Machine learning is a powerful tool for prediction, but with great power comes great responsibility. Data preparation/exploration and model selection is necessary, but does not have to be painful. This presentation will focus on machine learning as a process, from data preparation to decision making. Exploration will include a high level discussion of several machine learning techniques, using breast cancer data from the University of Wisconsin. Accuracy and output of models will be explained and combined into a custom ensemble method, considering the implications of Type I and Type II classification errors. Although the modeling is executed in R-Studio, the process is relevant to users of various backgrounds and tools.