The purpose of this book is to describe a methodology that has been established to schedule predictive maintenance of distribution transformers in the department of Cauca (Colombia) using machine learning. The proposed methodology is based on a predictive classification model that finds the minimum number of distribution transformers prone to failure. To verify this, the model was implemented and tested with real data in the Department of Cauca (Colombia). This methodology is a useful tool for decision making, which provides an ideal solution for predictive maintenance scheduling problems of distribution transformers.