One of the most challenging recent Vidora product initiatives involved real-time machine learning decisioning which we launched in late 2021 (learn more about real-time decisioning here). Real-time decisioning enables businesses to implement product experiences like next-best-action, next-best-offer, and dynamic decisioning using both real-time and historical data. Our engineering team built this experience from the ground up and pioneered new technology to enable these product experiences for our customers.

A big challenge we faced was enabling real-time featurization within the client. Specifically, how could we quickly build features using in-session user behaviors. This challenge required a light-weight SQL-like language for the client. Our team didn’t find any solution to meet our needs, so we decided to build a solution on our own and open source it for anyone to use.

Evin Sellin, one of Vidora’s engineering leaders, led the development of MistQL.

We were thrilled to see Evin’s work recognized and featured in Thoughtworks latest edition of Technology Radar.

MistQL supports JavaScript and Python implementation, allowing for it to be used in both client-side and server-side use cases. Learn more about MistQL here.

MistQL is a great example of how the Vidora engineering team continues to push the boundaries of what is possible for real-time machine learning. If you use MistQL, we would love to hear from you. Feel free to reach out to the team!

Relevant links on MistQL –

Want to Learn More?

Schedule a demo and talk to a product specialist about how Vidora’s machine learning pipelines can speed up your ML deployment and ultimately save you money.