Waxy crude oil is a non-Newtonian fluid that presents numerous challenges when transported through pipelines. The precipitation of paraffin wax under low-temperature conditions transforms the single-phase liquid into a multiphase, interlocking gel-like structure, with the potential to block the pipeline below the pour point temperature. Although maintaining a continuous flow is essential, pipeline shutdowns are sometimes inevitable due to equipment maintenance, the installation of new equipment, and emergencies. This would further elevate the cooling process and form a gelled crude oil, making the restarting process complex and challenging. Several models have been developed to predict the restart pressure. In many instances, the formation of intra-gel voids and the compressibility of waxy crude oil were not considered, resulting in an over-predicted restart pressure and pipeline sizes. The study on the compressibility of waxy crude oil, principally due to the formation of intra-gel voids, is believed to provide a more accurate restart pressure for the flow assurance of waxy crude. It has also been observed that Artificial Intelligence, particularly Artificial Neural Networks (ANNs), has become increasingly prominent as a predictive tool across various fields. Therefore, this study is aimed at adopting an Artificial Neural Network to predict the compressibility of waxy crude oil under cooling mode. It was observed that the trained model provided an R2 value of more than 0.99 and a mean square error of less than 0.00494 for all restart pressures trained. The trained model provided prediction accuracy of the compressibility of waxy crude oil under different restart pressures and cooling modes. It can be concluded that ANN is a promising tool for predicting the compressibility of waxy crude oil, thereby improving flow assurance.