200 likes | 424 Views
The Dynamics of Viral Marketing Jure Leskovec Lada Adamic Bernardo A. Huberman Stanford University University of Michigan HP Labs. Presented by Leman Akoglu March 2010. Targeted marketing. Why need Viral Marketing?. Personalized recommendations Cross-selling
E N D
The Dynamics of Viral MarketingJure Leskovec Lada Adamic Bernardo A. Huberman Stanford University University of Michigan HP Labs Presented by Leman Akoglu March 2010
Targeted marketing Why need Viral Marketing? • Personalized recommendations • Cross-selling • “people who bought x also bought y” • Collaborative filtering • “based on ratings of users like you…” Viral marketing We are more influenced by our friends than strangers. 68% of consumers consult friends and family before purchasing home electronics (Burke 2003) Our friends know about our needs/tastes better.
The paper in a nutshell • Analysis of a person-to-person recommendation network (June 2001 to May 2003) • 4 million people • 0.5 million products • 16 million recommendations Contributions: • Data statistics • Propagation, cascade sizes • Network effects • Effectiveness of viral marketing on product and pricing categories
recommendations people Music CDs and DVDs have the most/least number of items, respectively. Still, DVDs account for than half of all recommendations. Number of unique edges for Books, Music and Videos is less than number of customers –suggests many disconnected components
Largest connected component at the end contains ~2.5% of the nodes. • Total number of nodes grow linearly over time. • The service itself was not spreading epidemically.
recommendations people … buy+no discount buy+get discount • Influence: 1) Books (1/69) • 2) DVDs (1/108) • 3) Music (1/136) • 4) Video (1/203) • People tend to buy books when they • can get a discount whereas for DVDs • discount does not matter much.
Lag between time of recommendation and time of purchase Book DVD daily periodicity 40% of those who buybuy within a day but > 15% wait morethan a week
Contributions of the paper: • Data statistics • Propagation, cascade sizes • Network effects • Effectiveness of viral marketing on product and pricing categories
Identifying cascades steep drop-off shallow drop off t+t’’’ very few large cascades t+t’’ t t+t’ t … t t’’’ > t’’ > t’ Cascade size: 6 DVD cascades can grow large
Propagation model (produces power-law cascade-size distribution) • Each individual will have ptsuccessful recommendations. • pt:[0,1] • At time t+1, the total number of people in the cascade, Nt+1 = Nt * (1+pt)
Propagation model (produces power-law cascade-size distribution) • Summing over long time periods • The right hand side is a sum of random variables and hence normally distributed. (Central Limit Theorem) • Integrating both sides, N is log-normally distributed if s large resembles power-law
Contributions of the paper: • Data statistics • Propagation, cascade sizes • Network effects • Effectiveness of viral marketing on product and pricing categories
Question: Does receiving more recommendations increase the likelihood of buying? (receiver’s perspective) DVDs BOOKS • Book recommendations are rarely followed. • A peak at 2, and then a slow drop (!) • For DVDs, saturation is reached at 10 –diminishing returns
Question: Does sending more recommendations yield more purchases? (sender’s perspective) DVDs BOOKS • To too few –changes of success is low versus to everyone –spam effect • For Books, the number of purchases soon saturates. • For DVDs, the number of purchases increases throughout.
Question: Do multiple recommendations between two individuals weaken the impact of the bond on purchases? BOOKS DVDs YES! --Less is more…
Contributions of the paper: • Data statistics • Propagation, cascade sizes • Network effects • Effectiveness of viral marketing on product and pricing categories
Recommendation success by book category • Success rate: # of purchases following a recommendation / # recommenders • Books overall have a 3% success rate • Lower than average success rate • Fiction • romance (1.78), horror (1.81) • teen (1.94), children’s books (2.06) • comics (2.30), sci-fi (2.34), mystery and thrillers (2.40) • Nonfiction (personal & leisure) • sports (2.26) • home & garden (2.26) • travel (2.39) • Higher than average success rate • professional & technical • medicine (5.68) • professional & technical (4.54) • engineering (4.10), science (3.90), computers & internet (3.61) • law (3.66), business & investing (3.62)
What determines a product’s viral marketing success? Modeling recommendation success -- by linear regression Over 50K products s : success βi : Coefficient xi :
Modeling recommendation success significance at the 0.01 (***), 0.05 (**) and 0.1 (*) levels • # senders and receivers have negative coefficients, showing that successfully recommended products are actually more likely to be not so widely popular • more expensive and more recommended products have a higher success rate • avg. rating does not affect success much
Contributions of the paper: • Data statistics • Propagation, cascade sizes • Network effects • Effectiveness of viral marketing on product • and pricing categories Questions & Comments