Mobile is driving the advertising discussion today as people of all ages spend more time on their devices. With more than 10,000 active applications, 16+ million daily ad engagements, and over a billion total app downloads, Tapjoy knows mobile advertising.
To ensure that users have the best application experience, Tapjoy has architected a data science service to handle ad-requests optimization and personalization in real time. Robin Li shares the critical considerations for building such a Lambda architecture and details the methods Tapjoy used to evaluate and implement its real-time architecture. In particular, Robin examines how Tapjoy achieved the end state—the effect of combining off- and online power together to turn sophisticated algorithms into serviceable, data-driven products.
Robin Li is a managing analytics engineer at Tapjoy, where he oversees the design, implementation, and maintenance of Tapjoy’s big data platforms for data science and analytics. Robin’s work involves architecture-level framework and platform building on top of big data technologies such as Hadoop, Spark, Vertica, and NoSQL. Previously, he worked in the financial service industry. Robin holds an MSc in computer science from Imperial College London.
Yohan Chin works as a head of data science at Tapjoy, – focus on personalized mobile advertising, audience targeting, in-app user LTV maximization. His team works on data science modeling/data science back-end engineering/data insight visualization. Prior to Tapjoy, he was a lead research scientist at MySpace, where he led to build personalized music/video recommendation and multiple other data science products with social networking data. He has Ph.D. in Computer Science from University of Texas Dallas, B.S. from Seoul National University.
©2017, 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. • firstname.lastname@example.org
Apache Hadoop, Hadoop, Apache Spark, Spark, and Apache are either registered trademarks or trademarks of the Apache Software Foundation in the United States and/or other countries, and are used with permission. The Apache Software Foundation has no affiliation with and does not endorse, or review the materials provided at this event, which is managed by O'Reilly Media and/or Cloudera.