To support complex data-intensive applications such as personalized recommendations, targeted advertising, and intelligent services, the data management community has focused heavily on the design of systems to support training complex models on large datasets. Unfortunately, the design of these systems largely ignores a critical component of the overall analytics process: the deployment and serving of models at scale. We present Velox, a new component of the Berkeley Data Analytics Stack. Velox is a data management system for facilitating the next steps in real-world, large-scale analytics pipelines: online model management, maintenance, and prediction serving. Velox provides end-user applications and services with a low-latency, intuitive interface to models, transforming the raw statistical models currently trained using existing offline large-scale compute frameworks into full-blown, end-to-end data products. To provide up-to-date results for these complex models, Velox also facilitates lightweight online model maintenance and selection (i.e., dynamic weighting). Velox has the ability to span online and offline systems, to adaptively adjust model materialization strategies, and to exploit inherent statistical properties such as model error tolerance, all while operating at “Big Data” scale.
National Science Foundation
Expeditions in Computing