Player satisfaction is particularly difficult to ensure in online games, due to interactions with other players. In adversarial multiplayer games, matchmaking typically consists in trying to match together players of similar skill level. However, this is usually based on a single-skill value, and assumes the only factor of “fun” is the game balance. We present a more advanced matchmaking strategy developed for Ghost Recon Online, an upcoming team-focused first-person shooter (FPS) from Ubisoft (Montreal, QC, Canada). We first show how incorporating more information about players than their raw skill can lead to more balanced matches. We also argue that balance is not the only factor that matters, and present a strategy to explicitly maximize the players' fun, taking advantage of a rich player profile that includes information about player behavior and personal preferences. Ultimately, our goal is to ask players to provide direct feedback on match quality through an in-game survey. However, because such data were not available for this study, we rely here on heuristics tailored to this specific game. Experiments on data collected during Ghost Recon Online's beta tests show that neural networks can effectively be used to predict both balance and player enjoyment.

Beyond Skill Rating: Advanced Matchmaking in Ghost Recon Online

Account hijacking is considered one of the most serious security problems in online games A hijacker normally takes away valuable virtual items from the stolen accounts, and trades those items for real money Even though account hijacking is not uncommon, there is currently no general solutions to determine whether an account has been hijacked The game company is not aware of a hijack unless it is reported by the victim However, it is usually too late---usually a hijacker already took away anything valuable when a user finds that his/her account has been stolenIn this paper, we propose a new biometric for human identification based on users' game-play activities Our main summary are two-fold: 1) we show that the idle time distribution is a representative feature of game players; 2) we propose the RET scheme, which is based on the KullbackLeibler divergence between idle time distributions, for user identification Our evaluations shows that the RET scheme achieves higher than 90% accuracy with a 20-minute detection time given a 200-minute history size

/pdf/user-identification-based-on-game-play-activity-patterns-432avld9e4.pdf

User identification based on game-play activity patterns

Cyberspace plays an increasingly important role in people’s life due to its plentiful offering of services and information, e.g. the Word Wide Web, the Mobile Web and Online Games. However, the usability of cyberspace services is frequently reduced by its lack of customization according to individual needs and preferences.In this thesis we address the cyberspace customization issue by focusing on methods for user representation and prediction. Examples of cyberspace customization include delegation of user data and tasks to software agents, automatic pre-fetching, or pre-processing of service content based on predictions. The cyberspace service types primarily investigated are Mobile Commerce (e.g. news, finance and games) and Massively Multiplayer Online Games (MMOGs).First a conceptual software agent architecture for supporting users of mobile commerce services will be presented, including a peer-to-peer based collaborative filtering extension to support product and service recommendations.In order to examine the scalability of the proposed conceptual software agent architecture a simulator for MMOGs is developed. Due to their size and complexity, MMOGs can provide an estimated “upper bound” for the performance requirements of other cyberspace services using similar agent architectures.Prediction of cyberspace user behaviour is considered to be a classification problem, and because of the large and continuously changing nature of cyberspace services there is a need for scalable classifiers. This is handled by proposed classifiers that are incrementally trainable, support a large number of classes, and supports efficient decremental untraining of outdated classification knowledge, and are efficiently parallelized in order to scale well.Finally the incremental classifier is empirically compared with existing classifiers on: 1) general classification data sets, 2) user clickstreams from an actual web usage log, and 3) a synthetic game usage log from the developed MMOG simulator. The proposed incremental classifier is shown to an order of magnitude faster than the other classifiers, significantly more accurate than the naive bayes classifier on the selected data sets, and with insignificantly different accuracy from the other classifiers.The papers leading to this thesis have combined been cited more than 50 times in book, journal, magazine, conference, workshop, thesis, whitepaper and technical report publications at research events and universities in 20 countries. 2 of the papers have been applied in educational settings for university courses in Canada, Finland, France, Germany, Norway, Sweden and USA.

Scalable Agent-Based Simulation of Players in Massively Multiplayer Online Games

In this paper, we describe our work on classification of players in Massively Multiplayer Online Games using Hidden Markov Models based on player action sequences. In our previous work, we have discussed a classification approach using a variant of Memory Based Reasoning based on player action frequencies. That approach, however, does not exploit time structures hidden in action sequences of the players. The experimental results given in this paper show that Hidden Markov Models have higher recognition performance than our previous approach, especially for classification of players of different types but having similar action frequencies.

/pdf/mmog-player-classification-using-hidden-markov-models-yzqjzmnv0g.pdf

MMOG Player Classification Using Hidden Markov Models

The power of using machine learning to improve or investigate the experience of play is only beginning to be realised. For instance, the experience of play is a psychological phenomenon, yet common psychological concepts such as the typology of temperaments have not been widely utilised in game design or research. An effective player typology provides a model by which we can analyse player behaviour. We present a real-time classifier of player type, implemented in the test-bed game Pac-Man. Decision Tree algorithms CART and C5.0 were trained on labels from the DGD player typology (Bateman and Boon, 21st century game design, vol. 1, 2005). The classifier is then built by selecting rules from the Decision Trees using a rule- performance metric, and experimentally validated. We achieve ~70% accuracy in this validation testing. We further analyse the concept descriptions learned by the Decision Trees. The algorithm output is examined with respect to a set of hypotheses on player behaviour. A set of open questions is then posed against the test data obtained from validation testing, to illustrate the further insights possible from extended analysis.

/pdf/real-time-rule-based-classification-of-player-types-in-3ccwxkkhg1.pdf

Real-time rule-based classification of player types in computer games

In this paper, we discuss an approach for identiﬁcation of player types inmassively multiplayer online games (MMOGs). MMOGs provide fast growingonlinecommunities(Jarettet al.2003).Managingalarge-scalecommunityim-plies many challenges, such as identiﬁcation of player types, social structures,and virtual economic mechanisms, etc. In this paper, we address the challengeonidentiﬁcationofplayertypes.AsaﬁrststeptowarduseofrealMMOGdata,we demonstrate our approach using a PC

Identification of Player Types in Massively Multiplayer Online Games

Online game players are more satisfied with contents tailored to their preferences. Player classification is necessary for determining which classes players belong to. In this paper, we propose a new player classification approach using action transition probability and Kullback Leibler entropy. In experiments with two online game simulators, Zereal and Simac, our approach performed better than an existing approach based on action frequency and comparably to another existing approach using the Hidden Markov Model (HMM). Our approach takes into account both the frequency and order of player action. While HMM performance depends on its structure and initial parameters, our approach requires no parameter settings.

/pdf/classification-of-online-game-players-using-action-3rdk1f9qsp.pdf

Classification of Online Game Players Using Action Transition Probability and Kullback Leibler Entropy

The market of massively multiplayer online games (MMOGs) is expanding rapidly. MMOG business can be considered as eBusiness where CRM (Customer Relationship Management) is a key factor of success. This paper discusses an effective approach for player identification, the results of which can be exploited for CRM of MMOGs. A feature extraction method is proposed that is based on the frequency of each type of game items acquired by each player. To validate the proposed feature extraction method, experiments are conducted using game log data obtained from an MMOG simulator. The experimental results show that the proposed feature extraction method outperforms a method, previously proposed by the same authors, that is based on the frequency of each type of actions performed by each player.

MMOG Player Identification: A Step toward CRM of MMOGs

Generally action sequences of players in MMOGs (Massively Multiplayer Online Games) are lengthy and often contain consecutively meaningless actions. In our previous work, we have suggested a preprocessing algorithm using items instead of actions to improve classiflcation ability, and validated the results. In fact, the algorithm has limited applicability, because it is derived by a priori based on our observation of the simulated MMOG data. In this paper, we propose a more universal and efiective algorithm to transform action sequences to episode sequences. We show that episode sequences are more informative and improve the classiflcation ability over both action sequences and item sequences.

Episode Detection with Vector Space Model in Agent Behavior Sequences of MMOGs

In this chapter we have presented an efiective approach for identification of user types in virtual worlds. Two types of input features were discussed, action-based features and item-based features. The former type uses the information on the frequency of each type of action that each user performed. The latter one uses the information on the frequency of each type of item that each user acquired. AMBR, adopted as the classifier, could successfully identify the type of unknown user agents. In addition, it could give higher performance with the item-based features. In future work, we plan to conduct experiments using agents with more complicated behaviors and to investigate use of order information in either action sequences or item sequences. Eventually, we will apply our findings to real user data.

/pdf/user-type-identification-in-virtual-worlds-3tcsfgdxv3.pdf

Ji-Young Ho

Papers

Identification of Player Types in Massively Multiplayer Online Games

Classification of Online Game Players Using Action Transition Probability and Kullback Leibler Entropy

MMOG Player Identification: A Step toward CRM of MMOGs

Episode Detection with Vector Space Model in Agent Behavior Sequences of MMOGs

User Type Identification in Virtual Worlds