Overview
Use data analysis to build better gaming experiences
The video games industry collects vast amounts of data from its users. But most of this data is disregarded despite its value to the gaming industry.
This course will show you how to store and analyse data effectively and gain insights into game users’ actions and behaviours.
You’ll find out about the different models of data, such as tabular data, atomic data, and relational data.
You’ll understand how to store non-relational data at scale, and why data can be hard to distribute.
You’ll learn how to build better gaming experiences and increase profits.
This course is aimed at those who already work in the games industry, but may also be of interest to those looking to work in the sector.
In order to get the best out of this course you should have a laptop or desktop computer (Windows or Mac) that can run virtual machine software such as VirtualBox or Docker. You should be happy to install software on your machine such as Python or R Studio. Links and instructions for installation and use will be included during the course.
Syllabus
- Data in all its glory
- Welcome to Data Science and the Games Industry
- The data exhaust
- Tabular vs Big Data
- Relational Databases
- Disappearances in the CAP triangle
- Breaking the CAP triangle
- NoSQL
- Cassandra
- MongoDb
- Graphs and Graph databases
- Dark Data’s Hiding Place
- Taming the Data Exhaust
- Big data and distributed systems
- Hadoop, HDFS, MapReduce, and other technologies
- Real-time systems
- Lambda
- Analysis is our answer
- Statistics
- Consumer testing
- R and Python
- Bayesian Statistics
- Machine learning and data mining
- The Future