Model Building and Evaluation for Data Scientists

Building and evaluating machine learning (ML) models is daunting, but correctly engineered models can provide millions of dollars in value. In this course, you'll learn to build and evaluate these tools, leveraging existing data science knowledge.

Building and evaluating machine learning (ML) models unlocks a myriad of rewarding business opportunities for organizations that are able to do so effectively. But what skills do data scientists, with a strong understanding of statistics, data warehousing, and data analysis, need to master before they can create an effective ML model? In this course, Model Building and Evaluation for Data Scientists, you’ll learn a solid foundation of model building and evaluation fundamentals, with the core skills needed to begin building and deploying your own models. First, you’ll learn to match different kinds of datasets and business success requirements to the model type that is best suited to make inferences from that data or achieve that goal. Next, you’ll explore advanced data processing and preparation techniques, such as feature engineering and continuous data pipelines, which can all be used to improve model performance and outcomes. Finally, you’ll discover how to evaluate models, understand evaluation metrics, and adjust data and model training pipelines to optimize performance. When you’re finished with this course, you’ll have the skills of ML model building and evaluation needed to train and evaluate models of several different types and improve their performance, and the knowledge to continue learning more ML skills.

• Course Overview 1min
• Turning Data into Effective ML Models 13mins
• Evaluating and Optimizing ML Models 13mins