Subscribe to DSC Newsletter

Hey everyone,


   I am into area of analytics primarily into retail, CPG & advertising. I was curious to know the case of how machine learning is used in real time basis taking ecom sites like FB, Linkedin,etc.

Scenario:


Facebook shows a "people you may know" list based on your network and past interaction info. Now a user logs back(after a long time say 1 year) to facebook sees a list with 100 friend recommendations. As the user starts to add friends, will it be able to predict in real time other probable friends or be able to refine the list in real time. for instance, if out of the first 10 people shown in the list, user might choose to add 3 ignoring the 7 other. In such a case, the users recent input of selecting 3/10 be used for learning the recomendation engine? and be able to use the list for refining the remaining 90?If not, what is the latency involved in such learning ? 

    Would like to hear from you, if there are case studies or interesting finds about such a massive real time learning problem.

Regards

Deepak

http://bit.ly/Next-Gen-BI

Tags: analytics, engine, facebook, learning, linkedin, machine, recommendation

Views: 295

Reply to This

On Data Science Central

© 2021   TechTarget, Inc.   Powered by

Badges  |  Report an Issue  |  Privacy Policy  |  Terms of Service