The last decade has witnessed the rise of big data in game development as the increasing proliferation of Internet-enabled gaming devices has made it easier than ever before to collect large amounts of player-related data. At the same time, the emergence of new business models and the diversification of the player base have exposed a broader potential audience, which attaches great importance to being able to tailor game experiences to a wide range of preferences and skill levels. This, in turn, has led to a growing interest in data mining techniques, as they offer new opportunities for deriving actionable insights to inform game design, to ensure customer satisfaction, to maximize revenues, and to drive technical innovation. By now, data mining and analytics have become vital components of game development. The amount of work being done in this area nowadays makes this an ideal time to put together a book on this subject.
Data Analytics Applications in Gaming and Entertainment seeks to provide a cross section of current data analytics applications in game production. It is intended as a companion for practitioners, academic researchers, and students seeking knowledge on the latest practices in game data mining. The chapters have been chosen in such a way as to cover a wide range of topics and to provide readers with a glimpse at the variety of applications of data mining in gaming. A total of 25 authors from industry and academia have contributed 12 chapters covering topics such as player profiling, approaches for analyzing player communities and their social structures, matchmaking, churn prediction and customer lifetime value estimation, communication of analytical results, and visual approaches to game analytics. This book's perspectives and concepts will spark heightened interest in game analytics and foment innovative ideas that will advance the exciting field of online gaming and entertainment.
Author(s): Gunter Wallner
Series: Data Analytics Applications
Publisher: CRC Press
Year: 2019
Language: English
Pages: xxii+284
Cover
Half Title
Title Page
Copyright Page
Dedication
Table of Contents
Preface
How This Book Is Organized
Acknowledgments
Editor
Contributors
1: A Brief Overview of Data Mining and Analytics in Games
1.1 Introduction
1.2 Applications
1.2.1 Data Analytics to Improve Design and Player Experience
1.2.2 Data Analytics to Inform Business Decisions
1.2.3 Data Analytics to Innovate and Optimize Game Technology
1.2.4 Data Analytics to Empower Players and Foster Community Building
1.2.5 Summary
1.3 Limitations
1.4 Visual Analytics
1.5 Conclusions
References
2: Evaluating Gamer Achievements to Understand Player Behavior
2.1 Introduction
2.2 Research Design
2.2.1 NieR: Automata
2.2.2 Steam
2.3 Results
2.4 Discussion
2.5 Conclusions
References
Icon Sources
3: Building Matchmaking Systems
3.1 Introduction
3.2 Running Example
3.3 Queues
3.3.1 Design
3.3.2 Analytics
3.4 Match Builder
3.4.1 Design
3.4.2 Analytics
3.5 Match Scorer
3.5.1 Design
3.5.2 Analytics
3.5.3 Extension: Win Prediction Models
3.6 Player Rating Model
3.6.1 Design
3.6.2 Analytics
3.6.3 Extension: Performance-Based Ratings
3.7 Conclusions
References
4: A Data Science Approach to Exploring Hero Roles in Multiplayer Online Battle Arena Games
4.1 Introduction
4.2 Related Work
4.3 Data Collection
4.3.1 Replay File Collection
4.3.2 Replay File Analysis
4.4 Data Analysis
4.4.1 Clustering Performance Attributes
4.4.2 Identifying Hero Roles
4.4.3 Team Compositions
4.4.4 Classifying Individual Heroes
4.4.5 Comparison to Classifications of Blizzard Entertainment and Popular Fan Sites
4.5 Conclusions
Appendix
References
Icon Source
5: Predicting Customer Lifetime Value in Free-to-Play Games
5.1 Introduction
5.2 Definitions and Terminology
5.3 Applications of CLV Prediction
5.3.1 Customer Acquisition
5.3.2 Customer Retention
5.3.3 Customer Segmentation
5.3.4 Free-to-Play Games
5.4 Models
5.4.1 Average Models
5.4.2 Customer History Models
5.4.2.1 Recency, Frequency, and Monetary Value
5.4.2.2 Pareto/NBD
5.4.3 Markov Chain Models
5.4.4 Supervised Learning Models
5.5 Software Packages
5.5.1 Lifetimes/BTYD
5.5.2 Scikit-Learn
5.6 Conclusions
References
Icon Source
6: Advanced Data Science Models for Player Behavioral Prediction
6.1 Introduction
6.2 Predicting Churn and Player Life Expectancy with Ensemble Learning
6.2.1 Survival Analysis
6.2.2 Survival Trees and Ensembles
6.2.2.1 Decision Trees
6.2.2.2 Survival Trees
6.2.2.3 Survival Ensembles
6.2.3 Data Selection, Modeling, and Validation
6.2.3.1 Data Selection and Kaplan–Meier Visualization
6.2.3.2 Conditional Inference Survival Ensembles
6.2.3.3 Model Validation
6.3 A Machine Learning-Based Lifetime Value Computation: Deep Learning and Parametric Models
6.3.1 Historical and Predictive Approaches to Compute Lifetime Value
6.3.1.1 Pareto/Negative Binomial Distribution Model
6.3.1.2 Other Parametric Models
6.3.2 Lifetime Value Using Deep Learning Methods
6.3.2.1 Deep Multilayer Perceptron
6.3.2.2 Convolutional Neural Networks
6.3.3 Lifetime Value Using Deep Learning and Parametric Models: A Case Study
6.3.3.1 Dataset and Predictor Variables
6.3.3.2 Results and Discussion
6.4 Conclusions
Acknowledgments
References
Color Plates
7: Integrating Social and Textual Analytics into Game Analytics
7.1 Introduction
7.2 Background
7.2.1 Traditional Metrics and Key Performance Indicators
7.2.2 Textual Methods and Computational Linguistics
7.2.2.1 Text Normalization and Social Media Linguistic Analysis
7.2.2.2 Text Mining and Sentiment Analysis
7.2.2.3 Information Retrieval
7.2.2.4 Tools Development
7.3 Integration Framework
7.4 Implementation Guide
7.4.1 Traditional Metrics Workflow
7.4.2 Integration of Social and Textual Analytics
7.5 Case Study
7.5.1 About My Singing Monsters
7.5.2 Purpose of the Case Study
7.5.3 General Approach
7.5.4 Activation, Engagement, and Retention of Posters versus Non-Posters
7.5.5 Poster Social Effort
7.5.6 Sentiment Analysis
7.6 Conclusions
Appendix
References
8: Social Network Analysis Applied to Game Communities to Identify Key Social Players
8.1 Introduction
8.2 Related Work
8.3 The Game: Tom Clancy’s The Division
8.4 Method
8.4.1 Dataset
8.4.2 Data Analysis
8.4.3 Influencer Identification
8.4.4 Influencer Comparison
8.4.5 Influencer Impact on Communities
8.5 Results
8.5.1 Influencer Identification
8.5.2 Influencer Comparison
8.5.3 Influencer Impact on Communities
8.6 Conclusions
Acknowledgments
References
9: Methodological and Epistemological Reflections on the Use of Game Analytics toward Understanding the Social Relationships of a Video Game Community
9.1 Introduction
9.2 Context
9.2.1 Shifting from Games-as-a-Product to Games-as-a-Service
9.2.2 Predominance of Analytics Tools in the Industry
9.2.3 Community Metrics
9.2.4 Social Network Analysis
9.2.5 Sentiment Analysis
9.2.6 Responding to Questions in Communication Studies Using Community Metrics
9.3 Mixed-Methods Research with In-Game and Out-of-Game Data
9.4 Challenges That Arise from the Nature of the Collected Data Inside the Game
9.4.1 Results Whose Meaning Varies According to Context
9.4.2 Partial and Imprecise Data
9.4.3 Collected Information Aggregated with Other Data
9.5 Conclusions
References
10: An Analyst’s Guide to Communication
10.1 Introduction
10.2 Stage 1—Understand the Problem
10.2.1 Create a Process
10.2.2 Play the Game
10.2.3 Rephrase the Problem
10.2.4 Describe the Next Step
10.3 Stage 2—Prioritize the Work
10.3.1 Value versus Complexity Quadrant
10.4 Stage 3—Define the Goal
10.4.1 Definition of Done
10.5 Stage 4—Simplify the Results
10.6 Stage 5—Teach the Learnings
10.6.1 Get Them to Ask Questions
10.6.2 Make It Interactive
10.6.3 Make It Personal
10.6.4 Repeat—In Different Ways
10.7 Conclusions
Acknowledgments
Reference
Icon Sources
11: A Taxonomy of Visualizations for Gameplay Data
11.1 Introduction
11.2 Gameplay Data
11.3 Taxonomy
11.3.1 Comparison
11.3.2 Distribution
11.3.3 Relationships
11.3.4 Time
11.3.5 Space
11.3.6 Flow
11.4 Conclusions
References
12: Co-Design of an Interactive Analytics System for Multiplayer Online Battle Arena Game Occurrences
12.1 Introduction
12.2 Related Work
12.2.1 Visual Analysis of Gameplay Behavior
12.2.2 Data-Driven Approaches to Gameplay Data
12.3 Background and Requirement Analysis
12.3.1 About MOBA Games
12.3.2 Requirements from Domain Experts
12.4 Workflow and System Overview
12.4.1 Data Preprocessing
12.5 Deep Model-Based Analysis
12.5.1 Motivations for Deep Model-Based Analysis
12.5.2 Occurrence Classification
12.5.3 Deep Neural Network Architecture
12.5.4 Model Training
12.5.5 Spatio-Temporal Segments of Interest Identification
12.6 Visualization Design
12.6.1 Feature Map View
12.6.2 Statistical View
12.6.3 Detailed Match View
12.6.3.1 Trajectory Simulation
12.6.3.2 Critical Events Timeline
12.6.3.3 Equipment Upgrade Timeline
12.6.3.4 Resource Distribution
12.7 Use Cases
12.7.1 Case One: Inter-Occurrence Comparison
12.7.1.1 Observing Differences/Similarities among Occurrences
12.7.1.2 Reasoning About Potential Activities Behind an Occurrence
12.7.1.3 Statistical Analysis of an Occurrence
12.7.2 Case Two: Intra-Occurrence Pattern Verification
12.7.2.1 Verification of Snowballing
12.7.2.2 Verification of Comeback Time-Points
12.7.2.3 Final Push in Back and Forth
12.7.3 Experts’ Feedback and Discussion
12.7.3.1 System Usability
12.7.3.2 Visualization Design and Interactions
12.7.3.3 Suggestions
12.8 Conclusions
References
Index
