The aim of this study is to determine erosion risk classes and to generate their map in Ankara Guvenc Basin using geographic information system (GIS), remote sensing (RS) and statistical approaches with method of multi-criteria decision-making. Basin covers about 17.3 km(2). In order to determine erosion risk classes, seven criteria (texture, soil depth, precipitation, land use, elevation, slope and vegetation) that influence the occurrence of soil erosion, and sub-criteria of that seven criteria were taken into consideration. 1:25000 scale digital soil map and topographic map were used. In addition to that, Landsat 7 satellite images were used to generate the land use and vegetation cover map. Analytical hierarchy process (AHP) technique was used to determine the priorities of the each criteria while, the Z-score statistical analysis technique was used to determine the priorities of the sub-criteria. Finally, linear combination technique was used to determine classes of erosion risk. According to the obtained results, 45.9% of the basin area was identified as under high erosion risk.