As 5G deployments continue to increase worldwide, new applications can fully leverage the exceptional features of the emerging mobile networks. Ultra-Reliable Low Latency Communications (URLLC) serve as an excellent example of applications highly sensitive to jitter and packet loss. To meet these demanding requirements, 5G relies on network slicing, network virtualization, and software-defined networks. This ecosystem enables the precise allocation of resources for each network slice. However, the applications’ resource demands may vary over time. In this challenging and overwhelming environment, traditional human decision-making for slice reconfiguration is not suitable anymore, due to the multitude of parameters and the need for extremely fast response times. Machine Learning (ML) comes as a tool that can enable better use of the available resources with faster and more intelligent management. This paper introduces an ML model that can predict slices’ traffic and dynamically reconfigure computational capacity. With these forecasting capabilities, the virtualized resources can be fine-tuned to suit the slices’ requirements, guaranteeing their Quality of Service (QoS). By doing so, Mobile Network Operators can make optimized use of the equipment, tailoring their needs to each service while complying with the QoS level. The results obtained demonstrate that the proposed ML model, in combination with a specific set of hysteresis rules, can accurately predict the saturation of virtualized capacity with up to 91% accuracy and proactively adapt it to the network slice requirements.