With the advent of 5G, the market has been expecting the immersive user experience with rich multimedia content. Meeting such requirements within the physical constraints of limited spectrum and infrastructure availability is a challenging task, which prevents operators to scale their services properly. Currently, mobile operators are forced to invest large amount of money in their infrastructure, in order to maximize the capacity by network densification and higher frequency reuse factors. The dark side of such trend is that infrastructure becomes more expensive, spectrum price is getting higher and total cost of ownership for operator increases drastically. Nowadays, with the rise of artificial intelligence, cloud and edge computing the network becomes more flexible that opens many opportunities to enhance the performance and user experience. In this paper, we propose a new approach for content management in mobile network by using predictive caching of rich multimedia content in edge servers. Proposed approach is based on the content popularity prediction by using recurrent neural networks, that allows to deliver corresponding content in the close proximity to the target end users by the time it will be needed. Simulation results show that the proposed model is more than 90% accurate for both daily and weekly timeframes. Furthermore, we develop a method of personalized content caching in user devices based on their subscriptions and preferences, to make sure that user will have the best experience. Proposed approach for content management allows to improve the overall network performance by proactive content caching during the time of low network load. Moreover, the proactive caching allows to download the content in the best quality, regardless of the network congestions and bottlenecks.