L' Ardissono, C' Barbero, A' Goy and G' Petrone

1
Adaptive Web Stores

• L. Ardissono, C. Barbero, A. Goy and G. Petrone
• Dipartimento di Informatica
• Universita di Torino, Torino, Italy
• liliana,cris,goy,giovanna_at_di.unito.it
• http//www.di.unito.it/seta

2
The problem

• electronic catalogs are difficult to browse
• they often contain very different types of
  information, or are not detailed enough
• eterogeneous people visit them
• people have different interests, backgrounds,
  interaction needs
• there is no single solution to satisfy all needs
  (see also Benyon93, Smith-etal97)

3
An improvement...

• Information Filtering Electronic Commerce
  systems focus on selecting items suitable to the
  users preferences (exploiting techniques like
  collaborative filtering, case-based reasoning,
  ...)
• An interesting expansion is the focus on the
  interactional aspects on the Web

4
Our goals

• customization of product descriptions
• presentation of different sets of features
• use of different linguistic descriptions to
  present features
• selection of the amount of information to present
  (to constrain the information load)
• suggestion of different items of a product

5
Personalization strategies in SETA

• To generate the pages our system
• identifies the user preferences and interests
• tailors the contents of the catalog pages to the
  user characteristics
• suggests the items best matching the preferences
  in the user profile

6
Relevant areas

• dynamic hypermedia (to generate Web pages on the
  fly)
• user modeling (to handle user profiles)
• knowledge-based systems (to handle the
  information about products and customers)
• distributed agent architectures (to exploit
  specialized agents within a complex system)

7
Representation of user profiles

• Classification data (age, job, )
• Personality traits (domain expertise, technical
  interest, aesthetic interest, receptivity)
• e.g. Domain Expertise
• ltlow, 0.9gt,ltmedium,0.1gt,lthigh,0gt
• Preferences
• e.g. Ease of use importance 1
• ltlow, 0gt,ltmedium,0.3gt,lthigh,0.7gt

8
A stereotype (Novice user)

• Classification data
• age importance 0.7 lt0-24,
  0.3gt,lt25-44,0.2gt, ...
• job importance 0.8 ltstudent,
  0.8gt,lt25-44,0.2gt, ...
• Personality traits
• domain expertise ltlow, 0.9gt,ltmedium,0.1gt,lthi
  gh,0gt
• technical interest ltlow,
  0.8gt,ltmedium,0.2gt,lthigh,0gt
• receptivity ltlow, 0.2gt,ltmedium,0.7gt,lthigh,0.
  1gt
• Preferences
• ease of use importance 0.9 ltlow,
  0gt,ltmed,0.2gt,lth,0.8gt
• quality importance 1 ltlow,
  0gt,ltmed,0.6gt,lthigh,0.3gt

9
Representation of items

• VivaVoce T200
• Features
• agenda20 numbers
• price Lit. 90.000
• Properties
• ease of use high
• quality high
• Link to database table
• NB the Features are typed slots (there are
  technical, aestetic features, etc.)

10
Page tailored to an expert user
11
Page tailored to a non-expert user
12
Key roles in the architecture I

• Communication with the Web (SessionMgr)
• Management of the interaction flow (DialogMgr)
• Generation of the catalog pages by applying
  personalization strategies (Personalization
  agent)
• Initialization and update of user profiles by
  applying user modeling acquisition rules (UMC)

13
Key roles in the architecture II

• Selection and rating of the items to suggest to
  the user (Product Extractor)
• Management of the Users DB (to maintain user
  profiles in a permanent way)
• Management of the Products DB (containing the
  information about items)
• Maintenance of the users shopping cart

14
Matching items to users

• the items to be suggested are scored on the basis
  of the preferences in the user profile
• the property values of each item are matched
  against the users preferences, to identify the
  best matching items
• in the scoring process, the importance of the
  users preferences is exploited to rule out
  irrelevant mismatching properties

15
The System Architecture
Usrs DB Mgr
Users DB
Stereotype KB
Personal Agent
UM-i
UMC
W e b S e r v e r
Prod Taxonomy
Product Extractor
Session Mgr
Dialog Context
Dialog Mgr
Extr Context-i
Shopping Mgr
Cart
Products DBMgr
ProductsDB
16
Three-tier architecture
II level
Solaris JDK 1.1.3 Java Web Server 1.1
I level
W e b S e r v e r
Browser_i
Session Mgr
Agents
Browser _k
Netscape, Ms Explorer
Users DB
Products DB
NT JDK 1.1.4 ODBC driver
III level
17
Conclusions

• SETA virtual store shell for the construction of
  Web stores capable of tailoring the interaction
  to the users needs
• Agent-based system, where agents have been
  associated to each basic role in the management
  of the interactions with customers
• Special attention has been posed on user modeling
  and personalization strategies