You cannot have a machine learning platform that drives content recommendations without data. You also cannot properly measure the performance of recommendations without data. Data is key to monitoring, improving, and building complex recommendations systems that impact UX experiences. However, architecting a system that properly manages this data is important to allow for downstream clients to properly use, extract, and interact with said datasets.
Leemay Nassery explains the importance of data collection pipelines and walks you through efficiently storing various datasets. Along the way, Leemay shares how Comcast migrated its recommendations platform from bare-metal Hadoop infrastructure to an event-streaming cloud platform, comparing the legacy platform to the current cloud-based system and detailing how these changes improved the reliability, stability, and results generated by the respective downstream consumers like the company’s machine learning tier. Join in to learn how to avoid building a data pipeline jungle and ensure that the overall architecture meets the needs of your downstream data consumers.
Leemay Nassery is a senior engineer leading the recommendations and targeting engineering efforts at Comcast. She also sets the strategic direction for content personalization for Comcast’s Xfinity consumer-facing video products and leads efforts with A/B testing, testing and targeting, and producing the metrics to measure successful customer outcomes.
©2018, O’Reilly UK Ltd • (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