Predictive modeling is the process by which a model is created or chosen to try to best predict the probability of an outcome. Most often it wants to predict is in the future or unknown event. The model is chosen on the basis of detection theory. Models can use one or more classifiers.

Models

There are three predictive models

• Parametric
• Non-parametric
• Semi-parametric models

Parametric models make “specific assumptions with regard to one or more of the population parameters that characterize the underlying distributions”

Parametric
GMDH (Group method of data handling)
Naive Bayes
k-nearest neighbor algorithm
Majority classifier
Support vector machines (SVM)
Random forests
Boosted trees
CART (Classification and Regression Trees)
MARS (Multivariate adaptive regression splines)
Neural Networks
Ordinary Least Square
Generalized Linear Models (GLM)

Non-parametric
Generalized additive models
Robust regression

Semi-parametric models
Semiparametric regression

[1] http://googleresearch.blogspot.com/2014/10/smart-autofill-harnessing-predictive.html