The Mechanistic Empirical Pavement Design Guide (MEPDG) developed by the National Cooperative Highway Research Program (NCHRP) project 1-37A, is a very powerful tool for the design and analysis of pavements. The designer utilizes an iterative process to select design parameters and predict performance, if the performance is not acceptable they must change design parameters until an acceptable design is achieved. The design process has more than 100 input parameters across many areas, including, climatic conditions, material properties for each layer of the pavement, and information about the truck traffic anticipated. Many of these parameters are known to have insignificant influence on the predicted performance During the development of this procedure, input parameter sensitivity analysis varied a single input parameter while holding other parameters constant, which does not allow for the interaction between specific variables across the entire parameter space. A portion of this research identified a methodology of global sensitivity analysis of the procedure using random sampling techniques across the entire input parameter space. This analysis was used to select the most influential input parameters which could be used in a streamlined design process. This streamlined method has been developed using Multiple Adaptive Regression Splines (MARS) to develop predictive models derived from a series of actual pavement design solutions from the design software provided by NCHRP. Two different model structures have been developed, one being a series of models which predict pavement distress (rutting, fatigue cracking, faulting and IRI), the second being a forward solution to predict a pavement thickness given a desired level of distress. These thickness prediction models could be developed for any subset of MEPDG solutions desired, such as typical designs within a given state or climatic zone. These solutions could then be modeled with the MARS process to produce am “Efficient Design Solution” of pavement thickness and performance predictions. The procedure developed has the potential to significantly improve the efficiency of pavement designers by allowing them to look at many different design scenarios prior to selecting a design for final analysis.