BA 341 15th Edition Lecture 15 Outline of Last Lecture I. DecisionsII. Decision TreesIII. Decision making under uncertaintyIV. Decision Making under RiskOutline of Current Lecture V. Sequence of DecisionsVI. In summaryVII. Managing Process Variability Current LectureDecision Trees with a sequence of decisions:Let’s assume that our company has two decisions to make, with the second dependent on the outcome of the first. Let’s assume that before deciding about the plant, there is the option of a marketing study at a cost of $10,000. This study might reveal more accurate information about the market. How does this new decision affect our analysis?These notes represent a detailed interpretation of the professor’s lecture. GradeBuddy is best used as a supplement to your own notes, not as a substitute.In summary:- What is the optimal decision here?o First, conduct market surveyo Next, build large plant if survey results are favorable, otherwise, build small plant- How do we solve a decision tree?o “Rolling Back” (or “Folding Back”) the treeo Start at the endpoints of the branches (i.e., far right) and move left by Computing the EMV value when you encounter a chance (i.e., round) node, or Choosing the branch with the highest EMV when you encounter a decision (i.e., square) nodeo Decision trees can be used for sequential decisionsAn additional example:Consider the tree shown below, find the best decision alternativeEMV for A1: 10,000*0.6+2,000*0.4=6,800EMV for A2: 6,000*0.6+4,000*0.4=5,200EMV for A3: 20,000*0.6-6,000*0.4=9,600The decision is to go for A3.Managing Process VariabilityConsider a Service Call Center without any uncertainty - Customer arrivals are evenly spread out (e.g., 1 customer every 4 minutes)- Are there any blocked calls? No- Are there any customers tired of waiting? No- All systems need planning
View Full Document