Recommendation systems are everywhere, and in data science, we often consider them to be a solved problem. However, a typical recommendation system approaches breakdown when it encounters real-world data and businesses. Shioulin Sam explores the limitations of classical recommendation approaches and explains how multimodal embeddings, an emerging technique from deep learning research, enable you to build a better system.
Classical recommendation approaches do not understandd the content of the items they are recommending. In addition, they suffer from the cold start problem and are unable to create recommendations for items or users they haven’t seen before. Multimodal embeddings allow you to uncover how semantic content of items relates to users preferences. This new capability can help solve common recommendation pitfalls, such as the cold start problem, and open up new product possibilities.
Shioulin Sam is a research engineer at Cloudera Fast Forward Labs, where she bridges academic research in machine learning with industrial applications. Previously, she managed a portfolio of early stage ventures focusing on women-led startups and public market investments and worked in the investment management industry designing quantitative trading strategies. She holds a PhD in electrical engineering and computer science from the Massachusetts Institute of Technology.
For exhibition and sponsorship opportunities, email strataconf@oreilly.com
For information on trade opportunities with O'Reilly conferences, email partners@oreilly.com
View a complete list of Strata Data Conference contacts
©2018, O'Reilly Media, Inc. • (800) 889-8969 or (707) 827-7019 • Monday-Friday 7:30am-5pm PT • All trademarks and registered trademarks appearing on oreilly.com are the property of their respective owners. • confreg@oreilly.com