Soil is highly heterogeneous. The process of formation makes the nature of soil highly variable. Thus, it’s a great challenge to ensure safety in geotechnical engineering structures. Field tests are rarely performed in shallow foundations because of the high cost and lengthy duration of the process. This research proposes the use of artificial intelligence (AI) techniques to forecast the bearing capacity of a shallow foundation by simulating it with data collected from trials performed in various laboratories and published in the literature. The data is split into a training set (consisting of 70% of the total) and a testing set (consisting of 30% of the total). The testing dataset is used to evaluate the performance of the trained AI-based model. More specifically, several performance parameters are used to evaluate the model’s prediction accuracy.