PREDICTING THE FUTURE OF YOUR GAME. YOKOZUNA data A KEYWORDS STUDIO

Transcription

1 PREDICTING THE FUTURE OF YOUR YOKOZUNA data GAME. A KEYWORDS STUDIO

2 PUSHING THE GAME DATA SCIENCE FRONTIER TO A NEW LIMIT: A state-of-the-art machine learning engine that predicts individual player behaviour

3 WHY IS YOKOZUNA DATA SO UNIQUE?

4 IT PREDICTS WHEN EVERY PLAYER WILL LEAVE THE GAME DATE LEVEL PLAYTIME MONEY

5 IT PREDICTS WHICH ITEM THEY ARE WILLING TO PURCHASE NEXT probabilities Billing history Playtime Time to next purchase 08/06 08/15 08/27 09/06 Yokozuna Data predicts which virtual and actual items players want to will purchase at anytime

6 RECOMMENDS THE BEST SEQUENCE OF EVENTS TO MAXIMIZE PLAYER ENGAGEMENT CONSIDERING EXTERNAL AND ENVIRONMENTAL FACTORS

7 WHICH BUSINESS PROBLEMS DOES IT SOLVE?

8 PLAYER RETENTION GAME OPTIMIZATION GAME DEVELOPMENT

9 HOW DOES IT WORK?

10 ncr n! = r!(n-r)! Machine Learning AI Models Video Game Data Individual Player Behavioural Predictions Take Action

11 WHY IS IT SO GROUNDBREAKING?

12 OPERATIONAL PLAYER BEHAVIOURAL PREDICTION The first recommendation system and routine prediction platform that utilizes next-gen AI algorithms to move game development into the future.

13 DEEP LEARNING AND ENSEMBLE LEARNING Deep Learning and Ensemble Learning provide individual behavioral predictions, simulations and personalized challenges and rewards.

14 BIG DATA Utilizing the latest techniques in big data processing and cloud computing, YOKOZUNA data scales to datasets of any size.

15 HOW ACCURATE ARE OUR PREDICTIONS?

16 We won both tracks of the NCSoft's Blade & Soul Game Data Science competition at the IEEE 2017 Conference on Computational Intelligence in Games (CIG) Track 1 Which players will leave the game Track 2 When they will leave the game Team Test1 Score Test2 Score Total Score Rank Team Test1 Score Test2 Score YokozunaData (Japan) YokozunaData (Japan) UTU (Finland) IISLABSKKU TripleS (Korea) UTU (Finland) TheCowKing TripleS (Korea) goedleio DTND

17 YOKOZUNA DATA PEER-REVIEWED ARTICLES CHURN PREDICTION IN MOBILE SOCIAL GAMES: TOWARDS A COMPLETE ASSESSMENT USING SURVIVAL ENSEMBLES DISCOVERING PLAYING PATTERNS: TIME SERIES CLUSTERING OF FREE-TO-PLAY GAME DATA GAMES AND BIG DATA: A SCALABLE MULTI-DIMENSIONAL CHURN PREDICTION MODEL FORECASTING PLAYER BEHAVIORAL DATA AND SIMULATING IN-GAME EVENTS THE WINNING SOLUTION TO THE IEEE CIG 2017 GAME DATA MINING COMPETITION A MACHINE-LEARNING ITEM RECOMMENDATION SYSTEM FOR VIDEO GAMES CUSTOMER LIFETIME VALUE IN VIDEO GAMES USING DEEP LEARNING AND PARAMEDIC MODELS A. Perianez, A. Saas, A. Guitart and C. Magne IEEE DSAA 2016 Montreal A. Guitart, A. Perianez and A. Saas, IEEE CIG 2016 Santorini P. Bertens, A. Guitart and A. Perianez, A. Saas, IEEE CIG 2017 New York A. Guitart, P. Chen, P. Bertens and A. Perianez IEEE FICC 2018 Singapore A. Guitart, P. Chen, A. Periáñez P. Chen, A. Guitart, P. Bertens, A. Periáñez IEEE CIG 2018 Maastricht P. Chen, A. Guitart, A. Fernandez de Rio and A. Periáñez IEEE Big Data 2018 Seattle

18 WHO IS BEHIND YOKOZUNA DATA?

19 Awarded with Marie Curie individual fellowship. Most renowned award in Europe. Researcher Scientist at CERN, the European Organization for Nuclear Research, one of the world's largest and most respected centres for scientific research. Top 5 Data Scientist across the company. In charge of 40 countries, covering Europe, Middle East and Africa. ÁFRICA PERIÁÑEZ Founder & CEO PhD Mathematics (Ensemble Learning) University of Reading MSc String Theory CERN MSc Theoretical Physics UAM BSc Physics UAM Research Data Scientist for German Government to assimilate satellite data with a novel Ensemble Learning Research Data Scientist at RIKEN to assimilate HIMAWARI big data. Working with the world-leading K-computer

20 THE TEAM Africa Perianez, PhD Founder & CEO Ana Fernández, MSc SENIOR RESEARCH DATA SCIENTIST Pei Pei Chen, MSc MACHINE LEARNING ENGINEER LEAD Shi Hui Tan, MSc DATA SCIENTIST Anna Guitart, MSc DATA SCIENTIST Jing Li, PhD MACHINE LEARNING ENGINEER Cristian Conteduca, MSc BACKEND ENGINEER LEAD Peng Xiao, BSc BIG DATA ENGINEER Nitin Kumar, MSc FULL-STACK ENGINEER Pooja Revanna, MSc BACKEND ENGINEER Dexian Tang, MSc BIG DATA ENGINEER Vitor Santos, MA DESIGN & BUSINESS DIRECTOR Alvaro de Benito, MA PR & COMMUNICATION LEAD Yu-Kai Hung, MSc COMMUNITY MANAGER FOR ASIA Omid Aladini, MSc DATA INFRASTRUCTURE ADVISOR Javier Grande, PhD SCIENTIFIC EDITOR

21 MILESTONES

22 INTERNATIONAL PRESS COVERAGE BY TOP MEDIA 1 WINNERS OF GAME CHURN PREDICTION CONTEST IEEE NCSOFT +40 CMU APLICANTS FOR SUMMER INTERNSHIP BEST PAPER AWARD AT FICC PEER-REVIEWED ARTICLES PUBLISHED IN TOP MACHINE LEARNING CONFERENCES

23 WHAT IS THE MEDIA SAYING ABOUT US?

24 Game Makers Are Profiling Players to Keep Them Hooked An algorithm that knows when you'll get bored with your favourite video game The next generation of video games will use AI to personalize your experience Game makers deploy deep-learning AI algorithms to keep players coming back for more Data scientists are already working on ways to leverage historical data to create a model for prediction of when a player will stop playing. This algorithm can predict users' affinity towards video games