In this video, we explain how Generalized Linear Models (GLM) work under the hood. The goal is to show you how this foundational machine learning technique can be used to make accurate classification predictions based on several independent variables.
We start by exploring a synthetic healthcare dataset, guiding you through the data preparation steps that are necessary for modeling a predictive solution such as normalization and one-hot encoding. You’ll see how Teradata’s ML library simplifies these tasks, enabling us to run analyses at scale. This demo is all about understanding how to apply GLM effectively, so we will discuss the importance of getting your data into the right format to ensure accurate model predictions.
By the end of the video, you’ll have a clear understanding of how GLM can be used in healthcare for predictive modeling. The demo highlights not only the results but the process, making it easy for you to follow along and apply these techniques in your own work.
Access Teradata’s ClearScape Analytics Experience:
TeradataML, Generalized Linear Model documentation:
Chapters:
00:00 Introduction
05:14 Analyzing independent variables for patient risk
06:42 Data preparation and transformation
15:44 Understanding the generalized linear model and its parameters
20:03 Model evaluation
23:00 Summary