Game bot detection using behavioral analysis
Authors
Dsilva, Warren
Issue Date
2020
Degree
MSc in Data Analytics
Publisher
Dublin Business School
Rights holder
Rights
Items in eSource are protected by copyright. Previously published items are made available in accordance with the copyright policy of the publisher/copyright holder.
Abstract
Online games and especially MMORPGs have become very popular and people are investing and spending thousands of dollars on such games. Enhancing the user-experience has become a challenge for companies as gaming bots have begun to populate most of the games. In this paper, we battle this problem by using behavioural analysis of players to detect and differentiate between bots and human players. Feature selection was a key factor in this process as choosing the right features enabled to get higher accuracy rates. Feature selection techniques such as Rank importance were used to select the most important features to train the data. The data was then fit using classification algorithms such as Naïve Bayes, Random Forest, Generalized Linear Model and Ensemble technique. The results indicate that the Random Forest algorithm performs the best with an accuracy of 96%