160 likes | 300 Views
Consumer Profiling using Fuzzy Query and Social Network Techniques. Sema Alptekin, F. Olcay Cirit, Masoud Nikravesh. Consumer Profiling Targeted Advertising Increased Revenue. Sema Alptekin, F. Olcay Cirit, Masoud Nikravesh. Traditional Profiling vs. Social Profiling.
E N D
Consumer Profilingusing Fuzzy Query and SocialNetwork Techniques Sema Alptekin, F. Olcay Cirit, Masoud Nikravesh
Consumer ProfilingTargeted AdvertisingIncreased Revenue Sema Alptekin, F. Olcay Cirit, Masoud Nikravesh
Traditional Profilingvs.Social Profiling Sema Alptekin, F. Olcay Cirit, Masoud Nikravesh
Motivating Research:HomophilyInnovation Diffusion Sema Alptekin, F. Olcay Cirit, Masoud Nikravesh
Innovation Diffusion Implication: It is easiest to sell to those nearest the sold. Sema Alptekin, F. Olcay Cirit, Masoud Nikravesh
How and Why Web Communities Should Collect Social Data Sema Alptekin, F. Olcay Cirit, Masoud Nikravesh images used without permission. sorry!
Unifying Different Modalities:ChatMessage BoardsVoiceVideo7% 38% 55% Sema Alptekin, F. Olcay Cirit, Masoud Nikravesh
Why is online correspondence a good measure? • Immediacy Principle • Models ‘Buzz’ • Easy to track, more Honest Sema Alptekin, F. Olcay Cirit, Masoud Nikravesh
The “Club” Profiling Model: The Chess Club The Acme Widget Buyer’s Club Sema Alptekin, F. Olcay Cirit, Masoud Nikravesh
BISC Decision Support System - Fuzzy Queries over a Database - G.A. for Query Refinement - Perfect for Traditional Profiling Sema Alptekin, F. Olcay Cirit, Masoud Nikravesh
Integrating Traditional Profiles with Social Profiles: • Calculate a dynamic S-Score for each person • Give this score to the DSS Sema Alptekin, F. Olcay Cirit, Masoud Nikravesh
A B S-Score: Significance & Derivation 0.4 0.1 • - If the Social Network is thought of as a • Fuzzy Relation, the S-Score is the direct image of the Club on that Relation. • - Can be implemented as one Matrix • Multiplication to calculate everyone’s score. • Conceptually, this score represents thesocial nearness of each person to the Club, or the amount of Buzz he/she might hear from/about the club. 0.6 0.2 C 0.2 0.5 0.1 0.5 D F 0.3 0.3 Sema Alptekin, F. Olcay Cirit, Masoud Nikravesh E A B C D E F A 1 0 .4 0 0 0 B 0 1 .1 0 0 0 C … …
New Customers Profiling Process “Blanket” Advertising Targeted Advertising Refine Profile Initial Customer List Potential Customers Initial Profile DSS Query Sema Alptekin, F. Olcay Cirit, Masoud Nikravesh S-Scores Other Data
Other Applications/Extensions • Customer Relationship Management: target more than just ads • Targeted Email Ads • Predicting political outcomes in Thai Parliament (Dowpiset 1999) • Anti-SPAM? Counter-terrorism? Sema Alptekin, F. Olcay Cirit, Masoud Nikravesh
Ethical/Legal Considerations • Does this constitute a privacy policy violation? Will people find it unpalatable? • Is maintaining this data a subpoena waiting to happen? • What if targeting tips off friends/family to embarrassing habits/conditions? Sema Alptekin, F. Olcay Cirit, Masoud Nikravesh
Conclusion • These ideas are hypothetical, representing a work in progress. • Work on this project will continue into the next year. • Any large web portals willing to take the plunge? Sema Alptekin, F. Olcay Cirit, Masoud Nikravesh