Recommender%20Systems%20and%20Product%20Semantics

1
Recommender Systems and Product Semantics

• Rayid Ghani Andy FanoAccenture Technology Labs

Workshop on Recommendation Personalization in
E-CommerceMay 28, 2002
2
Who we are?Accenture Technology Labs

• RD Group for Accenture
• 40 researchers in Chicago, Palo Alto
  (California) and Sophia Antipolis (France)
• Research in Data Mining, Machine Learning,
  Ubiquitous Computing, Wearable Computing,
  Language Technologies, Virtual Augmented
  Reality, Collaborative Workspaces

3
What Does a Transaction Mean?

• Terabytes of transaction data.
• But what does any one transaction mean?
• What does it tell us about the customer?

4
Example Apparel

• Transactional information captured by retailers
• Date of Purchase
• SKU
• Price
• Size
• Brand
• But what does this tell me about the customer who
  bought it?

5
Product SemanticsWhat does a product mean?

• What does this shirt say about her?
• Is it conservative or flashy?
• Trendy or classic?
• Formal or casual?
• Where would we get this information?

6
Where do people get this information?Marketing

• Product Companies and Retailers spend fortunes
  telling customers what their products mean.
• Our idea
• Build a system that analyzes marketing texts to
  infer these attributes.

7
Example

• From the Macys web site
• DKNY Jeans Ruched Side-Tie Tee
• Get back to basics with a fresh new look this
  season. The Ruched Side-Tie Tee has a drawstring
  tie at left hip with shirred detail down the
  side. Stretch provides a flattering, shapely fit.
  V-neck.

8
Training the System
9
Inferring Attributes via Text Classification

• Build one classifier per attribute type
• Simple statistical classifier Naïve Bayes
  Multinomial model (McCallum Nigam 1998)
• For all words (description) and attribute values
• calculate P(word attribute value) using the
  manually rated items
• Given a new item description
• Calculate P(attribute value item description)
  for all attribute values
• Use Maximum Likelihood

10
Semi-supervised Learning

• Lot of product descriptions available for minimal
  cost
• Labeling them is expensive
• Apply magical algorithms that combine labeled and
  unlabeled data for classification
• EM (Nigam et al. 1999), Co-Training (Blum
  Mitchell 1999), Co-EM (Nigam Ghani), ECo-Train
  (Ghani, 2002)

11
The EM Algorithm
Estimate labels
Learn from labeled data
Naïve Bayes
12
A Peek at the Learned Models
Not Conservative (Flashy)
rose special leopard chemise straps flirty spray silk platform
Extremely Conservative
lauren ralph breasted seasonless trouser jones sport classic blazer
Lauren Single-Breasted BlazerSporty elegance and
classic Gatsby-esque styling are captured in this
impeccably designed single-breasted, three-button
blazer from Lauren by Ralph Lauren. With
traditional notch collar, signature button
hardware, front flap pockets, and signature crest
on left breast pocket.
Bias Slip DressThe perfect black dress gets
flirty and feminine in the bias-cut slip dress
with sheer ruffled cap sleeves. A low, scoop neck
and back is ultra-flattering while a draped,
romantic fit reveals total elegance.
13
A Peek at the Learned Models
formal
jacket fully button skirt lines seam crepe leather
Informal
jean tommy denim sweater pocket neck tee hilfiger
BLACK TRIACETATE JACKET
A fresh alternative to classic suiting. Wear open for cardigan effect, buttoned for a clean look. Hidden placket with four tonal buttons and a hook-and-eye closure at the collar. Falls to hip. Lined.
Polo Jeans Co. Muscle Logo TeeStrut your stuff
in the Muscle Logo Tee. Flattering on the arms
with a close-to-the-body fit, classic crewneck
and shimmery logo print with stars. A sporty new
basic for your tee collection.
14
A Peek at the Learned Models
Partywear
rock dress sateen length skirt shirtdress open platform plaid flower
Loungewear
chemise silk kimono calvin klein august lounge hilfiger robe gown
ABS by Allen Schwartz Asymmetrical Dress Just for
the party girl with a big feminine streak. A
ruffled one-shoulder cuts diagonally across the
front and back. Accented with a rhinestone detail
on the shoulder.
15
A Peek at the Learned Models
Extremely Sporty
sneaker camp base rubber sole white miraclesuit athletic nylon Mesh
Juniors
jrs dkny jeans tee collegiate logo tommy polo short sneaker
DKNY Jeans Jrs. Mesh Jersey SweaterAn innovative
take on the football jersey, the see-through mesh
sweater is a fashion favorite among the sporty
set. Denim appliqué
16
Populating the Knowledge Base
17
Recommender System
RetailersWeb Site
Learned Statistical Models
ExtractedDescriptions of Products Browsed
EvolvingUser Profile
Query the Knowledge Base forMatching Products
Recommend Matching Products to User
Product Semantics Knowledge Base
18
(No Transcript)
19
(No Transcript)
20
(No Transcript)
21
(No Transcript)
22
(No Transcript)
23
Advantages over Traditional Recommendation Systems

• This approach provides us some of the
  underlying attributes that characterize a
  customers preference.
• We can therefore begin to explain the
  preference rather than simply rely on the
  co-occurrence of purchases (e.g. people who
  bought x also bought y).
• This helps with
• Handling new products/rapidly changing products
• Low Frequency Products
• Cross Category Recommendations

24
Cross-Category Recommendations

• Difficult for collaborative filtering and
  content-based systems
• Build a model of the user - personality,
  stylistic attributes
• Taste in clothing might also be suggestive of
  taste in other products, say furniture and home
  decoration
• Create models for different product classes and
  create mappings among these models

25
Summary

• Understand a product and hence the customer
• Use Text Learning (supervised and
  semi-supervised) to abstract from product
  (description) to subjective, domain-specific
  features
• Effective for new (and low frequency) products
  and for cross-category recommendations