><li>Expert system shells </li></ul><ul><ul><li>Ready made processor that can be tailored to a particular problem domain </li></ul></ul><ul><li>Case-based reasoning (CBR) </li></ul><ul><li>Decision tree </li></ul>13-
    39. 39. Expert System Advantages <ul><li>For managers </li></ul><ul><ul><li>Consider more alternatives </li></ul></ul><ul><ul><li>Apply high level of logic </li></ul></ul><ul><ul><li>Have more time to evaluate decision rules </li></ul></ul><ul><ul><li>Consistent logic </li></ul></ul><ul><li>For the firm </li></ul><ul><ul><li>Better performance from management team </li></ul></ul><ul><ul><li>Retain firm’s knowledge resource </li></ul></ul>13-
    40. 40. Expert System Disadvantages <ul><li>Can’t handle inconsistent knowledge </li></ul><ul><li>Can’t apply judgment or intuition </li></ul>13-
    41. 41. Keys to Successful ES Development <ul><li>Coordinate ES development with strategic planning </li></ul><ul><li>Clearly define problem to be solved and understand problem domain </li></ul><ul><li>Pay particular attention to ethical and legal feasibility of proposed system </li></ul><ul><li>Understand users’ concerns and expectations concerning system </li></ul><ul><li>Employ management techniques designed to retain developers </li></ul>13-
    42. 42. Neural Networks <ul><li>Mathematical model of the human brain </li></ul><ul><ul><li>Simulates the way neurons interact to process data and learn from experience </li></ul></ul><ul><li>Bottom-up approach to modeling human intuition </li></ul>13-
    43. 43. The Human Brain <ul><li>Neuron -- the information processor </li></ul><ul><ul><li>Input -- dendrites </li></ul></ul><ul><ul><li>Processing -- soma </li></ul></ul><ul><ul><li>Output -- axon </li></ul></ul><ul><li>Neurons are connected by the synapse </li></ul>13-
    44. 44. Soma (processor ) Axon Synapse Dendrites (input) Axonal Paths (output) Simple Biological Neurons 13-
    45. 45. Evolution of Artificial Neural Systems (ANS) <ul><li>McCulloch-Pitts mathematical neuron function (late 1930s) was the starting point </li></ul><ul><li>Hebb’s learning law (early 1940s) </li></ul><ul><li>Neurocomputers </li></ul><ul><ul><li>Marvin Minsky’s Snark (early 1950s) </li></ul></ul><ul><ul><li>Rosenblatt’s Perceptron (mid 1950s) </li></ul></ul>13-
    46. 46. Current Methodology <ul><li>Mathematical models don’t duplicate human brains, but exhibit similar abilities </li></ul><ul><li>Complex networks </li></ul><ul><li>Repetitious training </li></ul><ul><ul><li>ANS “learns” by example </li></ul></ul>13-
    47. 47. Single Artificial Neuron 13- y 1 y 2 y 3 y n-1 y w 1 w 2 w 3 w n-1
    48. 48. The Multi-Layer Perceptron Y n2 IN n OUT n OUT 1 IN 1 Y 1 Input Layer OutputLayer 13-
    49. 49. Knowledge-based Systems in Perspective <ul><li>Much has been accomplished in neural nets and expert systems </li></ul><ul><li>Much work remains </li></ul><ul><li>Systems abilities to mimic human intelligence are too limited and regarded as primitive </li></ul>13-
    50. 50. Summary [cont.] <ul><li>AI </li></ul><ul><ul><li>Neural networks </li></ul></ul><ul><ul><li>Expert systems </li></ul></ul><ul><li>Limitations and promise </li></ul>13-