Book Image

Advanced Machine Learning with R

By : Cory Lesmeister, Dr. Sunil Kumar Chinnamgari
Book Image

Advanced Machine Learning with R

By: Cory Lesmeister, Dr. Sunil Kumar Chinnamgari

Overview of this book

R is one of the most popular languages when it comes to exploring the mathematical side of machine learning and easily performing computational statistics. This Learning Path shows you how to leverage the R ecosystem to build efficient machine learning applications that carry out intelligent tasks within your organization. You’ll work through realistic projects such as building powerful machine learning models with ensembles to predict employee attrition. Next, you’ll explore different clustering techniques to segment customers using wholesale data and even apply TensorFlow and Keras-R for performing advanced computations. Each chapter will help you implement advanced machine learning algorithms using real-world examples. You’ll also be introduced to reinforcement learning along with its use cases and models. Finally, this Learning Path will provide you with a glimpse into how some of these black box models can be diagnosed and understood. By the end of this Learning Path, you’ll be equipped with the skills you need to deploy machine learning techniques in your own projects.
Table of Contents (30 chapters)
Title Page
Copyright and Credits
About Packt
Contributors
Preface
Index

Identifying the customer segments in wholesale customer data using k-means clustering


The k-means algorithm is perhaps the most popular and commonly-used clustering method from partitioning clustering type. Though we usually call the clustering algorithm k-means, multiple implementations of this algorithm exist, namely the MacQueen, Lloyd and Forgy, and Hartigan-Wong algorithms. It has been studied and found that the Hartigan-Wong algorithm performs better than the other two algorithms in most situations. K-means in R makes use of the Hartigan-Wong implementation by default.

The k-means algorithm requires the k-value to be passed as a parameter. The parameter indicates the number of clusters to be made with the input data. It is often a challenge for practitioners to determine the optimal k-value. Sometimes, we can go to a business and ask them how many clusters they would expect in the data. The answer from the business directly translates to be the k parameter value to be fed to the algorithm...