Evaluating Network Design Decisions Using Decision Trees

5 EVALUATING NETWORK DESIGN DECISIONS USING DECISION TREES 

A decision tree is a graphic device used to evaluate decisions under uncertainty. Decision trees with DCFs can be used to evaluate supply chain design decisions given uncertainty in prices, demand, exchange rates, and inflation. 

The next step is to identify factors that will affect the value of the decision and are likely to fluctuate over the next T periods. These factors include demand, price, exchange rate, and inflation, among others. Having identified the key factors, the next step is to identify probability distributions that define the fluctuation of each factor from one period to the next. If, for instance, demand and price are identified as the two key factors that affect the decision, the probability of moving from a given value of d and and price in one period to any other value of demand and price in the next period must be defined. 

The next step is to identify a periodic disconnt rate fe to be applied to future cash flows. It is not essential that the same discount rate apply to each period or even at every node in a period. The discount rate should take into account the inherent risk associated with the investment. In general, a higher discount rate should apply to investments with higher risk. 

The decision is now evaluated using a decision tree, which contains the present and T future periods. Within each period, a node must be defined for every possible combination of factor values (say, demand and price) that can be achieved. Arrows are drawn from origin nodes in Period i to end nodes in Period i + 1. The probability on an arrow is referred to as the transition probability and is the probability of transitioning from the origin node in Period i to the end node in Period i+ 1. 

---