lecture19

# lecture19 - Data Mining CS57300 Purdue University Pattern...

This preview shows pages 1–8. Sign up to view the full content.

Data Mining CS57300 Purdue University November 18, 2010

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Pattern mining: representation & learning
Data mining components • Task specifcation: Pattern discovery • Data representation: Homogeneous IID data • Knowledge representation • Learning technique

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Pattern discovery • Models describe entire dataset (or large part of it) • Pattern characterize local aspects of data • Pattern: predicate that returns “true” for the instances in the data where the pattern occurs and “false” otherwise • Task: Fnd descriptive associations between variables
Examples • Supermarket transaction database • 10% of the customers buy wine and cheese • Telecommunications alarms database • If alarms A and B occur within 30 seconds of each other then alarm C occurs within 60 seconds with p=0.5 • Web log dataset • If a person visits the CNN website, there is a 60% chance the person will visit the ABC News website in the same month

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Pattern in tabular data • Primitive pattern: subset of all possible observations over variables X 1 ,...,X p • If X k is categorical then X k =c is a primitive pattern • If X k is ordinal then X k c is a primitive pattern • Start from primitive patterns and combine using logical connectives such as AND and OR • age<40 AND income<100,000 • chips=1 AND (beer=1 OR soda=1)
Pattern space • Set of legal patterns • DeFned through the set of primitive patterns and operators to combine primitives • Example • If variable X 1 ,...,X p are all binary we can deFne the space of patterns to be all conjunctions of the form (X i1 =1) AND (X i2 =1) AND . .. AND (X ik =1)

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

### Page1 / 30

lecture19 - Data Mining CS57300 Purdue University Pattern...

This preview shows document pages 1 - 8. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online