Pub Date : 2016-09-01DOI: 10.1109/CIG.2016.7860404
Elizabeth Camilleri, Georgios N. Yannakakis, A. Dingli
Player believability is often defined as the ability of a game playing character to convince an observer that it is being controlled by a human. The agent's behavior is often assumed to be the main contributor to the character's believability. In this paper we reframe this core assumption and instead focus on the impact of the game environment and aspects of game design (such as level design) on the believability of the game character. To investigate the relationship between game content and believability we crowdsource rank-based annotations from subjects that view playthrough videos of various AI and human controlled agents in platformer levels of dissimilar characteristics. For this initial study we use a variant of the well-known Super Mario Bros game. We build support vector machine models of reported believability based on gameplay and level features which are extracted from the videos. The highest performing model predicts perceived player believability of a character with an accuracy of 73.31%, on average, and implies a direct relationship between level features and player believability.
{"title":"Platformer level design for player believability","authors":"Elizabeth Camilleri, Georgios N. Yannakakis, A. Dingli","doi":"10.1109/CIG.2016.7860404","DOIUrl":"https://doi.org/10.1109/CIG.2016.7860404","url":null,"abstract":"Player believability is often defined as the ability of a game playing character to convince an observer that it is being controlled by a human. The agent's behavior is often assumed to be the main contributor to the character's believability. In this paper we reframe this core assumption and instead focus on the impact of the game environment and aspects of game design (such as level design) on the believability of the game character. To investigate the relationship between game content and believability we crowdsource rank-based annotations from subjects that view playthrough videos of various AI and human controlled agents in platformer levels of dissimilar characteristics. For this initial study we use a variant of the well-known Super Mario Bros game. We build support vector machine models of reported believability based on gameplay and level features which are extracted from the videos. The highest performing model predicts perceived player believability of a character with an accuracy of 73.31%, on average, and implies a direct relationship between level features and player believability.","PeriodicalId":6594,"journal":{"name":"2016 IEEE Conference on Computational Intelligence and Games (CIG)","volume":"45 Suppl 1 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75705487","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-09-01DOI: 10.1109/CIG.2016.7860410
Matthew Stephenson, Jochen Renz
This paper presents a procedural content generation algorithm for the physics-based puzzle game Angry Birds. The proposed algorithm creates complex stable structures using a variety of 2D objects. These are generated without the aid of pre-defined substructures or composite elements. The structures created are evaluated based on a fitness function which considers several important structural aspects. The results of this analysis in turn affects the likelihood of particular objects being chosen in future generations. Experiments were conducted on the generated structures in order to evaluate the algorithm's expressivity. The results show that the proposed method can generate a wide variety of 2D structures with different attributes and sizes.
{"title":"Procedural generation of complex stable structures for angry birds levels","authors":"Matthew Stephenson, Jochen Renz","doi":"10.1109/CIG.2016.7860410","DOIUrl":"https://doi.org/10.1109/CIG.2016.7860410","url":null,"abstract":"This paper presents a procedural content generation algorithm for the physics-based puzzle game Angry Birds. The proposed algorithm creates complex stable structures using a variety of 2D objects. These are generated without the aid of pre-defined substructures or composite elements. The structures created are evaluated based on a fitness function which considers several important structural aspects. The results of this analysis in turn affects the likelihood of particular objects being chosen in future generations. Experiments were conducted on the generated structures in order to evaluate the algorithm's expressivity. The results show that the proposed method can generate a wide variety of 2D structures with different attributes and sizes.","PeriodicalId":6594,"journal":{"name":"2016 IEEE Conference on Computational Intelligence and Games (CIG)","volume":"106 2 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78450989","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-09-01DOI: 10.1109/CIG.2016.7860405
R. Sifa, Sri. M. Srikanth, Anders Drachen, C. Ojeda, C. Bauckhage
Major commercial (AAA) games increasingly transit to a semi-persistent or persistent format in order to extend the value of the game to the player, and to add new sources of revenue beyond basic retail sales. Given this shift in the design of AAA titles, game analytics needs to address new types of problems, notably the problem of forecasting future player behavior. This is because player retention is a key factor in driving revenue in semi-persistent titles, for example via downloadable content. This paper introduces a model for predicting retention of players in AAA games and provides a tensor-based spatio-temporal model for analyzing player trajectories in 3D games. We show how knowledge as to trajectories can help with predicting player retention. Furthermore, we describe two new algorithms for three way DEDICOM including a fast gradient method and a seminonnegative constrained method. These approaches are validated against a detailed behavioral data set from the AAA open-world game Just Cause 2.
{"title":"Predicting Retention in Sandbox Games with Tensor Factorization-based Representation Learning","authors":"R. Sifa, Sri. M. Srikanth, Anders Drachen, C. Ojeda, C. Bauckhage","doi":"10.1109/CIG.2016.7860405","DOIUrl":"https://doi.org/10.1109/CIG.2016.7860405","url":null,"abstract":"Major commercial (AAA) games increasingly transit to a semi-persistent or persistent format in order to extend the value of the game to the player, and to add new sources of revenue beyond basic retail sales. Given this shift in the design of AAA titles, game analytics needs to address new types of problems, notably the problem of forecasting future player behavior. This is because player retention is a key factor in driving revenue in semi-persistent titles, for example via downloadable content. This paper introduces a model for predicting retention of players in AAA games and provides a tensor-based spatio-temporal model for analyzing player trajectories in 3D games. We show how knowledge as to trajectories can help with predicting player retention. Furthermore, we describe two new algorithms for three way DEDICOM including a fast gradient method and a seminonnegative constrained method. These approaches are validated against a detailed behavioral data set from the AAA open-world game Just Cause 2.","PeriodicalId":6594,"journal":{"name":"2016 IEEE Conference on Computational Intelligence and Games (CIG)","volume":"62 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81973217","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-09-01DOI: 10.1109/CIG.2016.7860428
Alican Sungur, Elif Sürer
Operating autonomous agents inside a 3D workspace is a challenging problem domain in real-time for dynamic environments since it involves online interaction with ever-changing decision constraints. This study proposes a neuroscience inspired architecture to simulate autonomous agents with interaction capabilities inside a 3D virtual world. The environment stimulates the operating agents based on their place and course of action. They are expected to form a life cycle composed of behavior chunks inside this environment and continuously optimize it around the stimulated reward. The architecture is composed of specialized units that run Cortical Learning Algorithm (CLA) which models functional properties of layers II and III as in six layer theory of neocortex. This work focuses on extending it with functional properties of layers IV, V and basal ganglia to obtain voluntary behavior that is suitable for an autonomous agent. Through experimental scenarios, the architecture is observed and evaluated in order to obtain an apparent learning process. The communication between layers and internal connectivity of embedded CLA units are able to capture sequential and causal relations from the environment and the first evaluation of the implementation has high potential for future directions.
{"title":"Voluntary behavior on cortical learning algorithm based agents","authors":"Alican Sungur, Elif Sürer","doi":"10.1109/CIG.2016.7860428","DOIUrl":"https://doi.org/10.1109/CIG.2016.7860428","url":null,"abstract":"Operating autonomous agents inside a 3D workspace is a challenging problem domain in real-time for dynamic environments since it involves online interaction with ever-changing decision constraints. This study proposes a neuroscience inspired architecture to simulate autonomous agents with interaction capabilities inside a 3D virtual world. The environment stimulates the operating agents based on their place and course of action. They are expected to form a life cycle composed of behavior chunks inside this environment and continuously optimize it around the stimulated reward. The architecture is composed of specialized units that run Cortical Learning Algorithm (CLA) which models functional properties of layers II and III as in six layer theory of neocortex. This work focuses on extending it with functional properties of layers IV, V and basal ganglia to obtain voluntary behavior that is suitable for an autonomous agent. Through experimental scenarios, the architecture is observed and evaluated in order to obtain an apparent learning process. The communication between layers and internal connectivity of embedded CLA units are able to capture sequential and causal relations from the environment and the first evaluation of the implementation has high potential for future directions.","PeriodicalId":6594,"journal":{"name":"2016 IEEE Conference on Computational Intelligence and Games (CIG)","volume":"128 1","pages":"1-7"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87912042","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-09-01DOI: 10.1109/CIG.2016.7860399
Nick Sephton, P. Cowling, Sam Devlin, Victoria J. Hodge, Nicholas H. Slaven
As part of their design, card games often include information that is hidden from opponents and represents a strategic advantage if discovered. A player that can discover this information will be able to alter their strategy based on the nature of that information, and therefore become a more competent opponent. In this paper, we employ association rule-mining techniques for predicting item multisets, and show them to be effective in predicting the content of Netrunner decks. We then apply different modifications based on heuristic knowledge of the Netrunner game, and show the effectiveness of techniques which consider this knowledge during rule generation and prediction.
{"title":"Using association rule mining to predict opponent deck content in android: Netrunner","authors":"Nick Sephton, P. Cowling, Sam Devlin, Victoria J. Hodge, Nicholas H. Slaven","doi":"10.1109/CIG.2016.7860399","DOIUrl":"https://doi.org/10.1109/CIG.2016.7860399","url":null,"abstract":"As part of their design, card games often include information that is hidden from opponents and represents a strategic advantage if discovered. A player that can discover this information will be able to alter their strategy based on the nature of that information, and therefore become a more competent opponent. In this paper, we employ association rule-mining techniques for predicting item multisets, and show them to be effective in predicting the content of Netrunner decks. We then apply different modifications based on heuristic knowledge of the Netrunner game, and show the effectiveness of techniques which consider this knowledge during rule generation and prediction.","PeriodicalId":6594,"journal":{"name":"2016 IEEE Conference on Computational Intelligence and Games (CIG)","volume":"54 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75611413","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-09-01DOI: 10.1109/CIG.2016.7860441
Kokolo Ikeda, Simon Viennot, Naoyuki Sato
The level of computer programs has now reached professional strength for many games, even for the game of Go recently. A more difficult task for computer intelligence now is to create a program able to coach human players, so that they can improve their play. In this paper, we propose a method to detect and label the bad moves of human players for the game of Go. This task is challenging because even strong human players only agree at a rate of around 50% about which moves should be considered as bad. We use supervised learning with features largely available in many Go programs, and we obtain an identification level close to the one observed between strong human players. Also, an evaluation by a professional player shows that our method is already useful for intermediate-level players.
{"title":"Detection and labeling of bad moves for coaching go","authors":"Kokolo Ikeda, Simon Viennot, Naoyuki Sato","doi":"10.1109/CIG.2016.7860441","DOIUrl":"https://doi.org/10.1109/CIG.2016.7860441","url":null,"abstract":"The level of computer programs has now reached professional strength for many games, even for the game of Go recently. A more difficult task for computer intelligence now is to create a program able to coach human players, so that they can improve their play. In this paper, we propose a method to detect and label the bad moves of human players for the game of Go. This task is challenging because even strong human players only agree at a rate of around 50% about which moves should be considered as bad. We use supervised learning with features largely available in many Go programs, and we obtain an identification level close to the one observed between strong human players. Also, an evaluation by a professional player shows that our method is already useful for intermediate-level players.","PeriodicalId":6594,"journal":{"name":"2016 IEEE Conference on Computational Intelligence and Games (CIG)","volume":"46 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79726810","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-09-01DOI: 10.1109/CIG.2016.7860392
Anders Drachen, Nicholas Ross, Julian Runge, R. Sifa
There are numerous widely disseminated beliefs in the rapidly growing domain of Mobile Game Analytics, notably within the context of the Free-to-Play model. However, the field remains in its infancy, as there is limited conclusive empirical knowledge available across industry and academia, to provide evidence for these beliefs. Additionally, the current knowledge base is highly fragmented. For Mobile Game Analytics to mature, empirical frameworks are needed. In this paper the concept of stylized facts is presented as a means to develop an initial framework for a common understanding of key hypotheses and concepts in the field, as well as organizing the available empirical knowledge. A focus on stylized facts research will not only facilitate communication but also, more importantly, improve the quality and actionability of insights. Unified terminology and a comprehensive collection of stylized facts can be the building blocks for a conceptually well-founded understanding of mobile gaming.
{"title":"Stylized facts for mobile game analytics","authors":"Anders Drachen, Nicholas Ross, Julian Runge, R. Sifa","doi":"10.1109/CIG.2016.7860392","DOIUrl":"https://doi.org/10.1109/CIG.2016.7860392","url":null,"abstract":"There are numerous widely disseminated beliefs in the rapidly growing domain of Mobile Game Analytics, notably within the context of the Free-to-Play model. However, the field remains in its infancy, as there is limited conclusive empirical knowledge available across industry and academia, to provide evidence for these beliefs. Additionally, the current knowledge base is highly fragmented. For Mobile Game Analytics to mature, empirical frameworks are needed. In this paper the concept of stylized facts is presented as a means to develop an initial framework for a common understanding of key hypotheses and concepts in the field, as well as organizing the available empirical knowledge. A focus on stylized facts research will not only facilitate communication but also, more importantly, improve the quality and actionability of insights. Unified terminology and a comprehensive collection of stylized facts can be the building blocks for a conceptually well-founded understanding of mobile gaming.","PeriodicalId":6594,"journal":{"name":"2016 IEEE Conference on Computational Intelligence and Games (CIG)","volume":"131 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81728540","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-09-01DOI: 10.1109/CIG.2016.7860448
Dennis J. N. J. Soemers, C. F. Sironi, T. Schuster, M. Winands
General Video Game Playing (GVGP) is a field of Artificial Intelligence where agents play a variety of real-time video games that are unknown in advance. This limits the use of domain-specific heuristics. Monte-Carlo Tree Search (MCTS) is a search technique for game playing that does not rely on domain-specific knowledge. This paper discusses eight enhancements for MCTS in GVGP; Progressive History, N-Gram Selection Technique, Tree Reuse, Breadth-First Tree Initialization, Loss Avoidance, Novelty-Based Pruning, Knowledge-Based Evaluations, and Deterministic Game Detection. Some of these are known from existing literature, and are either extended or introduced in the context of GVGP, and some are novel enhancements for MCTS. Most enhancements are shown to provide statistically significant increases in win percentages when applied individually. When combined, they increase the average win percentage over sixty different games from 31.0% to 48.4% in comparison to a vanilla MCTS implementation, approaching a level that is competitive with the best agents of the GVG-AI competition in 2015.
通用视频游戏(General Video Game Playing, GVGP)是人工智能的一个领域，智能体在其中玩各种事先未知的实时视频游戏。这限制了特定于领域的启发式的使用。蒙特卡罗树搜索(MCTS)是一种不依赖于特定领域知识的游戏搜索技术。本文讨论了GVGP中MCTS的八个增强功能;渐进历史，N-Gram选择技术，树重用，宽度优先树初始化，损失避免，基于新颖性的修剪，基于知识的评估，和确定性博弈检测。其中一些是从现有文献中已知的，并且是在GVGP的上下文中扩展或引入的，还有一些是对MCTS的新增强。大多数增强在单独应用时都能显著提高胜率。与普通MCTS相比，它们将60场不同游戏的平均胜率从31.0%提高到48.4%，接近2015年gvr - ai比赛中最佳代理的水平。
{"title":"Enhancements for real-time Monte-Carlo Tree Search in General Video Game Playing","authors":"Dennis J. N. J. Soemers, C. F. Sironi, T. Schuster, M. Winands","doi":"10.1109/CIG.2016.7860448","DOIUrl":"https://doi.org/10.1109/CIG.2016.7860448","url":null,"abstract":"General Video Game Playing (GVGP) is a field of Artificial Intelligence where agents play a variety of real-time video games that are unknown in advance. This limits the use of domain-specific heuristics. Monte-Carlo Tree Search (MCTS) is a search technique for game playing that does not rely on domain-specific knowledge. This paper discusses eight enhancements for MCTS in GVGP; Progressive History, N-Gram Selection Technique, Tree Reuse, Breadth-First Tree Initialization, Loss Avoidance, Novelty-Based Pruning, Knowledge-Based Evaluations, and Deterministic Game Detection. Some of these are known from existing literature, and are either extended or introduced in the context of GVGP, and some are novel enhancements for MCTS. Most enhancements are shown to provide statistically significant increases in win percentages when applied individually. When combined, they increase the average win percentage over sixty different games from 31.0% to 48.4% in comparison to a vanilla MCTS implementation, approaching a level that is competitive with the best agents of the GVG-AI competition in 2015.","PeriodicalId":6594,"journal":{"name":"2016 IEEE Conference on Computational Intelligence and Games (CIG)","volume":"30 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80354936","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-09-01DOI: 10.1109/CIG.2016.7860444
Yifan Sun, Chisheng Liang, Steven C. Sutherland, C. Harteveld, D. Kaeli
Player decision modeling can provide useful guidance to understand player performance in serious games. However, current player modeling focuses on high-level abstraction of player behavior rather than decision-level player modeling, and is predominantly applied to entertainment games. In this paper, we describe an approach from game design to data mining and data analysis to determine detailed player decision patterns. We illustrate this approach with VistaLights, a supply chain game we developed based on a recent oil spill event in Houston. With this game, we set up a within-subjects experiment to study decision making under varying circumstances, specifically to consider whether/how a recommendation system can improve human decisions. Using a series of data analysis techniques we built a coarse-grained decision model as well as a fine-grained model to compare players' actions on the game outcomes. The results confirm the need for decision-level modeling and show an ability of our approach to both identify the good and bad decision patterns among players.
{"title":"Modeling player decisions in a supply chain game","authors":"Yifan Sun, Chisheng Liang, Steven C. Sutherland, C. Harteveld, D. Kaeli","doi":"10.1109/CIG.2016.7860444","DOIUrl":"https://doi.org/10.1109/CIG.2016.7860444","url":null,"abstract":"Player decision modeling can provide useful guidance to understand player performance in serious games. However, current player modeling focuses on high-level abstraction of player behavior rather than decision-level player modeling, and is predominantly applied to entertainment games. In this paper, we describe an approach from game design to data mining and data analysis to determine detailed player decision patterns. We illustrate this approach with VistaLights, a supply chain game we developed based on a recent oil spill event in Houston. With this game, we set up a within-subjects experiment to study decision making under varying circumstances, specifically to consider whether/how a recommendation system can improve human decisions. Using a series of data analysis techniques we built a coarse-grained decision model as well as a fine-grained model to compare players' actions on the game outcomes. The results confirm the need for decision-level modeling and show an ability of our approach to both identify the good and bad decision patterns among players.","PeriodicalId":6594,"journal":{"name":"2016 IEEE Conference on Computational Intelligence and Games (CIG)","volume":"68 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87417133","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-09-01DOI: 10.1109/CIG.2016.7860403
Markus Viljanen, A. Airola, T. Pahikkala, J. Heikkonen
Decay of population level daily user activity in Tribeflame Ltd.'s mobile games is found to be determined by elementary differential equations. We describe practical methods for investigating laws underlying the decay of daily user activity in a given cohort, known as retention in the gaming industry. Simple decay patterns are found to accurately describe this evolution. In addition to being of academic interest in sharing parallels to population growth and decay dynamics, this finding has immediate applications in the mobile games industry. Utilizing this finding allows using smaller cohorts of users in intermittent paid acquisition tests and enables game performance forecasting over long timespans.
{"title":"User activity decay in mobile games determined by simple differential equations?","authors":"Markus Viljanen, A. Airola, T. Pahikkala, J. Heikkonen","doi":"10.1109/CIG.2016.7860403","DOIUrl":"https://doi.org/10.1109/CIG.2016.7860403","url":null,"abstract":"Decay of population level daily user activity in Tribeflame Ltd.'s mobile games is found to be determined by elementary differential equations. We describe practical methods for investigating laws underlying the decay of daily user activity in a given cohort, known as retention in the gaming industry. Simple decay patterns are found to accurately describe this evolution. In addition to being of academic interest in sharing parallels to population growth and decay dynamics, this finding has immediate applications in the mobile games industry. Utilizing this finding allows using smaller cohorts of users in intermittent paid acquisition tests and enables game performance forecasting over long timespans.","PeriodicalId":6594,"journal":{"name":"2016 IEEE Conference on Computational Intelligence and Games (CIG)","volume":"31 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79033901","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：