Sport is a global business into which passionate fans and smart corporations pour hundreds of billions of dollars. Particularly, football soccer detonates a great movement of money in bets, sponsorships, attendance to parties, sale of t-shirts and accessories, etc. Professional soccer has been in the market for quite some time. The sports management of soccer is awash with data, which has allowed the generation of several metrics associated with the individual and team performance. The aim is to find mechanisms to obtain competitive advantages. In this paper, we propose a procedure for predicting the outcome of a soccer match. The procedure consist of a Bayesian Model based on rank position along with a Machine Learning Model based on historical data of matches. The procedure was tested using a data set containing the results of over 200,000 soccer matches from different soccer leagues around the world and for predicting the outcome of the FIFA world cup 2018. The results shoed an improvement in accuracy and rank probability error compared with other methodologies.