VIDEO: How Qordoba’s Architecture & Machine Learning Work

At the Spark Summit 2017 East, Michelle Casbon, our Director of Data Science, gave an under-the-hood look at our architecture, machine learning and how they power some of our localization features.

The challenge with supporting multiple locales is the maintenance and generation of localized strings, which are deeply integrated into all facets of going-to-market: design, development, marketing, sales, and support. To address these challenges at Qordoba, we’re using highly scalable technologies and machine learning to drive massive customer efficiencies.

In her presentation, Michelle describes the techniques we’re using to deliver:

  • Continuous deployment of localized strings
  • Live syncing across platforms (mobile, web, photoshop, sketch, help desk, etc.)
  • Content generation for any locale
  • Emotional response detection

Michelle also shares our architecture for handling billions of localized strings, in any language, including:

  • Scala and Akka as an orchestration layer
  • Apache Cassandra and MariaDB as a storage layer
  • Apache Spark for natural language processing
  • Apache Kafka as a message bus for reporting, billing, & notifications
  • Docker, Marathon, & Apache Mesos for containerized deployment

Check out the presentation and request a demo to see how Qordoba would work in your environment.

Request a demo

Thanks for signing up!

Check your email for information about your account signup process.

* Required fields