Data Mining: Prediction Methods

The classification methods presented in the “Data Mining: Classification and Prediction” chapter construct a model learning from a training data set and then uses it to classify new unseen instances. These methods are referred as eager learners. In this chapter will be introduced other classification methods, such as k-nearest-neighbor, case-based reasoning, genetic algorithms. Moreover, prediction methods will be explored, in particular referring to linear and nonlinear regression and finally two cases of generalized linear models: logistic and Poisson regression. Keywords: Case-based reasoning; Generalized linear models; Genetic algorithms; Inear regression; Logist regression; Loisson regression; Nonlinear regression; k-nearest neighbor; Prediction