(thesis advisor)Chris Prentice
We now trust online and digital reviews and recommendations systems to support and guide most of our decisions, from choosing a new restaurant, buying a new product or finding a good doctor. These systems use complex algorithms to analyze huge amounts of data and return the “best” results based on metrics such as page views, stars, like buttons, date, and other criteria that are frequently not clear for us.
However these systems frequently do no not reflect the way we exchange information and discover things offline. Instead of asking for the opinion of a crowd of strangers, we usually ask for the opinion of our friends, or even just one of them. That’s because our friends’ opinions are much more reliable and personalized according to known experiences and interests.
The growth of digital social networks and communication platforms such as Facebook and Twitter has made it possible to exchange information in real time with our friends. However, real time dynamics and functionality make it nearly impossible to search and/or organize data in a way that it can be effectively reused.
Modeled after offline users behaviors, BuddySight is a social recommendation engine powered by the user’s network of friends. It facilitates the exchange of personalized recommendations for local business and services, such as restaurants, stores, lawyers, doctors, mechanics, and more with our social networks.
Accessible online and in a mobile application, BuddySight allows users to request or give location-based recommendations to their friends. Creating a direct channel to exchange personalized recommendations with known and trusted people instead of depending on the aggregation of big amounts of data.
There’s more! What you see on this site is only what is viewable online. Please visit our website to find out more about what’s in the archives.