Goal or Miss? A Bernoulli Distribution for In-Game Outcome Prediction in Soccer

Due to a colossal soccer market, soccer analysis has attracted considerable attention from industry and academia. In-game outcome prediction has great potential in various applications such as game broadcasting, tactical decision making, and betting. In some sports, the method of directly predicting in-game outcomes based on the ongoing game state is already being used as a statistical tool. However, soccer is a sport with low-scoring games and frequent draws, which makes in-game prediction challenging. Most existing studies focus on pre-game prediction instead. This paper, however, proposes a two-stage method for soccer in-game outcome prediction, namely in-game outcome prediction (IGSOP). When the full length of a soccer game is divided into sufficiently small time frames, the goal scored by each team in each time frame can be modeled as a random variable following the Bernoulli distribution. In the first stage, IGSOP adopts state-based machine learning to predict the probability of a scoring goal in each future time frame. In the second stage, IGSOP simulates the remainder of the game to estimate the outcome of a game. This two-stage approach effectively captures the dynamic situation after a goal and the uncertainty in the late phase of a game. Chinese Super League data have been used for algorithm training and evaluation, and the results demonstrate that IGSOP outperforms existing methods, especially in predicting draws and prediction during final moments of games. IGSOP provides a novel perspective to solve the problem of in-game outcome prediction in soccer, which has a potential ripple effect on related research.     

Link Prediction in Complex Networks Using Recursive Feature Elimination and Stacking Ensemble Learning

Link prediction is an important task in the field of network analysis and modeling, and predicts missing links in current networks and new links in future networks. In order to improve the performance of link prediction, we integrate global, local, and quasi-local topological information of networks. Here, a novel stacking ensemble framework is proposed for link prediction in this paper. Our approach employs random forest-based recursive feature elimination to select relevant structural features associated with networks and constructs a two-level stacking ensemble model involving various machine learning methods for link prediction. The lower level is composed of three base classifiers, i.e., logistic regression, gradient boosting decision tree, and XGBoost, and their outputs are then integrated with an XGBoost model in the upper level. Extensive experiments were conducted on six networks. Comparison results show that the proposed method can obtain better prediction results and applicability robustness.     

On Quantum Team Games

Recently Liu and Simaan (2004) convex static multi-team classical games have been introduced. Here they are generalized to both nonconvex, dynamic and quantum games. Puu's incomplete information dynamical systems are modified and applied to Cournot team game. The replicator dynamics of the quantum prisoner's dilemma game is also studied.     

Non-Classical Rules in Quantum Games

Over the last twenty years, quantum game theory has given us many ideas of how quantum games could be played. One of the most prominent ideas in the field is a model of quantum playing bimatrix games introduced by J. Eisert, M. Wilkens and M. Lewenstein. The scheme assumes that players’ strategies are unitary operations and the players act on the maximally entangled two-qubit state. The quantum nature of the scheme has been under discussion since the article by Eisert et al. came out. The aim of our paper was to identify some of non-classical features of the quantum scheme.     

Diversification and limited information in the Kelly game

Financial markets, with their vast range of different investment opportunities, can be seen as a system of many different simultaneous games with diverse and often unknown levels of risk and reward. We introduce generalizations to the classic Kelly investment game [J.L. Kelly, IEEE Transactions on Information Theory 2 (1956) 185-189] that incorporates these features, and use them to investigate the influence of diversification and limited information on Kelly-optimal portfolios. In particular, we present approximate formulas for optimizing diversified portfolios and exact results for optimal investment in unknown games where the only available information is past outcomes.     

MatchOrchestra: a generalized visual analytics for competitive team sports

Competitive sports analysis is a popular and valuable research topic in recent years. Sports are competitive, fast paced, and teamwork based. In this article, we introduce a generalized and effective system MatchOrchestra to analyze competitive team sports based on musical score and orchestra metaphor. MatchOrchestra provides views about player performance, team status, match tempo, player cooperation and confrontation, which can help analysts in performing specific analysis tasks. To demonstrate the usability of our proposed system, representative case studies were conducted on an NBA (National Basketball Association) game and also extend to apply in football match, which are both typical competitive sports matches.     

A model for competitiveness level analysis in sports competitions: Application to basketball

The degree of overall competitiveness of a sport league is a complex phenomenon. It is difficult to assess and quantify all elements that yield the final standing. In this paper, we analyze the general behavior of the result matrices of each season and we use the corresponding results as a probably density. Thus, the results of previous seasons are a way to investigate the probability that each team has to reach a certain number of victories. We developed a model based on Shannon entropy using two extreme competitive structures (a hierarchical structure and a random structure), and applied this model to investigate the competitiveness of two of the best professional basketball leagues: the NBA (USA) and the ACB (Spain). Both leagues’ entropy levels are high (NBA mean 0.983; ACB mean 0.980), indicating high competitiveness, although the entropy of the ACB (from 0.986 to 0.972) demonstrated more seasonal variability than that of the NBA (from 0.985 to 0.990), a possible result of greater sporting gradients in the ACB. The use of this methodology has proven useful for investigating the competitiveness of sports leagues as well as their underlying variability across time.     

Tripartite Dynamic Zero-Sum Quantum Games

The Nash equilibrium plays a crucial role in game theory. Most of results are based on classical resources. Our goal in this paper is to explore multipartite zero-sum game with quantum settings. We find that in two different settings there is no strategy for a tripartite classical game being fair. Interestingly, this is resolved by providing dynamic zero-sum quantum games using single quantum state. Moreover, the gains of some players may be changed dynamically in terms of the committed state. Both quantum games are robust against the preparation noise and measurement errors.     

Theoretical analysis of quantum game in cavity QED

Recent years, several ways of implementing quantum games in different physical systems have been presented. In this paper, we perform a theoretical analysis of an experimentally feasible way to implement a two player quantum game in cavity quantum electrodynamic(QED). In the scheme, the atoms interact simultaneously with a highly detuned cavity mode with the assistance of a classical field. So the scheme is insensitive to the influence from the cavity decay and the thermal field, and it does not require the cavity to remain in the vacuum state throughout the procedure.     

An evolutionary game theory model of binary opinion formation

A basic characteristic of most opinion models is that people tend to agree or compromise in the opinion interaction, which could be hopefully described by cooperative games in the evolutionary game theory framework. This paper presents game theory methods to model the formation of binary opinions: cooperative games are proposed to model the interaction rules of general people who tend to find an agreement; minority games are proposed to model the behaviors of contrarians; opinion preference is considered by varying the payoff values. The Majority Voter model could be restored from the proposed games. The game theory models show evolutionary results similar to traditional opinion models. Specially, the evolution of opinions with consideration of contrarians is in accordance with the Galam model. Furthermore, influences of evolving rule, network topology and initial distribution of opinions are studied through numerical simulations. Discussions about methods to promote or hinder the consensus state at the best equilibrium point are given.     

Quantum Parrondo game based on a quantum ratchet effect

A Parrondo game is a counterintuitive game where two losing games can be combined to form a winning game. We construct a quantum version of a Parrondo game based on a quantum ratchet effect for a delta-kicked model, which can be realized in optical lattices. A game set is presented and a quantum anti-Parrondo game is also investigated.     

基于体感技术的游戏重构框架的应用研究

为满足体感游戏市场需求,降低3D游戏前期投入风险,文章提出通过开发中间件模块对游戏开发过程进行简单改造,实现3D游戏向体感游戏平滑过渡的过程。先是简单介绍了体感技术的原理和工作过程,接着结合Kinect硬件系统提出了3D游戏到体感游戏重构框架（3D-MS重构框架）,然后设计和实现了中间件模块,并对现有3D游戏的提出具体改进策略和方法。最后以《神龙》游戏为案例进行了重构和实验测试,实验表明3D-MS重构框架是可行的,采用中间件技术可平滑、快速实现从3D游戏到体感游戏,比直接改造游戏的效率高2.2倍,同时能提高游戏的人机互动效果。     

Exploring and Selecting Features to Predict the Next Outcomes of MLB Games

(1) Background and Objective: Major League Baseball (MLB) is one of the most popular international sport events worldwide. Many people are very interest in the related activities, and they are also curious about the outcome of the next game. There are many factors that affect the outcome of a baseball game, and it is very difficult to predict the outcome of the game precisely. At present, relevant research predicts the accuracy of the next game falls between 55% and 62%. (2) Methods: This research collected MLB game data from 2015 to 2019 and organized a total of 30 datasets for each team to predict the outcome of the next game. The prediction method used includes one-dimensional convolutional neural network (1DCNN) and three machine-learning methods, namely an artificial neural network (ANN), support vector machine (SVM), and logistic regression (LR). (3) Results: The prediction results show that, among the four prediction models, SVM obtains the highest prediction accuracies of 64.25% and 65.75% without feature selection and with feature selection, respectively; and the best AUCs are 0.6495 and 0.6501, respectively. (4) Conclusions: This study used feature selection and optimized parameter combination to increase the prediction performance to around 65%, which surpasses the prediction accuracies when compared to the state-of-the-art works in the literature.     

Mesoscopic approach to minority games in herd regime

We study minority games in efficient regime. By incorporating the utility function and aggregating agents with similar strategies we develop an effective mesoscale notion of the state of the game. Using this approach, the game can be represented as a Markov process with substantially reduced number of states with explicitly computable probabilities. For any payoff, the finiteness of the number of states is proved. Interesting features of an extensive random variable, called aggregated demand, viz. its strong inhomogeneity and presence of patterns in time, can be easily interpreted. Using Markov theory and quenched disorder approach, we can explain important macroscopic characteristics of the game: behavior of variance per capita and predictability of the aggregated demand. We prove that in the case of linear payoff many attractors in the state space are possible.     

Effect of the Initial Temperature on the Characteristics of the Shot with a Block Charge

The effect of the initial temperature on the characteristics of the shot is studied for high-density block charges prepared by pressing powder grains coated with a polymer film. The experiments were carried out on laboratory barrel setups of caliber 7.62 and 14.5 mm with recording the muzzle velocity and pressure. Two shot schemes are considered: a classical scheme with the block charge placed in the chamber, and a hybrid scheme, with the block charge attached to the projectile, burning as it travels along the barrel. The effect observed at various initial temperatures of the block charge is compared with similar data for a standard poured-powder charge, for which the temperature gradient within ±50°C is 2.1?2.5% per 10°C. The experiments showed that, at positive temperatures, the temperature gradient for block propellant charges is appreciably smaller, 0.9?1.2% for the traditional shot scheme and 0.8% for the hybrid scheme. At negative temperatures of the block propellant charges, the characteristics of the shot decline significantly, which, however, can be restored to the temperature gradient typical of the standard shot by boosting the igniter.     

Quantum games via search algorithms

We build new quantum games, similar to the spin flip game, where as a novelty the players perform measurements on a quantum system associated to a continuous time search algorithm. The measurements collapse the wave function into one of the two possible states. These games are characterized by a continuous space of strategies and the selection of a particular strategy is determined by the moments when the players measure.     

Quantum Information Approach to the Ultimatum Game

The paper is devoted to quantization of extensive games with the use of both the Marinatto-Weber and the Eisert-Wilkens-Lewenstein concept of quantum game. We revise the current conception of quantum ultimatum game and we show why the proposal is unacceptable. To support our approach, we present a new idea of the quantum ultimatum game. Our scheme also makes a point of departure for a general protocol for quantizing extensive games.     

Zero-determinant strategy:An underway revolution in game theory

Repeated games describe situations where players interact with each other in a dynamic pattern and make decisions according to outcomes of previous stage games. Very recently, Press and Dyson have revealed a new class of zero-determinant(ZD) strategies for the repeated games, which can enforce a fixed linear relationship between expected payoffs of two players, indicating that a smart player can control her unwitting co-player’s payoff in a unilateral way [Proc. Acad. Natl. Sci.USA 109, 10409(2012)]. The theory of ZD strategies provides a novel viewpoint to depict interactions among players,and fundamentally changes the research paradigm of game theory. In this brief survey, we first introduce the mathematical framework of ZD strategies, and review the properties and constrains of two specifications of ZD strategies, called pinning strategies and extortion strategies. Then we review some representative research progresses, including robustness analysis,cooperative ZD strategy analysis, and evolutionary stability analysis. Finally, we discuss some significant extensions to ZD strategies, including the multi-player ZD strategies, and ZD strategies under noise. Challenges in related research fields are also listed.     

基于连续时间广义预测校正的水下非线性追踪博弈控制

针对复杂环境下的追踪控制问题,提出了一种基于连续时间广义预测校正的水下非线性追踪博弈控制算法.利用连续时间广义预测对目标机动偏离趋势进行在线预测补偿校正,将机动目标紧缩于最大捕获概率扇面之内,同时引入零效控制参数和连续时间广义预测校正算法,解决了微分对策动态博弈剩余时间难于估计的问题,提高了系统的响应速度.将算法应用于水下非线性追踪博弈的验证结果表明,该算法兼顾了控制约束与干扰抑制性能,能够实时有效地对抗初始偏差和随机扰动,不仅具有良好的导引效果,而且有效提高了系统对环境干扰的鲁棒性.     

Spatio-temporal dynamics of security investments in an interdependent risk environment

In a globalised world where risks spread through contagion, the decision of an entity to invest in securing its premises from stochastic risks no longer depends solely on its own actions but also on the actions of other interacting entities in the system. This phenomenon is commonly seen in many domains including airline, logistics and computer security and is referred to as Interdependent Security (IDS). An IDS game models this decision problem from a game-theoretic perspective and deals with the behavioural dynamics of risk-reduction investments in such settings. This paper enhances this model and investigates the spatio-temporal aspects of the IDS games. The spatio-temporal dynamics are studied using simple replicator dynamics on a variety of network structures and for various security cost tradeoffs that lead to different Nash equilibria in an IDS game. The simulation results show that the neighbourhood configuration has a greater effect on the IDS game dynamics than network structure. An in-depth empirical analysis of game dynamics is carried out on regular graphs, which leads to the articulation of necessary and sufficient conditions for dominance in IDS games under spatial constraints.