Multilayer Neural Network Model for Mixed martial arts Winner Prediction

The mixed martial arts, even one sport where multiple methods are employed, such as striking, jiu-jitsu, and various disciplines focused on combat. It's a popular and well-organized sport worldwide. It is one to one fighting sport where one side is marked with a red tag and the opponent is marked with a blue tag. This research aims to investigate and discover the winner of the contest through the impact of a multi-layer neural network-based deep learning model. In this machine-learning approach, combatants use several features to determine the winner. By applying these machine learning-based models we achieve a more than 10% increase in accuracy than previous studies. As the dataset is unbalanced accuracy could not only be used to assess the performance of the models, hence we have also obtained precision, recall, F1 score, and AUC score to validate the results.