Active Projects

Recommending Games

At a glance: There are hundreds of thousands of games on the market – how do we design systems to help people find the right ones?

People: Anders Drachen, Rafet Sifa, Christian Bauckhage, Fabian Hadiji, Christian Kersting and others.

Papers e.g.:

aDescription: People have hundreds of thousands of computer games to choose from, which makes finding games that fit your interests challenging. The problem mirrors that of finding the right book to read or music that fits your tastes, but is new in digital games because it is only within the last few years that the production of games has exploded, with an exponential increase in the number of games available. This represents not only a significant technical challenge but also a business opportunity. There are unprecedented opportunities to meet the needs of a variety of consumers in terms of matching needs with products. This form of recommendation is key to enhance user satisfaction with products. Towards addressing this challenge, we investigate behavioral patterns on Steam, the biggest game distribution platform in the world, catering to more than 170 million people worldwide. The project is focused on building fast, context-aware recommender systems to help players find games that suit their interests – and conversely help the industry find players that might be interested in their games. The project currently uses data covering over 5 billion hours of gameplay from more than 3000 games, and advanced machine learning methods to build recommender engines. For example via Archetype Analytics. In the context of machine learning, recommender systems are collections of supervised, unsupervised, reinforcement and hybrid learning techniques that aim to predict user’s preference or confidence level to a particular set of features based on the previously observed features. In essence, the goal is to provide personalized recommendations that suit the interests of the user in question. Recommender systems are virtually unheard of in digital games beyond basic notions such as popularity rankings.

E-sports analytics

At a glance: E-sports is a global phenomenon with millions of participants, and just in physical sports, amateur and professional players alike need to analyze their performance to help improve and make decisions.

People: Anders Drachen, Matthias Schubert, Tobias Mahlman, Diego Klabjan, Rafet Sifa, Christian Bauckhage, Fabian Hadiji, Christian Kersting and others.

Papers e.g.:

esportstournamentDescription: E-sports is the playing of computer games in a competitive environment, whether at the amateur or professional level. In recent years e-sports has become a global phenomenon and  has gained immense momentum, outcompeting many traditional sports in terms of the number of practitioners, prize pools and even viewership – and is a potential future Olympic discipline. In 2014 alone, 71 million people worldwide viewed competitive gaming, and tournament prices have reached 10 million dollars for first place. On the company side, considerable resources are being allocated to support the esports environment from the main companies in the domain such as Riot Games, Wargaming, Valve, Ubisoft and Turbine. The number of players active in the gaming community is also increasing, with individual games have dozens of millions of active players. Just like regular sports, e-sports practitioners, whether professionals or amateurs, need to analyze player behavior in order to facilitate training, commentating and overall development. But analyzing player behavior in a competitive digital game is a far more complex challenge than in e.g. soccer or basketball, because digital games provide a much greater variety of abilities to the players. This not the least because many of these games are set in fantastic environments that leave such mundane considerations as physics and reality and enters the realm of the fantastic. This means that e-sports analytics has to cover a wide variety of competitive games, from sport-simulation titles such as the FIFA-series of Soccer games to fantastical games such as League of Legends, which sees mythical heroes combating each other using everything from Medieval weapons to magical spells. E-sports analytics is very new. Millions of people worldwide generate their own statistics from matches, and tournaments use numbers heavily when describing games. However, the more sophisticated forms of analytics used in regular sports have yet to make a substantial impact in e-sports. The project seeks to change this, by applying advanced machine learning and data mining principles to finding patterns in the playstyles of e-sports players across amateur and professional levels, and developing visualization tools that allow players to take control of their stats and use them to improve.

Profiling Players

At a glance: Billions of people play digital games – what are the patterns in how we play, and can this be used in the design and marketing of games?

People: Anders Drachen, Rafet Sifa, Christian Bauckhage, Fabian Hadiji, Christian Kersting and others.

Paper e.g.:

bDescription: One of the most important challenges in contemporary big data analytics is to take the power of quantitative analysis and place it into the hands of everyone, not just trained analysts. Computer games can generate massive amounts of data about how people play them. Not only do these datasets have incredible volumes, they are also often very complex, high-dimensional and need to be analyzed fast in order to have business value. One problem is analyzing the data, another is making them, and the results of the analysis, accessible to the stakeholders that need to decide what actions to take based on the information obtained. The field of data visualization has grown up in the past decades to deal with the challenge of communicating data and analysis results. In games, given the often complex nature of the data we deal with, visualization is a particular challenge. Profiling is a widely used tool for analyzing complex behaviors and making the results actionable to companies. Profiling essentially means taking vast, complex consumer datasets and condensing them into sets of profiles, that describe overall – but different – patterns in the behavior of people. This project focuses on using machine learning techniques to develop actionable behavioral profiles of computer game players. The project has already results in about a dozen publications focusing on a variety of games from major commercial titles like Battlefield and Tera, to smaller indie titles, along the way paving the way for automated profiling tools to help game designers find out how their games are being played and the kinds of problems players may encounter on their way through a game.