Diagnosis techniques using urine are non-invasive, inexpensive, and easy to perform in clinical settings. The metabolites in urine, as the end products of cellular processes, are closely linked to phenotypes. Although research using urine metabolome has many advantages, there can also be problems, such as multiple characteristic signals mixing or averaging into undistinguishable signals. As a result, it seems that univariate methods cannot identify precise boundaries between two groups, such as cancerous and normal samples. Moreover, due to individual differences in genetic makeup and heterogeneity in cancer progression, the analysis of combinatorial information from many variables seems to be more suitable than univariate analysis. In this study, we therefore propose classification models using multivariate classification techniques and develop an analysis procedure for classification studies using metabolome data. Through this strategy, we identified five potential urinary biomarkers for breast cancer with high accuracy and also proposed potential diagnosis rules to help in clinical decision making. After further validation with independent cohorts and experimental confirmation, these marker candidates will likely lead to clinically applicable assays for earlier diagnoses of breast cancer. This multivariate classification research is the second trial in metabolome analysis after Denkert et al. and the first for urine metabolome studies.