In the second BizTalks session, the audience was amazed by how analytics and AI can be applied for the consumption of entertainment. With the potential to improve personalization for users and capture engaging moments, the two speakers – Assistant Professor Carlos FERNANDEZ-LORIA of the Department of Information Systems, Business Statistics and Operations Management, and Associate Professor WANG Wenbo of the Department of Marketing, shared their findings in a lively discussion.
A Case Study at Spotify: Can AI Help Us Do Better Than A/B Testing?
A core component of Spotify’s value proposal is personalization, which means this music tool tries to ensure that the content you receive is tailored to you based on the music you love. In his research, Prof. Fernandez-Loria and his co-authors partnered with Spotify to help them decide what would be the best algorithmic for DJ to deploy for each user. They show how large experimental data can provide substantial value for personalization, particularly when algorithms are specialized for the task at hand. Learn more about the research here.
Social Listening with Moment-to-Moment Data: A New Tool for Video and Live Streaming
Prof. Wang’s research zooms in to find out where are the engaging moments of contents to consumers during the period of experience and how to capture and quantify such moments which have important business implications. He shows that moment-to-moment synchronicity (MTMS) strongly predicts appreciation of movies and can be evaluated at a finer level to identify engaging contents. This approach can be applied to improve the timing of in-show advertising and help content producers improve the content quality. Learn more about the research here.