IS3301 Computer-Based Tools for Decision Support

This course introduces the principles for designing, implementing and using computer-based tools to support a variety of decision-making situations. A key objective of the course is to introduce managerial decision-making technology in a format that is not too abstract or too mathematical. We cover a variety of analytical techniques for decision making in complex environments, involving single or multiple criteria made under certainty and uncertainty. Students learn the difference between building "private" models and "public" models and are introduced to software engineering practices for engineering quality models. Exemplary computer-based applications that support or involve the use of formal decision making methods and tools are discussed. Group projects will supplement and reinforce the course's learning objectives.

Prerequisite

IS3200, IS3201

Lecture Hours

3

Lab Hours

2

Course Learning Outcomes

Upon successful completion of this course, students should be able to do:

• Introduction to Models and Spreadsheet Modeling
  • Represent information science issues in spreadsheet models, perform sensitivity analysis, and use sensitivity analysis to supplement ‘single answer’ models.
• Forecasting
  • Use models to predict explore “what if?” consequences in probabilistic modeling.
• Linear Optimization
  • Apply the basics of mathematical modeling:  abstracting the essential elements of a complex problem and representing them (when appropriate) in a linear optimization model.
  • Conduct sensitivity analysis of linear programming models using the basic concepts of duality and shadow prices.  Identify and value constrained resources, understanding the marginal value of activities.
• Nonlinear Optimization (Integer Optimization and Dynamic Models)
  • Apply the basic tools and techniques developed for linear models to integer and dynamic models.
• Decision Analysis and Simulation
  • Regression Analysis
    • Exploratory data analysis.
    • Prepare data for regression analysis.
    • Abstracting from the data; identify dependent and independent variables.
    • Run linear regression analysis with Excel.
      • Simple and multiple linear regression models.
  • Monte-Carlo simulation: Probabilistic Models
    • Learn to abstract the essential elements of a complex problem and represent the inter-relationships between independent variables.
    • Understand how variability (risk) and lack of information (uncertainty) affect outcome criteria (e.g., expected value)
    • Model problems involving risk, using Excel-based models, including selecting appropriate distributions for risky inputs (input modeling), verifying the simulation models, and analyzing the outputs.
    • Building What if analysis with the simulation