Who this book is for
This book is for data scientists and machine learning developers who want to build effective predictive models easily using XGBoost. We’ve set out to provide you with hands-on examples that address common challenges we’ve experienced when applying machine learning in our professional careers. Our goal is for this to be a practical guide and provide you with reusable code that can be applied to multiple classification and prediction tasks.
Our target audience consists of the following:
- Data scientists: We’ll provide a deep dive into the XGBoost model, and comparisons of XGBoost to other classification and regression tree models, so you can properly select the right model for your needs. We’ll discuss data cleaning and feature engineering techniques for numeric, categorical, and time-series data so that all these data types can be effectively modeled with XGBoost.
- Machine learning developers: We’ll discuss modeling and performance metrics, which will enable you to monitor and compare models. We’ll also cover XGBoost hyperparameter tuning, using XGBoost in pipelines, and model deployment practicalities.
- Data practitioners: This book includes hands-on walk-throughs to get you up and running on XGBoost quickly. We also provide an approachable explanation of machine learning concepts and how the XGBoost algorithm functions to give you a solid foundation.
