Evaluating the ultimate bearing capacity of piles has been always an important concern for geotechnical engineers. Pile setup is a term which refers to an increase in bearing capacity of pile after a specific time. This increase is mainly considered relevant to the dissipation of excess pore water pressure created as a result of disturbance of the soil around the pile. Many researches have been centered on the investigation of pile setup and the factors influencing that. Results indicate that soil and pile properties can affect the occurrence and intensity of this phenomenon. The application of artificial intelligence such as artificial neural networks and evolutionary algorithms are considered as efficient and powerful methods for prediction and function finding purposes. Consideration of setup phenomenon during the process of pile design may lead to a reduction in pile dimensions which is economically beneficial. In this study, a comprehensive dataset containing information about 172 test piles derived from literature reviews, is used to develop Group Method of Data Handling (GMDH) and Gene Expression Programming (GEP) ) in order to predict the time-dependent increase in bearing capacity of pile foundations driven in cohesive soil. It is noticeable that to evaluate the efficiency of the ultimate model, data is randomly divided into training and testing data which the former includes and the latter has used data. Regarding the literature, various equations have been proposed to predict the pile setup, but most of them had been limited to the specific area, having the special geotechnical features. The most striking difference between this study and the previous researches is that the dataset used in this study includes different piles driven in soil with varied properties, therefore the resulting equation is more generalizable in comparison with other ones. GMDH is computational approach that operates in a similar pattern to artificial neural networks. In this system, dual combinations of input variables are created in the form of Kolmogorov-Gabor polynomials. Based on the evaluation criteria such as Root Mean Squared Error (RMSE) and determination coefficient ( ), the polynomials with higher accuracy are selected and introduced to the next layer as inputs. This repetitive approach is used to reach the best polynomials predicting the target variable of the project. GMDH is a self-organized system in which the number of required layers and neurons are determined during the running. Gene Expression Programming (GEP) is a computational program that uses multi-genic chromosomes (individuals) to represent the ultimate solution of problems in form of GEP expression trees. This approach which is invented by Ferreira is a natural development of the Genetic Algorithm (GA) and Genetic Program (GP). to investigate the correlation between independent and target variables, the multiple Linear regression (MLR) is implemented at the initial stage of the study. According to the evaluation criteria, GEP with the determination coefficient of 0.834 is found to be the most effective approach to predict set-up among the other ones used in this research. Keywords: Pile, Set-up, Time-dependent bearing capacity, Cohesive soil, Gene Expression Programming, Group Method of Data Handling