ITM 760 Lecture Notes - Lecture 4: Association Rule Learning, Data Mining, Barcode

• School: Ryerson University
• Department: Information Technology Management
• Course: ITM 760
• Professor: Morteza Zihayat

Document Summary

Lecture 4: frequent item set mining over data streams. Goal: identify items that are bought together by sufficiently many customers. Approach: process the sales data collected with barcode scanners to find dependencies among items. If someone buys diaper, then he/she is likely to buy beer: ex: grocery store pairs diapers and beer together. Model wants to discover association rules: ex: ppl who bought {x,y,z} tend to buy {v,w, ex: frequently bought together items on amazon. Item: a product s/a milk large # of items. Basket(transaction): a subset of items: ex: the things one customer buys on one visit, each basket contains a few items, large # of baskets. Baskets = sets of products someone bought in one trip to the store (many baskets, but each basket contains few items) Ex: amazon"s people who bought x also bought y- think about it as a simple recommendation system. Frequent itemsets: simplest question: find sets of items that appear together frequently in baskets.