An Eager Regression Method Based on Selecting Appropriate Features
Tolga Aydın, Halil Altay Güvenir · The Florida AI Research Society · 2001
This paper describes a machine learning method, called Regression by Selecthtg Best P~’ttllll’es (RSBF). RSBF consists of two phases: The first phase aims to find the predictive power of each feature by constructing simple linear regression lines, one per each continuous feature and number of categories pen each categorical feature. Although the predictive power of a continuous feature is constant, it varies for each distinct value of categorical features. The second phase constructs multiple linear regression lines among continuous features, each time excluding the worst feature among the current set, and constructs multiple linear regression lines. Finally, these muhiple linear regression lines and the categorical simple linear regression lines are sorted according to their predictive power. In the querying phase of learning, the best lineal regression line and the features constructing that line are selected to make predictions.