Skip to main content

Data Mining for Analytics

General

Prefix

STAT

Course Number

615

Course Level

Graduate

Department/Unit(s)

Mathematics & Statistics

College/School

College of Science and Engineering

Description

Data mining principles and applications. Predictive modeling techniques for large data sets include classification and regression trees, logistic regression, neural networks, random forests and boosted trees. Handle missing values and outliers. Compare models and deploy best model to predict new data. Extensive
hands-on use of data mining software.

Prerequisites

Credits

Min

3

Max

3

Repeatable

No

Goals and Diversity

MN Goal Course

No

Cultural Diversity

No

Learning Outcomes

Outcome

Students will be able to explore large data sets graphically to better understand the data.

Outcome

Students will be able to describe data mining principles.

Outcome

Students will be able to explain the history of data mining and today¿s important applications.

Outcome

Students will be able to choose and apply appropriate predictive modeling techniques.

Outcome

Students will be able to use data mining software.

Course Outline

Course Outline

History, applications and data mining principles. 15% Data exploration. 10% Classification and regression trees. 20% Logistic regression. 15% Model comparisons and scoring. 10% Neural networks. 10% Random forests and boosted trees. 10% Comprehensive example. 10%

Dependencies

Programs

STAT615 is a completion requirement for: