Summary: The Gamer's Non-public Network (GPN) is a consumer/server know-how created by WTFast for making the community performance of on-line video games quicker and more reliable. GPN s use middle-mile servers and proprietary algorithms to better join on-line video-sport gamers to their sport's servers throughout a wide-area network. On-line video games are a large entertainment market and community latency is a key aspect of a player's aggressive edge. This market means many various approaches to network architecture are implemented by different competing corporations and that those architectures are consistently evolving. Making certain the optimal connection between a shopper of WTFast and the net game they want to play is thus an extremely difficult problem to automate. Using machine studying, we analyzed historical community data from GPN connections to explore the feasibility of community latency prediction which is a key part of optimization. Our subsequent step can be to collect reside data (together with client/server load, packet and port info and particular game state data) from GPN Minecraft servers and bots. MAIMERS.COM are going to use this info in a Reinforcement Learning model along with predictions about latency to change the purchasers' and servers' configurations for optimal community efficiency. These investigations and experiments will improve the quality of service and reliability of GPN systems.