Analysis of shopping basket Market-Basket transactions Example of Association Rules TID Items Bread,Milk Diaper})→{Beer, (Milk,Bread)[Eggs,Coke}, 2 Bread,Diaper,Beer,Eggs {Beer,Bread)→{Milk, Milk,Diaper,Beer,Coke Bread,Milk,Diaper,Beer Implication means co-occurrence, Bread,Milk,Diaper,Coke not causality! Given a set of transactions,find rules that will predict the occurrence of an item based on the occurrences of other items in the transaction ATA 9 Copyright 2019 by Xiaoyu Li
9 Copyright © 2019 by Xiaoyu Li. Analysis of shopping basket
Association Rules What are association rules? Boolean association rules Overview Multilevel association rules Quantitative association rules Multidimensional association rules Constraint-based association mining ● Summary DATA 10 Copyright 2019 by Xiaoyu Li
10 Copyright © 2019 by Xiaoyu Li. Association Rules
What are Association Rules? .Association rule mining: *"Finding frequent patterns,associations, correlations,or causal structures among sets of items or objects in transactional databases,relational databases,and other information repositories." ·Applications: 米 market basket data analysis,cross-marketing, catalog design,loss-leader analysis,etc. DATA 11 Copyright 2019 by Xiaoyu Li
11 Copyright © 2019 by Xiaoyu Li. What are Association Rules?
Properties of Association Rules Express how items or objects are related to each other,and how they tend to group together. Simple to understand (comprehensibility). Provide useful information (utilizability) Efficient discovery algorithms exist (efficiency). 12 DATA Copyright 2019 by Xiaoyu Li
12 Copyright © 2019 by Xiaoyu Li. Properties of Association Rules
Analysis of Example 1 Analysis of customers buying habits by finding associations between the different items that customers place in their "shopping baskets". Customer 1 Customer 3 Milk,eggs, cereal,bread Milk,eggs, Eggs,sugar sugar,bread Customer 2 13 DATA Copyright 2019 by Xiaoyu Li
13 Copyright © 2019 by Xiaoyu Li. Analysis of Example 1