2017 ARecommenderSystemforHeroLineUp
- (Hanke & Chaimowicz, 2017) ⇒ Lucas Hanke, and Luiz Chaimowicz. (2017). “A Recommender System for Hero Line-Ups in MOBA Games.” In: Proceedings of AIIDE-2017.
Subject Headings: DOTA 2, Video Game Hero, [[
Notes
Cited By
Quotes
Author Keywords
Abstract
MOBA games are currently one the most popular online game genres. In their basic gameplay, two teams of multiple players compete against each other to destroy the enemy's base, controlling a powerful unit known as “hero”. Each hero has different [[character ability|abilities, roles and strengths. Thus, choosing a good combination of heroes is fundamental for the success in the game. In this paper we propose a recommendation system for selecting heroes in a MOBA game. We develop a mechanism based on association rules that suggests the more suitable heroes for composing a team, using data collected from a large number of DOTA 2 matches. For evaluating the efficacy of the line-up, we trained a neural network capable of predicting the winner team with a 88.63% accuracy. The results of the recommendation system were very satisfactory with up to 74.9% success rate.
1 Introduction
MOBA Games have become one of the most played genres in recent years. Games such as League of Legends (LOL) or Defense of the Ancients 2 (DOTA 2) have attracted millions of online players and also become important platforms for e-sports tournaments, which distribute millions of dollars in prizes. In its basic gameplay, two teams of five players compete against each other to destroy the enemy’s base. Each player controls a powerful unit known as “hero” or “champion”, which is responsible for defeating enemy’s armies and defensive structures and, acting together, make the team advance in the game.
Each of these games has more than one hundred heroes that can be picked by players, each one with different abilities, roles and strengths. Thus, choosing a good combination of heroes is fundamental for the success in the game. The combination of heroes in a team is generally called line-up and the number of possible combinations surpasses 1016 in a game such as DOTA 2.
In this paper we present a recommendation system for picking heroes in a MOBA game. By collecting data from thousands of DOTA 2 matches, we were able to develop a mechanism based on association rules that indicates the more adequate heroes for composing a team line-up against another team. For evaluating the efficacy of the line-up, we trained a neural network that, given two teams, is capable of predicting the winner team with a good accuracy.
…
References
;
| Author | volume | Date Value | title | type | journal | titleUrl | doi | note | year | |
|---|---|---|---|---|---|---|---|---|---|---|
| 2017 ARecommenderSystemforHeroLineUp | Lucas Hanke Luiz Chaimowicz | A Recommender System for Hero Line-Ups in MOBA Games |