Book Image

Microsoft Azure Machine Learning

By : Sumit Mund, Christina Storm
Book Image

Microsoft Azure Machine Learning

By: Sumit Mund, Christina Storm

Overview of this book

Table of Contents (21 chapters)
Microsoft Azure Machine Learning
Credits
About the Author
Acknowledgments
About the Reviewers
www.PacktPub.com
Preface
Index

Model development


After preparing your data, you are not sure which model or regression algorithm would perform well for the problem at hand. Because the target variable P is continuous, you know that it's a regression problem. So, it would be worthwhile trying different algorithms and choosing the best one. You may use the Sweep Parameters module to obtain the optimum parameters for the algorithm. You need to pass three inputs to the Sweep Parameters module: the untrained algorithm, training dataset, and validation dataset. Use the Score modules to score the test data. Use an Evaluate module to compare the two models with the scored data.

You should try different algorithms to choose the best one. The following figure is just for your reference, which shows four algorithms.

Run the model and find out which algorithm performs the best for you.