Recommender Systems and Product Semantics

Recommender Systems and Product Semantics

Rayid Ghani & Andy FanoAccenture Technology Labs

Workshop on Recommendation & Personalization in E-CommerceMay 28, 2002

Who we are?Accenture Technology Labs

R&D 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…

What Does a Transaction Mean?

Terabytes of transaction data.

But what does any one transaction mean?

What does it tell us about the customer?

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?

Product Semantics:What 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?

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.

Example

From the Macy’s 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.

Product Descriptions

Domain Experts

Product descriptionsmarked up with attribute values

SupervisedLearning Algorithm

Learned Statistical Models

Training the System

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

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)

The EM Algorithm

Naïve Bayes

Learn from labeled data

Estimate labels

Probabilistically add to labeled data

Extremely Conservative

lauren

ralph

breasted

seasonless

trouser

jones

sport

classic

blazer

A Peek at the Learned ModelsNot Conservative

(Flashy)

rose

special

leopard

chemise

straps

flirty

spray

silk

platformBias 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.

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.

Informal

jean

tommy

denim

sweater

pocket

neck

tee

hilfiger

formal

jacket

fully

button

skirt

lines

seam

crepe

leather

A Peek at the Learned Models

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.

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.

Loungewear

chemise

silk

kimono

calvin

klein

august

lounge

hilfiger

robe

gown

Partywear

rock

dress

sateen

length:

skirt

shirtdress

open

platform

plaid

flower

A Peek at the Learned Models

ABS by Allen Schwartz Asymmetrical DressJust 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.

Extremely Sporty

sneaker

camp

base

rubber

sole

white

miraclesuit

athletic

nylon

Mesh

Juniors

jrs

dkny

jeans

tee

collegiate

logo

tommy

polo

short

sneaker

A Peek at the Learned Models

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

Populating the Knowledge Base

NewProduct

Descriptions

Product descriptionsautomatically marked up with attribute values

Learned Statistical Models

Product Semantics Knowledge Base

Retailer’sWeb Site

ExtractedDescriptions of Products Browsed

Product Semantics Knowledge Base

Learned Statistical Models

EvolvingUser Profile

Query the Knowledge Base fo

r

Matching Products

Recommend Matching

Products to User

Recommender System

Advantages over Traditional Recommendation Systems

This approach provides us some of the underlying attributes that characterize a customer’s 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

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

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