Pavement management and maintenance is an important aspect of pavement engineering. Maintenance and rehabilitation treatments should be chosen very carefully, considering financial resources and existing distress types. In jointed concrete pavements, transverse joint faulting is a key distress which considerably influences ride quality and road smoothness. There are many factors affecting joint faulting such as heavy traffic, pavement structure, climatic conditions, pavement age, etc. The condition of the base layer is one of those important factors, having a big effect in the performance of jointed concrete pavements. Base layer takes part in both early-age behaviour and long-term performance of jointed concrete pavements. In this research, Artificial Neural Networks (ANNs) and Multivariate Linear Regression (MLR) have been applied in order to predict joint faulting. Pavement age and different base layer parameters where considered in the analysis that used Long Term Pavement Performance (LTPP) project database. Research results show that ANNs approach can predict joint faulting in jointed concrete pavements successfully and more accurately, showing a high coefficient of multiple determination (R^2) values, besides very low amount of error.