Churn prediction in subscription services: An application of support vector machines while comparing two parameter-selection techniques.
Kristof CoussementDirk Van den PoelPublished in: Expert Syst. Appl. (2008)
Keyphrases
- parameter selection
- telecommunication services
- churn prediction
- adaptive regularization
- next generation networks
- web services
- model selection
- customer churn
- rule induction
- random forest
- image processing
- machine learning
- ls svm
- pattern recognition
- neural network
- k nearest neighbor
- association rules
- training data
- decision trees