Most of the land use change modelers have used to model binary land use change rather than multiple land use changes. As a first objective of this study, we compared two well-known LUC models, called classification and regression tree (CART) and artificial neural network (ANN) from two groups of data mining tools, global parametric and local non-parametric models, to model multiple LUCs. The case study is located in the north of Iran including cities of Sari and QaemShahr. Urban and agricultural changes over a period of 22 years between 1992 and 2014 have been model. Results showed that CART and ANN were effective tools to model multiple LUCs. While it was easier to interpret the results of CART, ANN was more effective to model multiple LUCs. In earlier studies, despite using CART, the extraction of effective factors of LUCs using a precise index has not been considered efficiently. As a second objective, this study performed a sensitivity analysis using variable importance index to identify significant drivers of LUCs. While ANN was a black box for sensitivity analysis, CART identified significant delivers of LUCs easy. The results showed that the most important factors were distance from urban areas and rivers while aspect was the least effective factor. As a third or final objective of this study, the recently modified version of receiver operating characteristics (ROC) called total operating characteristic (TOC) as well as ROC were used for accuracy assessment of CART and ANN. The area under the ROC curves were 78% and 75% for urban changes for ANN and CART models, respectively. The area under the ROC curves were 72% and 65% for agricultural changes for ANN and CART models, respectively. We found that although TOC and ROC were similar to each other, TOC proved more informative than conventional ROC as a goodness-of-fit metric. The outcome of this study can assist planners and managers to provide sustainability in natural resources and in developing a better plan for future given the needs to understand those contributing factors in urban and agriculture changes.