Build regression models with Amazon Redshift ML

 Build regression models with Amazon Redshift ML

With the rapid growth of data, many organizations are finding it difficult to analyze their large datasets to gain insights. As businesses rely more and more on automation algorithms, machine learning (ML) has become a necessity to stay ahead of the competition.

Amazon Redshift, a fast, fully managed, widely used cloud data warehouse, natively integrates with Amazon SageMaker for ML. With Amazon Redshift ML, you can use simple SQL statements to create and train ML models from your data in Amazon Redshift and then use these models for a variety of use cases, such as classification of a binary or multiclass outcome or predicting a numeric value through regression. Amazon SageMaker Autopilot provides all the benefits of automatic model creation, but as an advanced user, you can also influence the model training by providing different parameters such as model type, objective, and so on.

Amazon Redshift ML allows you to address several ML challenges, such as the following:

  • Binary classification – Predict a true/false outcome, such as whether a customer will churn. To explore this specific use case further, see Create, train, and deploy machine learning models in Amazon Redshift using SQL with Amazon Redshift ML.
  • Multiclass classification – Identify the class of an input value within a discrete number of classes. For example, you can identify which will be the best-selling product.
  • Regression – Predict a numerical outcome, like the price of a house or how many people will use a city’s bike rental service.

You can use Amazon Redshift ML to automate data preparation, pre-processing, and selection of problem type as depicted in this blog post. In this post, we assume that you have a good understanding of your data and what problem type you want to use for your use case. We demonstrate how to use Amazon Redshift ML to solve a regression problem predicting bike rental counts. We also provide some best practices for creating test data, validating your model, and using it for inference. We also show you how you can use the SageMaker console to troubleshoot the training process as an advanced user.

Prerequisites

As a prerequisite for implementing the example in this post, you need to set up an Amazon Redshift cluster with ML enabled on it. For the preliminary steps to get started, see Create, train, and deploy machine learning models in Amazon Redshift using SQL with Amazon Redshift ML.

Solution overview

In this post, we use Amazon Redshift ML to build a regression model that predicts the number of people that may use the city of Toronto’s bike sharing service at any given hour of a day. The model accounts for various aspects, including holidays and weather conditions. Because we need to predict a numerical outcome, we create a regression model.

We wa

[...]

Source - Continue Reading: https://aws.amazon.com/blogs/machine-learning/build-regression-models-with-amazon-redshift-ml/

webmaster

Related post