Author: Clive Cox

Seldon Core

Seldon Core 1.2 Release

The Seldon team are delighted to announce the release of version 1.2 of our open source model deployment platform for Kubernetes. The release follows our award win for ‘Best Innovation in Open Source Technology’ at the 2020 CogX Innovation Awards and provides several updates outlined below. Following the release, Seldon CTO Clive Cox commented “With…

Read Article

Seldon and Kubeflow 1.0

Here at Seldon, we’re immensely proud of the work we’re been doing on the KFServing project alongside other contributors from Google, Microsoft, Bloomberg and IBM — the official Kubeflow 1.0 release is a milestone worth celebrating. Kubeflow is Google’s solution for deploying machine learning stacks on Kubernetes and was built to address two major issues…

Read Article

Seldon 1.3.3 released with Kafka Streams

We’re pleased to release Seldon 1.3.3 with several changes: Analytics provided by Kafka Streams instead of Spark Streaming New Movielens 10 Million Demo Comprehensive benchmarking guide The 1.3.2 release of Seldon contained Spark streaming jobs to feed real-time analytics of running predictive API calls. However, Spark Streaming was quite a heavy requirement to enforce on…

Read Article

Seldon 1.3.2 with Grafana Analytics Dashboard

When we provide recommendation and predictive services to our enterprise customers, it’s important that we are able to keep track of and optimise the performance of the infrastructure as well as the impact of the recommendations and predictions on KPIs. We’re excited to include our favourite open-source analytics dashboard as a fully integrated component in Seldon’s machine learning infrastructure. The new 1.3.2 release…

Read Article

Seldon v0.94 release with user tag based affinity modelling and multiple dimensions

Aside from some performance improvements, there are two new functionality updates in this release. Firstly, a user tag based affinity modelling and item recommendation algorithm. This provides a simple use case where clients have keyword tagged items. The offline modeling stage associates users to tags they have interacted with more than the average user based…

Read Article

Seldon Release General Prediction Endpoint

Until now, Seldon has been focused on providing an enterprise-grade open-source recommendation engine – i.e. to suggest articles, videos, products to people based on behavioural and contextual data. In version 0.93, a general prediction endpoint is now available to developers. This major new feature allows easy integration of classification and regression machine learning models into…

Read Article

Seldon Microservices API for External Algorithms

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…

Read Article