The session explains discretization by grouping continuous data into intervals (binning) in order to simplify the data, reduce noise, and improve algorithm performance. The value of binning lies in the fact that an application can efficiently predict user needs or avoid overloads. The value of the session is a few additional design tools for optimizing solutions operating on large data volumes.

The session takes about 40 minutes and goes through types of binning, explaining variance and deep dives into binning evaluation metrics. Binning is one of the fundametal tools for big data analysis. During the session, Visual Studio will be used to show some code and how it works.