This course offers a comprehensive understanding of state-of-the-art predictive analytics using networked data in R. The primary objective of network analytics is to predict the classification of network nodes, such as identifying churners, fraudsters, defaulters, and more. To achieve this, we explore how to effectively utilize information from the network and its underlying structure in a predictive manner. One key concept we introduce is featurization, which involves incorporating network features alongside non-network features to enhance the performance of analytical models. Throughout the course, you will utilize the igraph package to create and label a customer network in a churn scenario, while also gaining a solid foundation in network learning. Additionally, we delve into the concepts of homophily, dyadicity, and heterophily, and demonstrate how these can provide valuable exploratory insights within your network. Leveraging the functionality of the igraph package, you will learn how to compute various network features, including both node-centric and neighbor-based features. Moreover, we explore the application of the Google PageRank algorithm to calculate network features and empirically validate their predictive capabilities. Finally, we guide you through the process of generating a flat dataset from the network and analyzing it using logistic regression and random forests. By the end of this course, you will have acquired the skills and knowledge necessary to perform advanced predictive analytics on networked data, enabling you to make informed decisions and gain valuable insights from complex network structures.