Quantitative Evaluation of Predictive Analytics: A Comparative Study of Machine Learning Models in eSports Outcome Forecasting

DOI

10.2991/978-94-6463-540-9_16How to use a DOI?

Keywords

Pokémon; eSports games; logistic regression; KNN; neural networks; decision trees

Abstract

The popularity of video games such as Pokémon has led to victory prediction receiving increasing attention from researchers and the eSports industry. This study used a dataset containing a variety of Pokémon attributes (including type, attack, defence, speed, and special abilities) and machine learning algorithms such as logistic regression, K-nearest neighbors, neural networks, and decision trees, to predict the outcome of battles based on these attributes and to provide insights into the complex dynamics of Pokémon battles. The results of the study show that the neural network and decision tree outperformed the others, with speed, attack power, and character-type relationships being the most important factors in determining victory or defeat. The models were 95% accurate, highlighting their potential role in shaping strategic decisions in games. In addition to proving the models’ effectiveness, this work advances the field of predictive game analysis by emphasizing the crucial strategic components of winning Pokémon battles.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Yue Fei
PY  - 2024
DA  - 2024/10/16
TI  - Quantitative Evaluation of Predictive Analytics: A Comparative Study of Machine Learning Models in eSports Outcome Forecasting
BT  - Proceedings of the 2024 2nd International Conference on Image, Algorithms and Artificial Intelligence (ICIAAI 2024)
PB  - Atlantis Press
SP  - 137
EP  - 145
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-540-9_16
DO  - 10.2991/978-94-6463-540-9_16
ID  - Fei2024
ER  -