Statistical teaching plays a key role in many areas of science, finance and industry. The following are some examples of learning problems:• Predict whether a patient hospitalized for a heart attack will have another heart attack. The forecast should be based on demographic, dietary, and clinical measurements of that patient.• Predict a stock price six months from now based on company performance and economic data.• Recognize numbers in a handwritten zip code based on a digitized image.• Estimate the amount of glucose in the blood a person with diabetes from the infrared absorption spectrum of that person's blood. • Identify risk factors for prostate cancer based on clinical and demographic variables. Learning theory plays a key role in the fields of statistics, data mining, and artificial intelligence, which intersect with the fields of technology. nicknames and other disciplines. This book is about data-driven learning. In a typical scenario, we have an outcome measure, usually quantitative (such as stock price) or categorical (such as heart attack or lack thereof), that we want to predict based on a variety of attributes (such as dietary data and measurements taken in during a clinical trial). We have a training data set that contains results and features for many objects (for example, people). Using this data, we create a prediction model, or learning algorithm, that will allow us to predict the outcome for new unseen objects. A good algorithm is an algorithm that accurately predicts such an outcome.