This course teaches you how to optimize the performance of predictive models beyond the basics by implementing various data munging and wrangling techniques. The course continues the development of supervised learning models that begins in the Supervised Machine Learning Pipelines Using SAS(R) Viya(R) course and extends it to ensemble modeling. Running unsupervised learning and semi-supervised learning models is also discussed. In this course, you learn how to do feature engineering and clustering of variables, and how to preprocess nominal variables and detect anomalies. This course uses Model Studio, the pipeline flow interface in SAS Viya that enables you to prepare, develop, compare, and deploy advanced analytics models. Importing and running external models in Model Studio is also discussed, including open-source models. SAS Viya automation capabilities at each level of machine learning are also demonstrated, followed by some tips and tricks with Model Studio. <p>The self-study e-learning includes:<br><ul><li>Annotatable course notes in PDF format. <li>Virtual lab time to practice.</ul>
