Personalization of Supermarket Product Recommendations

1
Personalization of Supermarket Product
Recommendations

• IBM Research Report (2000)
• R.D. Lawrence et al.

2
Introduction

• Personalized recommender system designed to
  suggest new products to supermarket shoppers
• Based upon their previous purchase behaviour and
  expected product appeal
• Shoppers use PDAs
• Alternative source of new ideas

3
Introduction continued

• Content-based filtering
• based on what person has liked in the past
• measure of distance between vectors representing
• Personal preferences
• Products
• overspecialization

• Collaborative filtering
• items that similar people have liked
• Associations mining (product domain)
• Clustering (customer domain)

4
Product Taxonomy
Classes (99)
Fresh Beef
Petfoods ..
Soft Drinks ..
Subclasses (2302)
Dried Cat Food
Beef Joints
Dried Dog Food
Canned Cat Food
Friskies Liver (250g)
Products (30000)
5
Overview
Normalized customer vectors
Customer Purchase Database
Product Database
Data Mining Clustering
Cluster assignments
Products eligible for recommendation
Cluster-specific Product lists
Product list for target customers cluster
Data Mining Associations
Personalized Recommendation List
Matching Algorithm
Product affinities
6
Customer Model

• Customer profile
• Vector, C(m)s, for each customer
• At subclass level gt 2303 dim space
• Normalized fractional spending
• quantifies customers interest in subclass
  relative to entire customer database
• value of 1 implies average level of interest in a
  subclass

7
Clustering Analysis

• To identify groups of shoppers with similar
  spending histories
• Cluster-specific list of popular products used as
  input to recommender
• Clustered at 99-dim product-class level
• Neural, demographic clustering algorithms
• Clusters evaluated in terms of dominant
  attributes products which most distinguish
  members of the cluster

• Cluster 1 Wines/Beers/Spirits
• Cluster 2 Frozen foods
• Cluster 3 - Baby products, household items
  etc..

8
Associations Mining

• Determine relationships among product classes or
  subclasses
• Used IBMs Intelligent Miner for Data
• Apriori algorithm
• Support, Confidence, Lift factors
• Rule Fresh Beef gt Pork/Lamb
• Support 0.016
• Confidence 0.33
• Lift 4.9
• Rule BabyDisposable Nappies gt BabyWipes

9
Product Model

• Each product, n, represented by a 2303-dim vector
  P(n)
• Individual entries Ps(n) reflect the affinity
  the product has to subclass s.

• 1.0 if s S(n) (same subclass)

• Ps(n)

1.0 if S(n) ? s (associated subclass)

• 0.5 if C(s) C(n) (same class)

• 0.25 if C(n) ? C(s) (associated class)

0 otherwise
10
Matching Algorithm

• Score each product for a specific customer and
  select the best matches.
• Cosine coefficient metric used

C is the customer vector P is the product vector
s mn is the score between customer m and product
n smn ?n C(m). P(n) / C(m) P(n)

11
Matching Algorithm ctd.

• Limit recommendations for each customer to 1 per
  product subclass, and 2 per class.
• 10 to 20 products returned to PDA
• Previously bought products excluded
• Data from 20,000 customers
• Recommendations for 200

12
Results

• Recommendations generated weekly
• 8 months, 200 customers from one store
• Respectable 1.8 boost in revenue from
  purchases from the list of recommended products.
• Accepted Recommendations from product classes new
  to the customer
• Certain products more amenable to
  recommendations. Wine vs. household care.
  interesting recommendations

13
Summary

• Product recommendation system for grocery
  shopping
• Content and Collaborative filtering
• Purchasing history
• Associations Mining
• Clustering
• Revenue boosts 2