Players of digital games face numerous choices as to what kind of games to play and what kind of game content or in-game activities to opt for. Among these, game content plays an important role in keeping players engaged so as to increase revenues for the gaming industry. However, while nowadays a lot of game content is generated using procedural content generation, automatically determining the kind of content that suits players' skills still poses challenges to game developers. Addressing this challenge, we present matrix- and tensor factorization based game content recommender systems for recommending quests in a single player role-playing game. We discuss the theory behind latent factor models for recommender systems and derive an algorithm for tensor factorizations to decompose collections of bipartite matrices. Extensive online bucket type tests reveal that our novel recommender system retained more players and recommended more engaging quests than handcrafted content-based and previous collaborative filtering approaches.

Mobile digital games are dominantly released under the freemium business model, but only a small fraction of the players makes any purchases. The ability to predict who will make a purchase enables optimization of marketing efforts, and tailoring customer relationship management to the specific user's profile. Here this challenge is addressed via two models for predicting purchasing players, using a 100,000 player dataset: 1) A classification model focused on predicting whether a purchase will occur or not. 2) a regression model focused on predicting the number of purchases a user will make. Both models are presented within a decision and regression tree framework for building rules that are actionable by companies. To the best of our knowledge, this is the first study investigating purchase decisions in freemium mobile products from a user behavior perspective and adopting behavior-driven learning approaches to this problem.

Behavioral game analytics has predominantly been confined to work on single games, which means that the cross-game applicability of current knowledge remains largely unknown. Here four experiments are presented focusing on the relationship between game ownership, time invested in playing games, and the players themselves, across more than 3000 games distributed by the Steam platform and over 6 million players, covering a total playtime of over 5 billion hours. Experiments are targeted at uncovering high-level patterns in the behavior of players focusing on playtime, using frequent itemset mining on game ownership, cluster analysis to develop playtime-dependent player profiles, correlation between user game rankings and, review scores, playtime and game ownership, as well as cluster analysis on Steam games. Within the context of playtime, the analyses presented provide unique insights into the behavior of game players as they occur across games, for example in how players distribute their time across games.

Coronary heart disease (CHD) is a major cause of death worldwide.In the U.S. CHD is responsible for approximated 1 in every 6 deaths with a coronary event occurring every 25 seconds and about 1 death every minute based on data current to 2007.Although a multitude of cardiovascular risks factors have been identified, CHD actually reflects complexinteractions of these factors over time. Today's datasets from longitudinal studies offer great promise to uncover these interactions but also pose enormous analytical problems due to typically large amount of both discrete and continuous measurements and risk factors with potential long-range interactions over time.Our investigation demonstrates that a statistical relational analysis of longitudinal data can easily uncover complex interactions of risks factors and actually predict future coronary artery calcification (CAC) levels --- an indicator of the risk of CHD present subclinically in an individual --- significantly better than traditional non-relational approaches.The uncovered long-range interactions between risk factors conform to existing clinical knowledgeand are successful in identifying risk factors at the early adult stage. This may contribute to monitoring young adults via smartphones and to designing patient-specific treatments in young adults to mitigate their risk later.

Pre-symptomatic drought stress prediction is of great relevance in precision plant protection, ultimately helping to meet the challenge of "How to feed a hungry world?". Unfortunately, it also presents unique computational problems in scale and interpretability: it is a temporal, large-scale prediction task, e.g., when monitoring plants over time using hyperspectral imaging, and features are `things' with a `biological' meaning and interpretation and not just mathematical abstractions computable for any data. In this paper we propose Dirichlet-aggregation regression (DAR) to meet the challenge. DAR represents all data by means of convex combinations of only few extreme ones computable in linear time and easy to interpret.Then, it puts a Gaussian process prior on the Dirichlet distributions induced on the simplex spanned by the extremes. The prior can be a function of any observed meta feature such as time, location, type of fertilization, and plant species. We evaluated DAR on two hyperspectral image series of plants over time with about 2 (resp. 5.8) Billion matrix entries. The results demonstrate that DAR can be learned efficiently and predicts stress well before it becomes visible to the human eye.

The paper describes ongoing integrated research on designing intelligent robots that can assist humans in making a situation assessment during Urban Search & Rescue (USAR) missions. These robots (rover, microcopter) are deployed during the early phases of an emergency response. The aim is to explore those areas of the disaster hotzone which are too dangerous or too difficult for a human to enter at that point. This requires the robots to be "intelligent" in the sense of being capable of various degrees of autonomy in acting and perceiving in the environment. At the same time, their intelligence needs to go beyond mere task-work. Robots and humans are interdependent. Human operators are dependent on these robots to provide information for a situation assessment. And robots are dependent on humans to help them operate (shared control) and perceive (shared assessment) in what are typically highly dynamic, largely unknown environments. Robots and humans need to form a team. The paper describes how various insights from robotics and Artificial Intelligence are combined, to develop new approaches for modeling human robot teaming. These approaches range from new forms of modeling situation awareness (to model distributed acting in dynamic space), human robot interaction (to model communication in teams), flexible planning (to model team coordination and joint action), and cognitive system design (to integrate different forms of functionality in a single system).

Inspired by “GoogleTM Sets” and Bayesian sets, we consider the problem of retrieving complex objects and relations among them, i.e., ground atoms from a logical concept, given a query consisting of a few atoms from that concept. We formulate this as a within-network relational learning problem using few labels only and describe an algorithm that ranks atoms using a score based on random walks with restart (RWR): the probability that a random surfer hits an atom starting from the query atoms. Specifically, we compute an initial ranking using personalized PageRank. Then, we find paths of atoms that are connected via their arguments, variablize the ground atoms in each path, in order to create features for the query. These features are used to re-personalize the original RWR and to finally compute the set completion, based on Label Propagation. Moreover, we exploit that RWR techniques can naturally be lifted and show that lifted inference for label propagation is possible. We evaluate our algorithm on a realworld relational dataset by finding completions of sets of objects describing the Roman city of Pompeii. We compare to Bayesian sets and show that our approach gives very reasonable set completions.

Internet memes are phenomena that rapidly gain popularity or notoriety on the Internet. Often, modifications or spoofs add to the profile of the original idea thus turning it into a phenomenon that transgresses social and cultural boundaries. It is commonly assumed that Internet memes spread virally but scientific evidence as to this assumption is scarce. In this paper, we address this issue and investigate the epidemic dynamics of 150 famous Internet memes. Our analysis is based on time series data that were collected from Google Insights, Delicious, Digg, and StumbleUpon. We find that differential equation models from mathematical epidemiology as well as simple log-normal distributions give a good account of the growth and decline of memes. We discuss the role of log-normal distributions in modeling Internet phenomena and touch on practical implications of our findings.

Partially-observable Markov decision processes (POMDPs) provide a powerful model for sequential decision-making problems with partially-observed state and are known to have (approximately) optimal dynamic programming solutions. Much work in recent years has focused on improving the efficiency of these dynamic programming algorithms by exploiting symmetries and factored or relational representations. In this work, we show that it is also possible to exploit the full expressive power of first-order quantification to achieve state, action, and observation abstraction in a dynamic programming solution to relationally specified POMDPs. Among the advantages of this approach are the ability to maintain compact value function representations, abstract over the space of potentially optimal actions, and automatically derive compact conditional policy trees that minimally partition relational observation spaces according to distinctions that have an impact on policy values. This is the first lifted relational POMDP solution that can optimally accommodate actions with a potentially infinite relational space of observation outcomes.

A new method is proposed for compiling causal independencies into Markov logic networks. A Markov logic network can be viewed as compactly representing a factorization of a joint probability into the multiplication of a set of factors guided by logical formulas. We present a notion of causal independence that enables one to further factorize the factors into a combination of even smaller factors and consequently obtain a finer-grain factorization of the joint probability. The causal independence lets us specify the factor in terms of weighted, directed clauses and an associative and commutative operator, such as "or", "sum" or "max", on the contribution of the variables involved in the factors, hence combining both undirected and directed knowledge.