MARKET BASKET ANALYSIS
•Association Rule Mining A.K.A. Market Basket Analysis
•Association-rule mining discovers correlations among items within transactions
•The correlations are expressed in the following form:
X
→
Y
meaning:
Transactions that contain X are likely to contain Y as well
where X and Y represent sets of transaction items.
•Two important quantities measured for every association rule
–
Support:
the fraction of transactions that contain both X and Y items
Support (X
→
Y) = Count (transactions containing X and Y) / Count (all transactions)
–
Confidence:
the fraction of transactions containing items X, which also contain items Y.
Confidence (X
→
Y) = Count (transactions containing X and Y) / Count (transactions
containing X)
•The support measures the significance of the rule, so we are interested in rules with relatively
high support.
•The confidence measures the strength of the correlation, so rules with low confidence are not
meaningful, even if their support is high.
This
preview
has intentionally blurred sections.
Sign up to view the full version.
•
We are looking for association rules with 0.5% support and 50% confidence

This is the end of the preview.
Sign up
to
access the rest of the document.
- Spring '08
- Jukic
- Data Mining, market basket analysis, items Y. Confidence
-
Click to edit the document details