Iletken @ Strands $100K Call for Recommender Start-Ups - RecSys08

60 %
40 %
Information about Iletken @ Strands $100K Call for Recommender Start-Ups - RecSys08
Technology

Published on October 24, 2008

Author: strands

Source: slideshare.net

Personally Relevant Content Based On Social Connections

Team M. Deniz OKTAR, BSc @ Koc University, Istanbul Firat GELBAL, MSc @ TU/e, Eindhoven Baris Can DAYLIK, BSc @ Koc University, Istanbul Selcuk ATLI, MSc @ RPI, New York Board of Advisors: Prof . James Hendler, Professor in Computer Science @ RPI, TWC Dr. Tarcan Kumkale, Assist. Prof. in Psychology @ Koc Dr. Oznur Ozkasap, Assist . Prof . in Computer Science @ Koc

M. Deniz OKTAR, BSc @ Koc University, Istanbul

Firat GELBAL, MSc @ TU/e, Eindhoven

Baris Can DAYLIK, BSc @ Koc University, Istanbul

Selcuk ATLI, MSc @ RPI, New York

Board of Advisors:

Prof . James Hendler, Professor in Computer Science @ RPI, TWC

Dr. Tarcan Kumkale, Assist. Prof. in Psychology @ Koc

Dr. Oznur Ozkasap, Assist . Prof . in Computer Science @ Koc

Problems No psychological or social aspect Rapidly emerging online media content like news feeds need special engine Computation time New user issue Critical mass problem Overspecialization Explicit feedback

No psychological or social aspect

Rapidly emerging online media content like news feeds need special engine

Computation time

New user issue

Critical mass problem

Overspecialization

Explicit feedback

Value Proposition Wisdom of the Crowd vs. Circle of Trust Social added value 3-layered Hybrid Engine Weighted social proximity graphs Multiple social graphs for different interests Implicit/explicit feedback vs 14 C It rains heavily in Eindhoven. Firat says: It rains heavily in Eindhoven.

Wisdom of the Crowd vs. Circle of Trust

Social added value

3-layered Hybrid Engine

Weighted social proximity graphs

Multiple social graphs for different interests

Implicit/explicit feedback

+ + Individual Interests + + + + + + + + + + + + Politics Technology Music Sports Relevance = α ∙ Content + β ∙ CF + θ ∙ Social Relevance = α ∙ Content + β ∙ CF + θ ∙ Social

+ + + + + + + + + Network Interests + + + + + + + Relevance = α ∙ Content + β ∙ CF + θ ∙ Social Relevance = α ∙ Content + β ∙ CF + θ ∙ Social

+ + + + + + + Circle of Trust Interests + + + + + + + + Relevance = α ∙ Content + β ∙ CF + θ ∙ Social Relevance = α ∙ Content + β ∙ CF + θ ∙ Social

+ + + + + + + + Interests’ Reconfiguration + + + + Relevance = α ∙ Content + β ∙ CF + θ ∙ Social

+ + + Interests’ Reconfiguration + + + + Sports Proximity + + + + +

+ + Interests’ Reconfiguration + + + + Politics Proximity + + + + + +

Smarter Social Ads Social Advertising: “ If your friends have it, then you will have it ” People are influenced by their friends iletken captures people that most influence their friends Opinion leaders are easy to find

Social Advertising:

“ If your friends have it, then you will have it ”

People are influenced by their friends

iletken captures people that most influence their friends

Opinion leaders are easy to find

Thanks Focus on developing the recommendation system. Add value to your social network. For more information: www.iletken-project.com

Focus on developing the recommendation system.

Add value to your social network.

For more information: www.iletken-project.com

Questions? New User/Critical Mass P oblem Social Capital Importance of Trust Why Different Chinese Song Problem Social Noise Thanks

New User/Critical Mass P oblem

Social Capital

Importance of Trust

Why Different

Chinese Song Problem

Social Noise

Thanks

Critical Mass Problem BACK Solution: Hybrid Engine

Trust is Value BACK

Social Capital BACK

Why Different Social Added Value Live Social Graphs BACK vs live updates on social graphs 14 C It rains heavily in Eindhoven. Firat says: It rains heavily in Eindhoven.

Social Added Value

Live Social Graphs

Chinese Song Problem BACK Time Songs of American User Relevance Songs of Chinese User Radiohead – Paranoid Android +++ Coldplay – X&Y Oasis – Wonderwall ++ Blur – Coffee and TV Greenday – Good Riddance +++ Foo Fighters – Big Me ... ... Franz Ferdiand – Take me Out

Social Noise Iletken uses Social Noise instead of Random BACK Noise = Random(t); vs Noise = Social Capital

Iletken uses Social Noise instead of Random

Add a comment

Related presentations

Related pages

5 Early Recommendation Technologies That Could Shake Up ...

International recommendation technology provider Strands has announced the five finalists in the Strands $100K Call for Recommender Start-Ups ... iletken ...
Read more

MyStrands Offers $100k for Best Recommender Start-up ...

MyStrands Offers $100k for Best Recommender ... for the best recommender start-up. The Strands $100,000 Call for Recommender Start-ups is essentially ...
Read more

Fırat Gelbal

Fırat Gelbal Amsterdam ... iletken Recommender Systems ... 3rd place with ‘iletken project’ in the Strands $100K Call for Recommender Start-Ups
Read more

Kişiselleştirmenin geleceği Strands.com

Strands Call for Recommender Start-ups ve İletken Projesi. ... İletken kişilerin hayat ... Cuma gunu projeler icin final var. ACM RecSys08 konferansinda ...
Read more

Gravity R&D - Wikipedia, the free encyclopedia

The data mining team of the company is actively doing research in the field of recommender ... Strands $100K Call for Recommender Start-ups ...
Read more

Judging Recommender Start-ups In Switzerland; Will ...

Judging Recommender Start-ups In ... and Strands, a recommender company MSG ... as part of their first-ever $100K Call For Recommender Start-Ups.
Read more

ILETKEN TERMIK HESAPLAR - Documents - Docslide.us

share iletken termik hesaplar.
Read more

M. Deniz OKTAR | LinkedIn

View M. Deniz OKTAR’S professional profile on LinkedIn. LinkedIn is the world's largest business network, helping professionals like M. Deniz OKTAR ...
Read more