Real-time communication (RTC) platforms have undergone a consistent increase in popularity in recent years and, nowadays, they are fundamental for both work and leisure purposes. To ensure adequate Quality of Experience (QoE) for users of RTC services, proper traffic management policies are needed that, when critical network conditions are detected, react by operating either at the network configuration level or on the application to improve QoE. However, predicting critical network conditions, and in particular packet losses that are particularly harmful to QoE, is a very challenging task. We propose a system for predicting losses that might occur in the near future (i.e., in a second) for RTP streaming traffic. We analyse several ML algorithms, from standard techniques, to Deep neural networks and Anomaly detection algorithms, and we apply them on more than 66 hours of data from two popular RTC applications. The selection of the algorithm and its tuning turns out to be fundamental to achieve good performance. In one of the best setting, which is based on a Balanced Random Forest classifier, we obtain a recall of 0.82.
