Silicon Studio pushes the Data Science frontier to a new limit: YOKOZUNA data Player behavior prediction machine learning platform

After more than 2 years of development YOKOZUNA data will be officially released. The platform’s cutting edge AI, applies the latest advancements in both machine learning and cloud computing to solve the complex data analysis challenges of modern video-games.

Groundbreaking recommendation system for game development Know which players to target, how and when, to increase monetization and engagement

In the last few years, the video-game industry has been witness to a true revolution as both traditional video-game platforms and emerging mobile games have become continuously connected to the internet. This recent paradigm shift allows game developers to collect a huge amount of data in real time while maintaining an active relationship with the players.

Developing a profitable game however can be a challenging endeavor in itself. Thousands of games are published every year and compete for a limited number of players. This rivalry combined with the increasing cost of game production of games requires more efficient development.

To fully take advantage of and maintain a level of competitiveness in this new scenario, it’s paramount to develop adequate machine learning methods that model and predict player behavior, scaling up to millions of monthly active users, and allow an intuitive visualization of the results. This is YOKOZUNA data.

Takehiko Terada, the CEO of Silicon Studio, states that, “Silicon Studio has always been at the forefront of data-driven game development. YOKOZUNA data has proven to be an effective tool and had a tremendous impact on monetization and increasing player retention of our games. For this reason, we have decided to lead the data revolution within the game industry by releasing YOKOZUNA data to the public. We are democratizing Game Data Science.”

Utilizing the latest techniques in Big Data processing and Cloud Computing, YOKOZUNA data scales to games of any size, providing individual behavioral predictions.

A/B testing and push notification integrations empower YOKOZUNA data to automatically discover the best course of actions to be taken.

Lifespan predictions give the ability to know not just which players will leave the game but also when they will leave (in terms of days, in-game level or hours played) and how much they are worth to the life of the game.

Event Simulation and forecasting tools allow for the optimization of marketing and in-game event planning, forecasting future sales and recommending which events should be planned at which time.

The item recommendation system predicts the best item for every player in order to create personalized promotions and better retain key players.

This is just a taste of the features and possibilities that are offered, and new features are continuously in development. YOKOZUNA Data goes beyond analytics offering real actionable predictions and recommendations that can lead to an increase in retention, player engagement and ultimately overall sales.

Highlights of some achievements and milestones of the Data Science Unit of Silicon Studio:

• Two IEEE publications in top Machine Learning conferences
  http://ieeexplore.ieee.org/document/7796943/
  http://ieeexplore.ieee.org/document/7860442/
  
  
• Participation in Game Data Science panel at CIG
  http://cig16.image.ece.ntua.gr/
  
  
• Oral presentations in top Data Science conferences
  
  
• Organization of two editions of Special Session on Game Data Science at DSAA2016 Montreal DSAA2017 Tokyo with key collaborations (e.g. Ubisoft, King, Gameloft and the most renowned Professors in Academia)
  https://sites.ualberta.ca/~dsaa16/
  https://yokozuna.siliconstudio.co.jp/events/GDS-DSAA2017/
  
  
• Head of Data Science at Silicon Studio, Dr. Perianez keynote speaker at Big Data and Analytics innovation summit in Shanghai September 2017 (together with other top companies in machine learning field e.g. DeepMind, Alibaba, etc.)
  https://theinnovationenterprise.com/summits/big-data-analytics-shanghai-2017

About YOKOZUNA data

YOKOZUNA data is a state-of-the-art machine learning engine to predict individual player behavior, a recommendation system, and a player prediction platform that utilizes next generation AI algorithms to move game development into the future.

A free proof of concept is available to show predictions results and advanced analytics of your games at no cost.

Contact us for an interactive demo and a more in-depth explanation at www.yokozunadata.com

About Silicon Studio

Silicon Studio is a Japan-based game engine and middleware company providing quality rendering, optical effects, and post-effects solutions for game development. Silicon Studio also publishes games across mobile, PC and consoles, and develops games for third parties. Silicon Studio is at the forefront of data driven development, player behavioral research and predictive analytics.