How to read a user's mind? Designing algorithms for contextual recommendations
Submitted by Bharath Mohan (@bharathmohan) on Monday, 22 May 2017
Section: Crisp talk for data engineering track Technical level: Beginner
The human mind is going through thousands of thoughts everyday. A perfect recommender system needs to know what is going on and suggest something useful - at all times, without being perceived as intrusive or noisy. After slicing every possible sensor within the reach of a digital system - from the GPS, Accelerometer, Time of day, Temperature, Browsing History, TV Viewing, Sound, a “perfect recommender system” should learn which ones to give more importance to, predict the state of mind - in order to make the most effective recommendations. This talk takes an exemplary approach to derive some heuristics that can drive these algorithms.
Bharath Mohan is CEO of Sensara, a company that provides Smarter Live TV User Experience & Monetization. Sensara offers Smart Remotes, TV Search & Personalization, Smart TV Interfaces and TV Deep Data Mining. Bharath earlier worked for Google, and was part of the launch team in Google Finance, and also a technical lead for Google News. Bharath has a PhD in Computer Science from the Indian Institute of Science.