Decision Trees

Decision Trees

1. uncertainity

   • hard to calculate outcomes
   • unpredictable factors
   • Risk attitude varies between decision makers

2. Terminology

   • Root node
     • Chance nodes
       • Assigned probabilities above relate to the chance of the node to actually happen.
       • endpoint

3. Method

   • EV: probability * gain / loss
     • rollback.
       • The process of successively calculating expected values from the endpoints of the decision tree to the root node, as demonstrated in this section, is called a decision tree rollback
   • strategies
     • maximin - play safe
     • maximax - most gain (and risk usually)
     • minimax regret . opportunity loss- minimize loss
     • EMV - expected monetary value
       • Expected Opportunity Loss, which combines the Minimax Regret with the statistical principles of EMV to give a conservative statistical approach.