Using Machine Learning to Predict Game Outcomes Based on Player-Champion Experience in League of Legends

• URL: http://arxiv.org/abs/2108.02799v1
• Date: Thu, 5 Aug 2021 18:03:03 GMT
• Title: Using Machine Learning to Predict Game Outcomes Based on Player-Champion Experience in League of Legends
• Authors: Tiffany D. Do, Seong Ioi Wang, Dylan S. Yu, Matthew G. McMillian, Ryan P. McMahan
• Abstract summary: We propose a method for predicting game outcomes in ranked League of Legends (LoL) games based on players' experience with their selected champion. Using a deep neural network, we found that game outcomes can be predicted with 75.1% accuracy after all players have selected champions.
• Score: 0.13124513975412253
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: League of Legends (LoL) is the most widely played multiplayer online battle arena (MOBA) game in the world. An important aspect of LoL is competitive ranked play, which utilizes a skill-based matchmaking system to form fair teams. However, players' skill levels vary widely depending on which champion, or hero, that they choose to play as. In this paper, we propose a method for predicting game outcomes in ranked LoL games based on players' experience with their selected champion. Using a deep neural network, we found that game outcomes can be predicted with 75.1% accuracy after all players have selected champions, which occurs before gameplay begins. Our results have important implications for playing LoL and matchmaking. Firstly, individual champion skill plays a significant role in the outcome of a match, regardless of team composition. Secondly, even after the skill-based matchmaking, there is still a wide variance in team skill before gameplay begins. Finally, players should only play champions that they have mastered, if they want to win games.

Related papers

• People use fast, goal-directed simulation to reason about novel games [75.25089384921557]
  We study how people reason about a range of simple but novel connect-n style board games. We ask people to judge how fair and how fun the games are from very little experience.
  arXiv  Detail & Related papers  (2024-07-19T07:59:04Z)
• QuickSkill: Novice Skill Estimation in Online Multiplayer Games [19.364132825629465]
  Current matchmaking rating algorithms require considerable amount of games for learning the true skill of a new player. This is known as the ''cold-start'' problem for matchmaking rating algorithms. This paper proposes QuickSKill, a deep learning based novice skill estimation framework.
  arXiv  Detail & Related papers  (2022-08-15T11:59:05Z)
• GCN-WP -- Semi-Supervised Graph Convolutional Networks for Win Prediction in Esports [84.55775845090542]
  We propose a semi-supervised win prediction model for esports based on graph convolutional networks. GCN-WP integrates over 30 features about the match and players and employs graph convolution to classify games based on their neighborhood. Our model achieves state-of-the-art prediction accuracy when compared to machine learning or skill rating models for LoL.
  arXiv  Detail & Related papers  (2022-07-26T21:38:07Z)
• DraftRec: Personalized Draft Recommendation for Winning in Multi-Player Online Battle Arena Games [25.615312782084455]
  This paper presents a personalized character recommendation system for Multiplayer Online Battle Arena (MOBA) games. We propose DraftRec, a novel hierarchical model which recommends characters by considering each player's champion preferences and the interaction between the players. We train and evaluate our model from a manually collected 280,000 matches of League of Legends and a publicly available 50,000 matches of Dota2.
  arXiv  Detail & Related papers  (2022-04-27T07:46:17Z)
• Sequential Item Recommendation in the MOBA Game Dota 2 [64.8963467704218]
  We explore the applicability of Sequential Item Recommendation (SIR) models in the context of purchase recommendations in Dota 2. Our results show that models that consider the order of purchases are the most effective. In contrast to other domains, we find RNN-based models to outperform the more recent Transformer-based architectures on Dota-350k.
  arXiv  Detail & Related papers  (2022-01-17T14:19:17Z)
• Bandit Modeling of Map Selection in Counter-Strike: Global Offensive [55.41644538483948]
  In Counter-Strike: Global Offensive (CSGO) matches, two teams first pick and ban maps, or virtual worlds, to play. We introduce a contextual bandit framework to tackle the problem of map selection in CSGO and to investigate teams' pick and ban decision-making. We find that teams have suboptimal map choice policies with respect to both picking and banning. We also define an approach for rewarding bans, which has not been explored in the bandit setting, and find that incorporating ban rewards improves model performance.
  arXiv  Detail & Related papers  (2021-06-14T23:47:36Z)
• ELO System for Skat and Other Games of Chance [1.3706331473063877]
  The evaluation of player strength in trick-taking card games like Skat or Bridge is not obvious. We propose a new ELO system for Skat to overcome these weaknesses.
  arXiv  Detail & Related papers  (2021-04-07T08:30:01Z)
• Which Heroes to Pick? Learning to Draft in MOBA Games with Neural Networks and Tree Search [33.23242783135013]
  State-of-the-art drafting methods fail to consider the multi-round nature of a MOBA 5v5 match series. We propose a novel drafting algorithm based on neural networks and Monte-Carlo tree search, named JueWuDraft. We demonstrate the practicality and effectiveness of JueWuDraft when compared to state-of-the-art drafting methods.
  arXiv  Detail & Related papers  (2020-12-18T11:19:00Z)
• Interpretable Real-Time Win Prediction for Honor of Kings, a Popular Mobile MOBA Esport [51.20042288437171]
  We propose a Two-Stage Spatial-Temporal Network (TSSTN) that can provide accurate real-time win predictions. Experiment results and applications in real-world live streaming scenarios showed that the proposed TSSTN model is effective both in prediction accuracy and interpretability.
  arXiv  Detail & Related papers  (2020-08-14T12:00:58Z)
• Suphx: Mastering Mahjong with Deep Reinforcement Learning [114.68233321904623]
  We design an AI for Mahjong, named Suphx, based on deep reinforcement learning with some newly introduced techniques. Suphx has demonstrated stronger performance than most top human players in terms of stable rank. This is the first time that a computer program outperforms most top human players in Mahjong.
  arXiv  Detail & Related papers  (2020-03-30T16:18:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.