Market Basket Analysis
Problem: given a database of transactions of customers of
a supermarket, find the set of frequent items copurchased and analyze the association rules that is
possible to derive from the frequent patterns and how their
rankings vary for different relevance measures (confidence,
lift, etc.).
Input:
• supermarket.arff -- to be used with nodes: Association Rule
Learner, Association Rule Learner (Borgelt), and Item Set Finder
(Borgelt)
• supermarket_weka.arff – to be used with node FPGrowth
Learning curve
Problem: Show experimentally whether the following
statement is true or false:
• for a fixed test set of 1000 rows, the larger is the
training set the more accurate is the classier.
Input: census.arff
Customer Segmentation
Problem: given the dataset of RFM (Recency, Frequency
and Monetary value) measurements of a set of customers
of a supermarket, find a high-quality clustering using Kmeans and discuss the profile of each found cluster (in
terms of the purchasing behavior of the customers of each
cluster).
Input: rfm.arff
• Recency = no. of days since last purchase
• Frequency = no. of distinct shopping days
• Monetary = total amount spent in purchases