Training a multi-class classification model using the Linear Learner model type
In this section, you will learn how to build a multi-class classification model in Amazon Redshift ML using the linear learner algorithm.
To do this, we will use a customer segmentation dataset from Kaggle: https://www.kaggle.com/datasets/vetrirah/customer.
You will use this dataset to train a model to classify customers into one of four segments (A
, B
, C
, or D
). By segmenting customers, you can better understand the customer and do targeted marketing to customers, with product offerings that are relevant to them.
Our data has already been split into training and testing sets and is stored in the following S3 locations:
s3://packt-serverless-ml-redshift/chapter06/segmentation/train.csv
s3://packt-serverless-ml-redshift/chapter06/segmentation/test.csv
After successfully connecting to Redshift as an admin or database developer, load data into Amazon Redshift as follows:
-
...