Machine learning (ML) uses algorithms to help computers “learn” from and make predictions on large collections of data. Large databases of known-materials data have flourished in the field of material sciences, such as the materials genome project (APL Mater. 1, 011002, 2013), opening the possibility for novel research based on big data analytics. In this work, we use ML methods to find two-dimensional-layered materials in the materials genome project database. With standard supervised algorithms we classify 144 as binary layered-materials, which we analyze in detail to providing insights and statistics on low-dimensional materials. This work provides details and new insights on the application of machine learning for the computational discovery of materials.