Data Analytics Applications in Gaming and Entertainment

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