Decision Trees

A decision tree is a tool that helps calculate the expected values of the choices that are available to you.

It uses probabilities of events happening and estimates of each possible outcome to help you make a decision. For example, if you called in to a radio contest where you got a chance to choose between a 1 in 10 chance of winning fifty dollars, and a 1 in 100 chance of winning a thousand dollars, which would you pick?

On the $50 side of the decision tree, one branch would give a 90% chance of $0, and a 10% chance of $50. The math is basically (.9 x 0) + (.1 x $50), or $0 + $5. So, you would expect to get a $5 payout by choosing the $50 prize option.

On the $1000 side, the branches would be (.99 x $0) + (.01 x $1000), or 0+$10. Your expected value would be $10.

It isn’t quite as simple as just saying to take the higher expected return. You might be risk averse and would prefer the smaller chance of going home empty handed. But the decision tree gives you better information to use in your decision making.

This example is simple. In most business decisions, there are many layers of things that have to happen to get to particular outcomes. Decision trees help organize these types of complicated scenarios.

The tool is called a decision tree because of the manner in which the decision points spread out like branches.

Note that this tool is used at the last point where you make a decision. If you have a series of decisions, the tool is not really useful because you can’t determine an expected value if it is based on a variable.