Milling chatter is a major challenge in manufacturing: it induces vibrations that can hinder machine performance and lifetime, precision, product quality and tool ware. As such, it should be prevented.
The current techniques for preventing milling chatter rely on trial and error processes, as well as expert operation. Such techniques do not allow for high levels of automation.

One further challenge in predicting this chatter vibration lies in a phenomenon known as *Concept Drift*, describing how statistical properties of a data set can change as time goes by. This means that a model trained on data acquired over a specific time period may decrease in performance over time.

**Goal:** Your objective in this hackathon is to build a Machine Learning based solution that predicts milling chatter based on vibration sensor data acquired from the milling machine spindle, and yet remains valid despite drifting of the dataset properties (test set).