Valorant Esports Pre-Match Betting Advisory System uses Machine Learning to Predict Winning Probability and Simulate Odds and Earning Projections

Pawar, Abhishek Mahendra (2024) Valorant Esports Pre-Match Betting Advisory System uses Machine Learning to Predict Winning Probability and Simulate Odds and Earning Projections. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

Over the last few years, the esports world has seen significant growth and Valorant has become the most popular competitive game. As a result of this growth, the betting market has grown, and however betting platforms that exist today still heavily rely on common statistical methods, which are not suitable in the case of the dynamic game. In this thesis, I present a machine learning-based pre-match betting advisory system to predict match outcomes of Valorant professional tournaments. The system goes over historical data like player and team statistics and matches details and uses that to forecast winning probabilities, simulate betting odds that seem genuine, and potential earnings. We implement a robust methodology on complex datasets involving data preprocessing, synthetic data generation using CTGAN and Gaussian Mixture Models, feature engineering, and model evaluation. We developed and compared multiple machine learning models including XGBoost, CatBoost, and a Hybrid Stacking model. We chose XGBoost as its scalability and efficiency make it good for deploying, and beat out others with 73% accuracy. The system consists of a user friendly Streamlit interface that will enable bettors to input a match and get winning probability and earnings projection. The paper points out possibilities of advanced machine learning in esports betting, The future improvements will focus on expanding to other games and improving accuracy with real time performance metrics.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Haycock, Barry UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science G Geography. Anthropology. Recreation > GV Recreation Leisure > Games and Amusements > Gambling Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning G Geography. Anthropology. Recreation > GV Recreation Leisure > Games and Amusements > Online Games
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	04 Sep 2025 09:11
Last Modified:	04 Sep 2025 09:11
URI:	https://norma.ncirl.ie/id/eprint/8770

Actions (login required)

View Item