Tianshi Zhu

Software Engineer

Tianshi is one of the Tech Leads on ML Infra team at Stripe. The team builds out the platforms to power Stripe's fraud detection systems and other ML products. Prior to that, he worked on Sigma team at Stripe and Search Infra team at linkedin. Tianshi has spent the last six years on big data and large real-time systems. He graduated from UPenn with a Master's degree in Electrical Engineering.

Tuesday, October 1
2:30 pm
2:55 pm
Robertson 2
We introduce Semblance, a machine learning feature generation system for both model training and real time prediction. Semblance is based on the foundation of Functional Reactive Programming, enabling a programming model which guarantees that features are correct by construction with regard to time ordered events. Semblance features are platform agnostic, which allows the same feature definition to be evaluated in different platforms, such as Scalding, Spark, Flink, Storm, or other similar map-reduce style or stream processing systems. In addition, Semblance enables a lambda architecture system, which we have implemented in production to evaluate features in real time within a few milliseconds.
© 2020 TWIMLcon. All rights reserved.