Predictive Model
Model

A simplified representation of reality created to serve a purpose.

E.g., Map, Architectural blueprint, Engineering prototype Mathematical Model
 E.g., a formula: V=IR
Prediction
 To estimate an unknown value (target variable)
Predictive Model

To setup a formula for estimating an unknown value (target variable) of interest

Supervised Learning

It is often built and tested using events from historical data.

Usage Example
 Predictive models for spam filtering estimate whether a given piece of email is spam.
 Predictive Model Form
 Mathematical Form
 Logical statement such as a rule
 But often it is a hybrid of the two

Predictive Model Type
 Classification models
 Classprobability estimation models
 Regression models
 Predictive Modeling
 To create a model which describes a relationship between a set of selected variables (attributes or features) and a target variable.
 It estimates the value of the target variable as a function of the selected variables
[Source: Data Science for Business]
 Terminology
 Instance (or Example)
 a fact or a data point
 Feature Vector (or Row)
 Attributes
 An instance is described by a set of attributes (or fields, columns, variables, or features)
 Independent variables or predictors
 Target Variable
 Dependent variable
 Instance (or Example)
Model Induction
 Induction
 A term from philosophy that refers to generalizing from specific cases to general rules (or laws, or truths).
 Model Induction
 The creation of models from data
 Most inductive procedures have variants that induce models both for classification and for regression.
 Training Data
 The input data for the induction algorithm, used for inducing the model
 They are also called labeled data
 Induction vs. Deduction
 Deduction starts with general rules and specific facts, and creates other specific facts from them.
 The use of our models can be considered a procedure of deduction.