Seldon has released a new Microservices API that allows developers to build their own real-time predictive scoring components and utilize them from within the Seldon predictive engine. This makes it simple to test and develop new predictive algorithms while taking advantage of the A/B testing, optimization and caching layers of Seldon.
Components can be added and removed with no downtime in production and A/B tested against existing algorithms. These additions make it easier for data science teams to quickly experiment and provide focused solutions to their specific business cases while taking advantage of the surrounding production-grade framework Seldon provides for a predictive data pipeline, such as data ingestion, A/B testing, algorithm switching, optimization, caching, filtering, and results combining.
For find out more about the Microservices API, please read the technical docs.