Pessimistic cost-sensitive active learning of decision trees for profit maximizing targeting campaigns.
Lior RokachLihi NaamaniArmin ShmiloviciPublished in: Data Min. Knowl. Discov. (2008)
Keyphrases
- profit maximizing
- decision trees
- advertising campaigns
- decreasing function
- nash equilibrium
- electricity markets
- cost sensitive learning
- training data
- naive bayes
- machine learning algorithms
- high demand
- classification trees
- classification rules
- ensemble methods
- active learning strategies
- online advertising
- rule sets
- training set
- machine learning
- probability estimation
- supervised learning
- data sets
- reinforcement learning
- feature selection