Mobile Legend: Bang Bang (MLBB) Win-Lose Prediction by Using Machine

SITI RUBIAH, MUSLIM (2023) Mobile Legend: Bang Bang (MLBB) Win-Lose Prediction by Using Machine. [Final Year Project Report] (Unpublished)

	PDF SITI RUBIAH (24 pgs).pdf Download (444kB)
	PDF (Please get the password by email to repository@unimas.my , or call ext: 082-583914/3973/3933) SITI RUBIAH ft.pdf Restricted to Registered users only Download (3MB)

Abstract

Mobile Legends: Bang Bang achieved the highest number of global downloads among free multiplayer online battle arena (MOBA) games, with an impressive count of over 4.7 million downloads across both Google Play and the Apple App Store combined in July 2022. Since then, a number of studies incorporating machine learning have been conducted for this mobile game, mostly focused on attempting to anticipate the actions of the players and predict the outcome of the match. This research study’s goal is to propose a machine learning approach to win and loss prediction in MLBB by using Logistic Regression and to measure the performance of the machine learning model. This study involves collecting and pre-processing game statistics data, such as hero, role, kill, death, gold gained, hero damage, turret damage and damage taken from 30 gameplay where Google Colab will be used to develop and testing the model. According to the findings, the logistic regression models had achieved 0.8 accuracy indicates the model is capable of generalizing well to new data and has a reasonably good predictive performance. Overall, this study contributes to the growing body of knowledge in e�sports analytics and showcases the power of machine learning in revolutionizing competitive gaming.

Actions (For repository members only: login required)

View Item