Streaming ML

SymetryML is driving an evolution in machine learning with its cutting edge, Kafka-native, streaming machine learning, which provides several unique benefits that conventional (batch) learning can’t support.

  • SML
  • Confluent
  • Kafka
Introducing StreamingML For Event-Stream Processing Architecture

SymetryML's proprietary online learning algorithms & models provide streaming machine learning & exploration, unlocking an entirely new level of real-time capabilities.

Click Here To Get The SymetryML Kafka Connector From The Confluent Hub

Email us at and we'll get you set up with a SymetryML license and answer any questions about the connector and streamingML

SymetryML integrates very well with Kafka allowing for the unique capabilities:

  • Separation between predictive model building and data ingestion. This allows to perform continuous ML - as the stream of data is coming from a Kafka topic – to build various predictive models using any of your features as the target variables as well as using any other features as inputs variables.
  • No Rescan of your Kafka Topic is ever needed to build multiple, different predictive models.
  • SymetryML can scale with many Kafka Topics with multiple partitions, this will be covered in a subsequent blog post.
  • SymetryML can automatically adapt to Kafka Topic schema change. If your data schema changes a lot, this will is great feature to have.
  • Extensive exploration API that allows you to get various real-time metrics from your streaming data.

Other Technical Highlights:

  • Explore your data in real time with the Exploration API
  • Real-Time support for many for supervised classification, regression and sequence models
  • Various Real-time unsupervised anomaly & clusterning algorithms & models
  • Rest-API for developers & Web-UI for business & analytics users
  • Streaming ML with Kafka

  • SymetryML "Fusion Project"


Schedule a demo