Although numerous models have been employed to address the issue of landslide susceptibility at regional scale, few have incorporated landslide typology into a model application. Thus, the aim of the present study is to perform landslide susceptibility zonation taking landslide classification into account using a data-driven model. The specific objective is to answer the question: how to select reasonable influencing factors for different types of landslides so that the accuracy of susceptibility assessment can be improved? The Qilihe District in Lanzhou City of northwestern China was undertaken as the test area, and a total of 12 influencing factors were set as the predictive variables. An inventory map containing 227 landslides was created first, which was divided into shallow landslides and debris flows based on the geological features, distribution, and formation mechanisms. A weighted frequency ratio model was proposed to calculate the landslide susceptibility. The weights of influencing factors were calculated by the integrated model of logistic regression and fuzzy analytical hierarchy process, whereas the rating among the classes within each factor was obtained by a frequency ratio algorithm. The landslide susceptibility index of each cell was subsequently calculated in GIS environment to create landslide susceptibility maps of different types of landslide. The analysis and assessment process were separately performed for each type of landslide, and the final landslide susceptibility map for the entire region was produced by combining them. The results showed that 73.3% of landslide pixels were classified into “very high” or “high” susceptibility zones, while “very low” or “low” susceptibility zones covered only 3.6% of landslide pixels. The accuracy of the model represented by receiver operating characteristic curve was satisfactory, with a success rate of 70.4%. When the landslide typology was not considered, the accuracy of resulted maps decreased by 1.5~5.4%.