A majority of the global population subscribe to mobile networks, also known as cellular networks. Thus, optimizing mobile traffic would bring benefits to many people. The downlink user throughput in cellular networks is subject to heavy fluctuations, which leads to inefficient use of network capacity. The underlying network protocols address this issue by making use of adaptive content delivery strategies. An example of such a strategy is to maximize the video stream resolution with respect to the available bandwidth. However, the currently dominating solutions are reactive and hence take time to adapt to bandwidth changes. In this work, a deep learning framework for downlink user throughput prediction is proposed. Accurate throughput predictors could provide information about the future downlink bandwidth to the underlying protocols that would let them become proactive in their decision making and adapt faster to resource changes. The models are trained with novel loss functions that capture the different costs of overestimation and underestimation. They are based on feedfordward and LSTM networks and achieve up to 79.4 % accuracy.