Module 6: Relationship Mining Basics

Relationship Mining

• Discover relationships between variables in a data set with many variables

• Many types of relationship mining

Correlation Mining

• Perhaps the simplest form of relationship mining

• Finding substantial linear (or monotonic) correlations between variables

• In a large set of variables

Association Rule Mining

Try to automatically find simple if-then rules within the data set

Sequential Pattern Mining

Try to automatically find temporal patterns within the data set

Network Analysis

• Social Network Analysis

• Epistemic Network Analysis

• Both have their own LASER badges, separate from Relationship Mining!

This week

• We will go in depth on correlation mining, association rule mining, sequential pattern mining

• How to use them to discover insights from data

• How to avoid obtaining spurious or meaningless “findings”

• We will cover examples of each of these three forms of relationship mining

What applications are you interested in?

Who here has already used correlation mining (or something like it), association rule mining, or sequential pattern mining?

What applications are you interested in?

• Who here already has specific ideas for how you’d like to use correlation mining (or something like it), association rule mining, or sequential pattern mining?

• Tell us more – about the data, about the goals of your analysis

First Up

Correlation Mining