Predictive analysis of mobile network traffic is fundamental for the next-generation cellular network.rnProactively knowing user demand allows telecom systems to perform optimal resource allocation.rnNowadays, telecom companies face a network congestion problem; this problem results in longer delays,rndrastic jitter, and excessive packet losses. As a result, the quality of service (QoS) of networksrndeteriorates, and the quality of experience (QoE) perceived by end-users will be unsatisfied. As arnsolution, different researchers used statistical and neural network models for the prediction of videornstreaming data traffic. However, these models did not incorporate self-similarity and long termrndependence characteristics of the video streaming data traffic. So, this study aims to predict the videornstreaming data traffic by using the Deep Learning, Long Short Term Memory (LSTM), model whichrnincorporates self-similarity and long term dependence.We have reviewed various kinds of literature,rnconference papers, journals, white papers, and books related to the prediction of video streaming datarntraffic to achieve the objective of this study. Ten months of data (from October 2018 to July 2019) ofrnvideo streaming data traffic information from five Radio Network Controllers (RNCs) of the UniversalrnMobile Telecommunication System (UMTS) network in the city of Addis Ababa (A.A) is collected.rnFinally, this research work result indicates that the LSTM model has 57.8% of MAE improvement ofrnforecasting error compared to the hybrid model, i.e., Seasonal Auto-Regression Integrated MovingrnAverage (SARIMA) and Extreme Learning Machine (ELM) model, which has the second lower error.rnThe overall results of this research work demonstrate that the LSTM model is an effective method forrnpredicting video streaming traffic to reflect temporal patterns. Such accuracy is vital to provide a betterrndynamic resource allocation for video streaming traffic.