Esports are competitive videogames watched by audiences. Most esports generate detailed data for each match that are publicly available. Esports analytics research is focused on predicting match outcomes. Previous research has emphasized prematch prediction and used data from amateur games, which are more easily available than those from professional level. However, the commercial value of win prediction exists at the professional level. Furthermore, predicting real-time data is unexplored, as is its potential for informing audiences. Here, we present the first comprehensive case study on live win prediction in a professional esport. We provide a literature review for win prediction in a multiplayer online battle arena (MOBA) esport. This article evaluates the first professional-level prediction models for live DotA 2 matches, one of the most popular MOBA games, and trials it at a major international esports tournament. Using standard machine learning models, feature engineering and optimization, our model is up to 85% accurate after 5 min of gameplay. Our analyses highlight the need for algorithm evaluation and optimization. Finally, we present implications for the esports/game analytics domains, describe commercial opportunities and practical challenges, and propose a set of evaluation criteria for research on esports win prediction.

Hyperinflation and price volatility in virtual economies has the potential to reduce player satisfaction and decrease developer revenue. This paper describes intuitive analytical methods for monitoring volatility and inflation in virtual economies, with worked examples on the increasingly popular multiplayer game Old School Runescape. Analytical methods drawn from mainstream financial literature are outlined and applied in order to present a high level overview of virtual economic activity of 3467 price series over 180 trading days. Six-monthly volume data for the top 100 most traded items is also used both for monitoring and value estimation, giving a conservative estimate of exchange trading volume of over £60m in real value. Our worked examples show results from a well functioning virtual economy to act as a benchmark for future work. This work contributes to the growing field of virtual economics and game development, describing how data transformations and statistical tests can be used to improve virtual economic design and analysis, with applications in real-time monitoring systems.

Heightmap generation is currently a tedious topic with the majority of generation using Perlin noise which forms a reliable, but sometimes repetitive output. In this paper, a method of generating height maps from real-world digital elevation data taken from specific regions of the planet is proposed. Raw elevation data sourced from NASA's SRTM (30m) data set is transformed into a height map format, this data is then passed into a two type unsupervised model. The method uses a type of generative adversarial network to learn the spatially-invariant features within the input regions. Producing a network model that can output an extensive amount of varying, but visually and structurally similar height maps to that of the input regions. The visual validity of outputs from the network was tested using data from 262 human participants, with over 90.15% of generated samples being correctly assigned to the original input data with a significance of P <;0.001.

Monte Carlo tree search (MCTS) has become a popular solution for game artificial intelligence (AI), capable of creating strong game playing opponents. However, the emergent playstyle of agents using MCTS is not necessarily human-like, believable or enjoyable. AI Factory Spades, currently the top rated Spades game in the Google Play store, uses a variant of MCTS to control AI allies and opponents. In collaboration with the developers, we showed in a previous study that the playstyle of human players significantly differed from that of the AI players. This paper presents a method for player modeling using gameplay data and neural networks that does not require domain knowledge, and a method of biasing MCTS with such a player model to create Spades playing agents that emulate human play whilst maintaining strong, competitive performance. The methods of player modeling and biasing MCTS presented in this study are applied to the commercial codebase of AI Factory Spades, and are transferable to MCTS implementations for discrete-action games where relevant gameplay data are available.

In this paper, we analyze the gameplay data of three popular customizable card games where players build decks prior to gameplay. We analyze the data from a player engagement perspective, how the business model affects players, how players influence the business model and provide strategic insights for players themselves. Sifa et al. found a lack of cross-game analytics, whereas Marchand and Hennig-Thurau identified a lack of understanding of how a game's business model and strategies affect players. We address both issues. The three games have similar business models but differ in one aspect: the distribution model for the cards used in the game. Our longitudinal analysis highlights this variation's impact. A uniform distribution creates a spread of decks with slowly emerging trends while a random distribution creates stripes of deck building activity that switch suddenly each update. Our method is simple, easily understandable, independent of the specific game's structure, and able to compare multiple games. It is applicable to games that release updates and enables comparison across games. Optimizing a game's updates strategy is the key, as it affects player engagement and retention, which directly influence businesses' revenues and profitability in the $95 billion global games market.

Tuning game difficulty prior to release requires careful consideration. Players can quickly lose interest in a game if it is too hard or too easy. Assessing how players will cope prior to release is often inaccurate. However, modern games can now collect sufficient data to perform large scale analysis post deployment and update the product based on these insights. AI Factory Spades is currently the top rated Spades game in the Google Play store. In collaboration with the developers, we have collected gameplay data from 27 592 games and statistics regarding wins/losses for 99 866 games using Google Analytics. Using the data collected, this study analyses the difficulty and behavior of an Information Set Monte Carlo Tree Search player we developed and deployed in the game previously. The methods of data collection and analysis presented in this study are generally applicable. The same workflow could be used to analyze the difficulty and typical player or opponent behavior in any game. Furthermore, addressing issues of difficulty or nonhuman-like opponents postdeployment can positively affect player retention.

This paper presents the game, framework, rules and results of the Multi-objective Physical Travelling Salesman Problem (MO-PTSP) Competition, that was held at the 2013 IEEE Conference on Computational Intelligence in Games (CIG). The MO-PTSP is a real-time game that can be seen as a modification of the Travelling Salesman Problem, where the player controls a ship that must visit a series of waypoints in a maze while minimizing three opposing goals: time spent, fuel consumed and damage taken. The rankings of the competition are computed using multi-objective concepts, a novel approach in the field of game artificial intelligence competitions. The winning entry of the contest is also explained in detail. This controller is based on the Monte Carlo Tree Search algorithm, and employed Covariance Matrix Adaptation Evolution Strategy (CMA-ES) for parameter tuning.

Process parallelization is more important than ever, as most modern hardware contains multiple processors and advanced multi-threading capability. This paper presents an analysis of the parallel behaviour of Information Set Monte Carlo Tree Search and the Upper Confidence Bounds for Trees (UCT) variant of MCTS, and certain parallelization techniques (specifically Tree Parallelization) have different effects upon ISM-CTS and Plain UCT. The paper presents a study of the relative effectiveness of different types of parallelization, including Root, Tree, Tree with Virtual Loss, and Leaf.

This paper presents a number of approaches for solving a real-time game consisting of a ship that must visit a number of waypoints scattered around a 2-D maze full of obstacles. The game, the Physical Traveling Salesman Problem (PTSP), which featured in two IEEE conference competitions during 2012, provides a good balance between long-term planning (finding the optimal sequence of waypoints to visit), and short-term planning (driving the ship in the maze). This paper focuses on the algorithm that won both PTSP competitions: it takes advantage of the physics of the game to calculate the optimal order of waypoints, and it employs Monte Carlo tree search (MCTS) to drive the ship. The algorithm uses repetitions of actions (macro actions) to reduce the search space for navigation. Variations of this algorithm are presented and analyzed, in order to understand the strength of each one of its constituents and to comprehend what makes such an approach the best controller found so far for the PTSP.

Monte Carlo tree search (MCTS) is a recently proposed search method that combines the precision of tree search with the generality of random sampling. It has received considerable interest due to its spectacular success in the difficult problem of computer Go, but has also proved beneficial in a range of other domains. This paper is a survey of the literature to date, intended to provide a snapshot of the state of the art after the first five years of MCTS research. We outline the core algorithm's derivation, impart some structure on the many variations and enhancements that have been proposed, and summarize the results from the key game and nongame domains to which MCTS methods have been applied. A number of open research questions indicate that the field is ripe for future work.

Monte Carlo tree search (MCTS) is an AI technique that has been successfully applied to many deterministic games of perfect information. This paper investigates the application of MCTS methods to games with hidden information and uncertainty. In particular, three new information set MCTS (ISMCTS) algorithms are presented which handle different sources of hidden information and uncertainty in games. Instead of searching minimax trees of game states, the ISMCTS algorithms search trees of information sets, more directly analyzing the true structure of the game. These algorithms are tested in three domains with different characteristics, and it is demonstrated that our new algorithms outperform existing approaches to handling hidden information and uncertainty in games.

In this paper, we examine the use of Monte Carlo tree search (MCTS) for a variant of one of the most popular and profitable games in the world: the card game Magic: The Gathering (M:TG). The game tree for M:TG has a range of distinctive features, which we discuss here; it has incomplete information through the opponent's hidden cards and randomness through card drawing from a shuffled deck. We investigate a wide range of approaches that use determinization, where all hidden and random information is assumed known to all players, alongside MCTS. We consider a number of variations to the rollout strategy using a range of levels of sophistication and expert knowledge, and decaying reward to encourage play urgency. We examine the effect of utilizing various pruning strategies in order to increase the information gained from each determinization, alongside methods that increase the relevance of random choices. Additionally, we deconstruct the move generation procedure into a binary yes/no decision tree and apply MCTS to this finer grained decision process. We compare our modifications to a basic MCTS approach for M:TG using fixed decks, and show that significant improvements in playing strength can be obtained.

Bag of visual patches (BOP) image representation has been the main research topic in computer vision literature for scene and object recognition tasks. Building visual vocabularies from local image feature vectors extracted automatically from images have direct effect on producing discriminative visual patches. Local image features hold important information of their locations in the image which are ignored during quantization process to build visual vocabularies. In this paper, we propose Spatial Pyramid Vocabulary Model (SPVM) to build visual vocabularies from local image features at pyramid level. We show, with experiments on multi-class classification task using 700 natural scene images, that the spatial pyramid vocabulary model is suitable and discriminative for bag-of-visual patches semantic image representation compared to using universal vocabulary model (UVM).

This paper presents an application of reputation based trust assessment model in mobile ad hoc network setting. A game between the Sender (originator) and Intermediary (forwarder) nodes in the network is modelled and plugged-in to a trust assessment framework that classifies feedback according to past acquaintances between the nodes. Simulations for the experiments have been carried out in an Iterated Prisoner's dilemma like setting, where each player represents a network node. Through our experiments we show that having trust model decreases the Packet Drop Ratio (PDR) in an ad hoc network setting. Further, the results show that Gain through the utility and savings of energy is better with application of the trust model.

The problem of object/scene image classification has gained increasing attention from many researchers in computer vision. In this paper we investigate a number of early fusion methods using a novel approach to combine image colour information and the bag of visual patches (BOP) for recognizing natural scene image categories. We propose keypoints density-based weighting method (KDW) for merging colour moments and the BOP on a spatial pyramid layout. We found that the density of keypoints located in each image sub-region at specific granularity has noticeable impacts on deciding the importance of colour moments on that image sub-region. We demonstrate the validity of our approach on a six categories dataset of natural scene images. Experimental results have proved the effectiveness of our proposed approach.

Summary form only given. Constructing fast, accurate classifiers for large data sets is an important task in data mining and knowledge discovery. In this research paper, a new classification method called multi-class classification based on association rules (MCAR) is presented. MCAR uses an efficient technique for discovering frequent items and employs a rule ranking method which ensures detailed rules with high confidence are part of the classifier. After experimentation with fifteen different data sets, the results indicated that the proposed method is an accurate and efficient classification technique. Furthermore, the classifiers produced are highly competitive with regards to error rate and efficiency, if compared with those generated by popular methods like decision trees, RIPPER and CBA.

Building fast and accurate classifiers for large-scale databases is an important task in data mining. There is growing evidence that integrating classification and association rule mining together can produce more efficient and accurate classifiers than traditional classification techniques. In this paper, the problem of producing rules with multiple labels is investigated. We propose a new associative classification approach called multi-class, multi-label associative classification (MMAC). This paper also presents three measures for evaluating the accuracy of data mining classification approaches to a wide range of traditional and multi-label classification problems. Results for 28 different datasets show that the MMAC approach is an accurate and effective classification technique, highly competitive and scalable in comparison with other classification approaches.

We investigate the performance of several hyperheuristics applied to a real-world personnel-scheduling problem. A hyperheuristic is a high-level search method which manages the choice of low level heuristics, making it a robust and easy to implement approach for complex real-world problems. We need only to develop new low level heuristics and objective functions to apply a hyperheuristic to an entirely new problem. Although hyperheuristic methods require limited problem-specific information, their performance for a particular problem is determined to a great extent by the quality of low level heuristics used. We address the question of designing the set of low level heuristics for the problem under consideration. We construct a large set of low level heuristics by using a technique which allows us to "multiply" partial low level heuristics. We apply hyperheuristic methods to a trainer scheduling problem using commercial data from a large financial institution. The results of the experiments show that simple hyperheuristic approaches can successfully tackle a complex real-world problem provided that low level heuristics are carefully selected to treat various constraints. We also examine how the choice of different sets of low level heuristics affects solution quality.

This paper describes a new model for robust predictive/reactive scheduling of steel continuous casting based on the use of multi-agents, tabu search and heuristic approaches. A continuous caster agent generates a predictive production schedule taking into account manufacturing requirements and local constraints using tabu search. The predictive schedule is modifies so as to minimize deviation between the performance measure values of the realized and predictive schedules in order to react to real-time events. We propose several schedule-repair and complete reschedule strategies to handle the real-time events, evaluate and compare their performance. The decision as to whether to locally repair the schedule or reschedule from scratch (complete reschedule) is based on three measures: robustness, utility and stability. Utility measures the change in schedule objective following schedule revision. Stability measures the deviation from the original schedule caused by schedule revision to quantify the undesirability of making large changes to the initial predictive schedule unless absolutely necessary. Robustness combines the utility and stability measures. In order to investigate the performance of these measures and strategies, simulation experiments were carried out and results are reported.

This paper investigates a genetic algorithm based hyperheuristic (hyper-GA) for scheduling geographically distributed training staff and courses. The aim of the hyper-GA is to evolve a good-quality heuristic for each given instance of the problem and use this to find a solution by applying a suitable ordering from a set of low-level heuristics. Since the user only supplies a number of low-level problem-specific heuristics and an evaluation function, the hyperheuristic can easily be reimplemented for a different type of problem, and we would expect it to be robust across a wide range of problem instances. We show that the problem can be solved successfully by a hyper-GA, presenting results for four versions of the hyper-GA as well as a range of simpler heuristics and applying them to five test data set.

A hybrid population-based metaheuristic for the space allocation problem in academic institutions is presented that is based upon previous experiments using a range of techniques including hill-climbing, simulated annealing, tabu search and genetic algorithms. The proposed approach incorporates the best characteristics of each technique, makes an automatic selection of the parameters according to the problem characteristics and surpasses the performance of these standard techniques in terms of the solution quality evaluated with a penalty function. This approach incorporates local search heuristics, adaptive cooling schedules and population-based techniques. Our experiments show that this technique produces competitive solutions for the space allocation problem. In this problem, it is often desirable to obtain a set of candidate solutions so that the decision maker can select the best among them. By controlling a common cooling schedule for the whole population in the simulated annealing component, it is possible to find one excellent solution or to produce a population of good solutions.

Considers a scheduling problem that arises for numerically controlled machines in the manufacture of printed circuit boards. In order to maximize the throughput rate of these machines, the time taken for the pick-and-place sequence of components for each board has to be minimized. The determination of good pick-and-place sequences on a single placement machine gives rise to three related problems, namely the assignment of component types to feeder slots, the problem of tool changes and the sequence itself. In this paper, we consider a sophisticated type of placement machinery equipped with multiple placement heads. We introduce a suitable model for this complex scheduling problem and present tailored constructive and local search heuristics to determine good, locally optimal solutions. We embed the local search techniques proposed in the variable neighborhood search metaheuristic framework to find still better locally optimal solutions and effectively search a larger part of the solution space. The heuristics have been implemented and applied to a panel of 12 test circuit boards to analyze their performance.