Chp 3 Provost And Fawcett

Question 1

Supervised segmentation

Answer 1

How can we segment the population into groups that differ from each other with respect to some quantity of interest

Question 2

Information

Answer 2

Quantity that reduces uncertainty about something

Question 3

Tree induction

Answer 3

Incorporates the idea of supervised sit on in an elegant manner repeatedly selecting informative attributes

Question 4

Model

Answer 4

Simplified representation of reality created to serve a purpose

Question 5

Predictive model

Answer 5

Formula for estimating the unknown value of interest (the target)

Question 6

Prediction

Answer 6

Estimate an unknown value

Question 7

Descriptive modeling

Answer 7

Gain insight into the underlying phenomenon or process

Question 8

Supervised learning

Answer 8

Model creation where the model describes a relationship between a set of selected variables(attributes or features) and a predefined variable called the target variable

Question 9

Instance/example/row

Answer 9

Represents a fact or data point

Question 10

Instance/feature vector

Answer 10

Described by a set of attributes(fields, columns, variables, features)

Question 11

Model induction

Answer 11

Creation of models from data

Question 12

Training data

Answer 12

Input data for the induction algorithm used for the inducing model

Question 13

Entropy

Answer 13

A measure of disorder that can be applied to a set

Question 14

Information gain (IG)

Answer 14

Measures how much an attribute improves (decreases the entropy number) over the whole segmentation it creates

Question 15

Instance space

Answer 15

Space described by the data features