Market Basket Analysis using Association Rule Mining
- Programming Assignment for Elective Course CS 176 (Data Mining)
- Mining association rules and frequent item sets allows for the discovery of interesting and useful connections or relationships between items.
- Apriori and FP-growth algorithms are used to mine association rules from a sample retail market basket data set. The results are then evaluated based on several interest measures (lift, IR, Kulc).
Objective
The objectives of the study are the following:
- to obtain association rules and analyze them for better decision support, better understanding of data, or increasing company profit using the Apriori Algorithm and FP-Growth Algorithm
- to analyze association rules based on relevance, interestingness, and correlation, and use lift, Imbalance Ratio (IR), and Kulczynski (Kulc) measure as correlation measures.
Methodology
A comprehensive description of the methodologies used is discussed in report.pdf.