With the era of big data and the rapid increase in patient-specific information, there has been tremendous interest by the radiation oncology community in utilizing machine learning algorithms because of their ability to learn data dependencies from the current environment and generalize into unseen tasks. Application of machine learning currently covers varying areas of the radiation oncology field ranging from treatment response modeling, treatment planning, image-guidance, and motion tracking to quality assurance. In this chapter, we introduce some of the basic concepts of machine learning algorithms, the corresponding different learning approaches, and the process of validating their performance, particularly in the context of personalized radiotherapy and improving decision-making during treatment planning and adaptation. This will be further illustrated by a detailed representative example.