In this talk we will discuss the exciting journey towards Machine Learning (ML) based zero day malware detection in a production environment. We will talk about the usual ML steps such as data harvesting, feature extraction, classification algorithm optimisation, model training, and evaluation. We will demonstrate the steps on a simple classifier assembled during the talk. Having a functioning ML model is great but how do you get it to real customers? The remainder of the talk will be devoted to discussion of the production environment specifics and how to address them. Finally, we will practically show how to turn our ML model into a high throughput, low latency REST service.

After this talk, students should be able to combine several popular technologies (Python Scikit-learn and Openscoring) to create a scalable and maintainable ML driven service.