Breast cancer is the most prevalent female cancer in the world and its incidence is increasing, largely because of the Western lifestyle. There is a need, not only to predict women who will develop the disease, but also to apply drug and lifestyle measures in order to prevent the disease. Current risk prediction models are based on combinations of risk factors and have good predictive but low discriminatory power. New risk prediction methods might come from examination of single nucleotide polymorphisms in several genes or from an increased knowledge of the molecular and cellular biology of the breast, particularly with respect to aberrant gene expression and protein synthesis. These methods might also determine new targets for preventive agents and lifestyle change. Many potential preventive measures are available and some have been successful. New approaches are required, however, not only to prevent the disease but to devise methods for their assessment that do not require very large and expensive clinical trials.