PUBG Winner Ranking Prediction using R Interface ‘h2o’ Scalable Machine Learning Platform

Gaming is an important aspect of the new generation and with this aspect comes improvement, which can be concerning graphics, sounds, gameplay, interaction, or ranking. The ranking is a healthy competition where different players can know standing around the globe, which makes them more competitive and help them stand above all. PUBG is multiplayer gaming that is supported on various platforms with a huge number of players online every day. This huge number can lead to a huge ranking, to overcome this difficulty there is a package in R programming called H2O which helps the developer to work with large numbers of datasets and also apply all different types of algorithms ranging from Machine Learning as well as Deep Learning and various unsupervised Learning. The algorithms used in this research are Linear Regression, Random Forest in the category of Machine Learning & Deep Neural Network in the category of Deep Learning. The metric evaluation of all these algorithms was carried out by using MAE (Mean Absolute Error) for the ranking of different players.