SlideShare a Scribd company logo
1 of 47
Download to read offline
Understanding and
improving games through
machine learning
Natasha Latysheva
Data Scientist
Jagex Games Studio
This talk:
1. Introduction to Jagex
2. Recap of main machine learning
fields + examples
3. Fun ML in video games in general
4. ML projects at Jagex Data Science
• Identifying player personas
• Deep learning player lifecycle
sequences
• Automatic bot and abuse
detection
• Trading card deck analysis
• Quest recommender systems
Jagex Game Studios
• Video game development company based in
Cambridge
• Best known for Runescape, the world's
largest free-to-play massively multiplayer
online role-playing game (MMORPG). First
released in 2001!
• Extremely community oriented game
• Old School Runescape was released in 2013
RuneScape
Main..
.. and
RuneScape
Old School
TF2 meets
Minecraft!
A quick machine
learning recap
Machine learning recap
Essentially learning patterns from data.
Branches of ML:
• 1. Supervised learning.
• Most familiar names, e.g. linear regression,
logistic regression, decision trees, random
forests, SVMs, many neural nets.
• Algorithm is presented with input data and
explicit labels on that input. Learn signals
associating input data with labels.
• Everything from good ole iris classification to
detecting diseased patients from complex
medical images.
Machine learning recap
2. Unsupervised learning.
• No explicitly labelled data, instead often seeking
to find natural sub-groups of similar data points
within the data.
• Describing the structure of the dataset.
• Objective evaluation of accuracy often
difficult/not possible
• Common methods:
• Clustering methods like k-means and
hierarchical clustering
• Dimensionality reduction methods like
principal components analysis
• Outlier/anomaly detection
• Some NNs, e.g. generative adversarial
networks (GANs)
Larsen et al. 2016
Machine learning recap
3. Reinforcement learning.
• Agent must maximise cumulative reward by
learning to optimally interact with an
environment by choosing ‘good’ actions
• E.g. robot must come up with correct limb
positions and joint torque to move
efficiently/quickly
• Manufacturing program must maximise total
units of product produced each day by
controlling/tuning sub-processes
• Video game player agent must process the
information from pixels on the screen to
operate virtual keyboard + mouse to choose
when to turn, apply brakes, gas, etc.
DuskDrive (OpenAI Universe, 2016)
Houthooft et al. 2017
Fun machine learning in
video games examples
1. DeepMind
• Classic Atari games
• Learning from raw pixel feeds to
maximise future cumulative reward
(i.e. score), no previous information
encoded
• Ability to generalise skill playing
across games
• In some cases, outperforming human
players
• Deep Q-network approach
• Combining deep learning of the
value function Q(s, a) with RL +
experience replay
• Deep NN is Q(s, a) approximator,
trained with Bellman updates Compulsory DeepMind demo:
https://www.youtube.com/watch?v=V1eYniJ0Rnk
Mnih et al., 2015
DeepMind handling quite complex games
DeepMind handling quite complex games
• 2. Hitman: NPC locomotion learning with RL
• 3. Hearthstone (collectible card game)
• 3. Hearthstone (collectible card game)
Bursztein, 2014
5. Predicting outcome:
Domain experts (like casters) generate metrics (per turn +
cumulative) that seem important to winning a game:
• Mana advantage (delta mana spent in turn)
• Board advantage (delta # minions)
• Hand size advantage
• Board mana advantage (delta total mana spent), etc.
• No info on hero class or health
• 4. Candy Crush (King)
Recent and upcoming ML
projects at Jagex
1. Identifying player
personas
.
Identifying player personas
• Understand different archetypes of players
in Runescape
• Ultimately we would like to have a better
sense of our customer base
• Helps games devs
• Helps us understand the motivations, churn
behaviours, and value of our customers
.
Identifying player personas
• Draw inspiration from Bartel types
• Generated ~280 features to quantify our player
behaviour
• Loosely based on Bartle Types (Killers, Achievers,
Socializers, Explorers)
• Quickly abandoned
• Example behavioural features
• Chat Rank Score
• Skill Heterogeneity
• Forum Interactions
• Economic Activity
• Social Clustering Coefficients
• Abilities Used During Play
.
Identifying player personas
• Data cleaning:
• Normalising by total and that year play time,
logging certain variables
• Dimensionality reduction using principal
components analysis
• Identifying optimal number of clusters using
silhouette plots or tSNE
Then… doing the clustering in PC space!
Life stages
• Differences in playtime both overall and recently are such a strong differentiating factor between
players that you first need to cluster on life cycle stages
Life stages
Name % Median
Lifetime
Playtime
Median
Yearly
Playtime
Little Activity
Short Lifetime Playtime
30.7% 3h 3h
Little Activity
Long Lifetime Playtime
22.1% 590h 4h
Active
Mid Lifetime Playtime
22.2% 75h 35h
Extremely Active
Extreme Lifetime
Playtime
25% 2130h 320h
• The extremely dedicated players make up a huge proportion of total revenue.
Playstyles interacting with lifecycle stages
• Can observe which play styles emerge
or dominate at which lifecycle stages
• Can characterise transitions between
the different personas in consecutive
years
• Importantly: Quantify which types of
players tend to abandon the game
2. Deep learning player
lifecycle sequences
Player lifecycle sequences
Matt Project
• Players can undergo a variety of business relevant lifecycle
transitions.
Player lifecycle sequences
Matt Project
• Number of possible combinations, complexity of transitions,
scale of data, etc. leads to a difficult modelling problem
• Goal: We want to learn more about the player base and
how their lifecycle stages change.
• Two approaches:
• 1. Building transition probability matrices to examine
trends and project player states forward into the future
Matt Project
• Transition matrix approach does a surprisingly good job.
Deep learning player lifecycle sequences Matt Project
• 2. Building a recurrent neural network (specifically, an LSTM RNN) to learn the types of transitions that
happen and project these forward into the future
• Inherent memory to the system.
• But - difficult and time-consuming to train! GPUs help.
• On the plus side, can generate sequences seeded with multiple states. Also, in theory can learn
quite complex patterns.
• Models operational but need to tune hyperparameters and compare performance to transition
matrices.
[Colah’s blog]
3. Sentiment, bot and
abuse detection work
Matt Project
Sentiment, bot and abuse detection work
Matt Project
• At the moment we:
• Help community team understand the popularity of
updates using sentiment detection
• Very simple model – Naïve Bayes classifier run over
in-game chat to identify emotional valence
• Detect instances of harassment
• Search through text with preset list of regular
expressions
• Try to learn more complex language models
• Using word2vec to identify words with similar
semantic meanings, identify harassment using
learned vector embeddings
Matt Project
[Saed Sayad]
In progress…
Training deep
convolutional
neural nets to
identify bot-like
mouse
movements
[Adit Deshpande]
Common CNN architecture
[Also working to automate bot removal in other ways]
.
4. Trading card deck analysis
• Play a sequence of cards in a sequence to
create a quest for your legend
• Many cards have additional effects that buff
your character, provide weapons, alter
creature power, or grief / damage your
opponent
• Games span 5 chapters where each player
places up to 4 cards per chapter
• The gameplay is combo-oriented where card
play sequence is very important
Miro Project
.
Build card vectors with word2vec
• Learn card vectors using Word2Vec
algorithm:
• Given a card vector, predict the
remaining cards that were played by
the player in that chapter.
This worked surprisingly well!
• Cards with similar effects clustered
together
• Legend specific cards clustered together
• Common cards that combo well with
Legend specific cards are located in a
region of space close to the Legend
Miro Project
.
Build deck vectors with word2vec
• Tweak Word2Vec algorithm (more akin to
Paragraph2Vec) to learn vector
representation for custom decks
• Deck vectors naturally learned archetype
clusters without being explicitly taught
• Decks from different legends that play by
similar strategies tend to cluster in the same
region of space
• Deck vectors can be used down-stream in
other ML tasks
• Matchmaking
• assessing deck quality
• recommending cards
• predicting churn
Miro Project
• Card and deck vectors userful for game devs for exploring the space of
decks real players use
• Interactive web application for exploring decks by hovering over
decks, filtering by cards, player rank, and win rate
• Built clustering tool on top of deck vectors to allow devs to quickly
identify common cards within a region of ‘deck space’
• View summary statistics on the clusters (win rates, play rates,
cluster sizes)
• This is used to identify balance issues in game, identify how players are
playing decks, and categorize player play-styles
Miro Project
Chronicle project conclusions
5. Quest recommender
system
Matt and Miro Project
• Ultimate goal: help guide players towards
appropriate and interest-relevant content
• Starting point: recommend appropriate quests
to players.
• Modelling using 2 approaches:
• 1. Restricted Boltzmann Machine (RBM)
trained on past quest data
• 2. Matrix factorisation on past quest data
with a REST API built to interface with game
Miro Project
Quest recommender system
Matt and Miro Project
[deeplearning4j]
Acknowledgements
• Data Science Team!
• Miroslaw Horbal
• Matt Dixon
• Babis Georgiadis
• Katie Scott
• Joel Graham
• Ilian Mitev
• Analytics Team 
Questions?

More Related Content

What's hot

Game Connection Paris 2016 - Making games pay: data secrets for game monetiza...
Game Connection Paris 2016 - Making games pay: data secrets for game monetiza...Game Connection Paris 2016 - Making games pay: data secrets for game monetiza...
Game Connection Paris 2016 - Making games pay: data secrets for game monetiza...Lauren Cormack
 
iGaming webinar - Real time player management lessons from social casino
iGaming webinar - Real time player management lessons from social casinoiGaming webinar - Real time player management lessons from social casino
iGaming webinar - Real time player management lessons from social casinoLauren Cormack
 
Achieving better engagement and LTVs by combining gamification and real-time ...
Achieving better engagement and LTVs by combining gamification and real-time ...Achieving better engagement and LTVs by combining gamification and real-time ...
Achieving better engagement and LTVs by combining gamification and real-time ...deltaDNA
 
UK GIAF: Winter 2015
UK GIAF: Winter 2015UK GIAF: Winter 2015
UK GIAF: Winter 2015deltaDNA
 
What the best games know that the rest don't - Isaac Roseboom, deltaDNA
What the best games know that the rest don't - Isaac Roseboom, deltaDNAWhat the best games know that the rest don't - Isaac Roseboom, deltaDNA
What the best games know that the rest don't - Isaac Roseboom, deltaDNALauren Cormack
 
Deltadna achieving better engagement and LTV by combining gamification and ...
Deltadna   achieving better engagement and LTV by combining gamification and ...Deltadna   achieving better engagement and LTV by combining gamification and ...
Deltadna achieving better engagement and LTV by combining gamification and ...deltaDNA
 
Transforming player value - iGaming webinar
Transforming player value - iGaming webinar Transforming player value - iGaming webinar
Transforming player value - iGaming webinar Lauren Cormack
 
GIAF USA Winter 2015
GIAF USA Winter 2015GIAF USA Winter 2015
GIAF USA Winter 2015deltaDNA
 
GIAF London Fall 2017 - Important trends in ad strategies and how to benefit ...
GIAF London Fall 2017 - Important trends in ad strategies and how to benefit ...GIAF London Fall 2017 - Important trends in ad strategies and how to benefit ...
GIAF London Fall 2017 - Important trends in ad strategies and how to benefit ...deltaDNA
 
Analytics: going from crushing candy to delivering dinners
Analytics: going from crushing candy to delivering dinnersAnalytics: going from crushing candy to delivering dinners
Analytics: going from crushing candy to delivering dinnersdeltaDNA
 
80% data 20% luck - How to make profitable games in 2019
80% data 20% luck - How to make profitable games in 201980% data 20% luck - How to make profitable games in 2019
80% data 20% luck - How to make profitable games in 2019deltaDNA
 
GIAF USA Winter 2015 - The secrets to successful F2P ad monetization
GIAF USA Winter 2015 - The secrets to successful F2P ad monetization GIAF USA Winter 2015 - The secrets to successful F2P ad monetization
GIAF USA Winter 2015 - The secrets to successful F2P ad monetization Lauren Cormack
 
Important trends in ad strategies and how to benefit from them
Important trends in ad strategies and how to benefit from themImportant trends in ad strategies and how to benefit from them
Important trends in ad strategies and how to benefit from themdeltaDNA
 
Analytics - How and why you are making a mess of it and ruining your analysts...
Analytics - How and why you are making a mess of it and ruining your analysts...Analytics - How and why you are making a mess of it and ruining your analysts...
Analytics - How and why you are making a mess of it and ruining your analysts...deltaDNA
 
EGR webinar 2016 - Real-time approaches to fraud and social responsibility
EGR webinar 2016 - Real-time approaches to fraud and social responsibilityEGR webinar 2016 - Real-time approaches to fraud and social responsibility
EGR webinar 2016 - Real-time approaches to fraud and social responsibilityLauren Cormack
 
How to make profitable games in 2019
How to make profitable games in 2019How to make profitable games in 2019
How to make profitable games in 2019deltaDNA
 
How to Make your Gaming App a Success
How to Make your Gaming App a SuccessHow to Make your Gaming App a Success
How to Make your Gaming App a SuccessdeltaDNA
 
Emily Greer at GDC 2018: Data-Driven or Data-Blinded?
Emily Greer at GDC 2018: Data-Driven or Data-Blinded?Emily Greer at GDC 2018: Data-Driven or Data-Blinded?
Emily Greer at GDC 2018: Data-Driven or Data-Blinded?Kongregate
 
Quick to Market – 1 Game Every 8 Weeks | Jesse Divnich
Quick to Market – 1 Game Every 8 Weeks | Jesse DivnichQuick to Market – 1 Game Every 8 Weeks | Jesse Divnich
Quick to Market – 1 Game Every 8 Weeks | Jesse DivnichJessica Tams
 
Double Game Revenue & Engagement:10 Killer Insights
Double Game Revenue & Engagement:10 Killer InsightsDouble Game Revenue & Engagement:10 Killer Insights
Double Game Revenue & Engagement:10 Killer InsightsdeltaDNA
 

What's hot (20)

Game Connection Paris 2016 - Making games pay: data secrets for game monetiza...
Game Connection Paris 2016 - Making games pay: data secrets for game monetiza...Game Connection Paris 2016 - Making games pay: data secrets for game monetiza...
Game Connection Paris 2016 - Making games pay: data secrets for game monetiza...
 
iGaming webinar - Real time player management lessons from social casino
iGaming webinar - Real time player management lessons from social casinoiGaming webinar - Real time player management lessons from social casino
iGaming webinar - Real time player management lessons from social casino
 
Achieving better engagement and LTVs by combining gamification and real-time ...
Achieving better engagement and LTVs by combining gamification and real-time ...Achieving better engagement and LTVs by combining gamification and real-time ...
Achieving better engagement and LTVs by combining gamification and real-time ...
 
UK GIAF: Winter 2015
UK GIAF: Winter 2015UK GIAF: Winter 2015
UK GIAF: Winter 2015
 
What the best games know that the rest don't - Isaac Roseboom, deltaDNA
What the best games know that the rest don't - Isaac Roseboom, deltaDNAWhat the best games know that the rest don't - Isaac Roseboom, deltaDNA
What the best games know that the rest don't - Isaac Roseboom, deltaDNA
 
Deltadna achieving better engagement and LTV by combining gamification and ...
Deltadna   achieving better engagement and LTV by combining gamification and ...Deltadna   achieving better engagement and LTV by combining gamification and ...
Deltadna achieving better engagement and LTV by combining gamification and ...
 
Transforming player value - iGaming webinar
Transforming player value - iGaming webinar Transforming player value - iGaming webinar
Transforming player value - iGaming webinar
 
GIAF USA Winter 2015
GIAF USA Winter 2015GIAF USA Winter 2015
GIAF USA Winter 2015
 
GIAF London Fall 2017 - Important trends in ad strategies and how to benefit ...
GIAF London Fall 2017 - Important trends in ad strategies and how to benefit ...GIAF London Fall 2017 - Important trends in ad strategies and how to benefit ...
GIAF London Fall 2017 - Important trends in ad strategies and how to benefit ...
 
Analytics: going from crushing candy to delivering dinners
Analytics: going from crushing candy to delivering dinnersAnalytics: going from crushing candy to delivering dinners
Analytics: going from crushing candy to delivering dinners
 
80% data 20% luck - How to make profitable games in 2019
80% data 20% luck - How to make profitable games in 201980% data 20% luck - How to make profitable games in 2019
80% data 20% luck - How to make profitable games in 2019
 
GIAF USA Winter 2015 - The secrets to successful F2P ad monetization
GIAF USA Winter 2015 - The secrets to successful F2P ad monetization GIAF USA Winter 2015 - The secrets to successful F2P ad monetization
GIAF USA Winter 2015 - The secrets to successful F2P ad monetization
 
Important trends in ad strategies and how to benefit from them
Important trends in ad strategies and how to benefit from themImportant trends in ad strategies and how to benefit from them
Important trends in ad strategies and how to benefit from them
 
Analytics - How and why you are making a mess of it and ruining your analysts...
Analytics - How and why you are making a mess of it and ruining your analysts...Analytics - How and why you are making a mess of it and ruining your analysts...
Analytics - How and why you are making a mess of it and ruining your analysts...
 
EGR webinar 2016 - Real-time approaches to fraud and social responsibility
EGR webinar 2016 - Real-time approaches to fraud and social responsibilityEGR webinar 2016 - Real-time approaches to fraud and social responsibility
EGR webinar 2016 - Real-time approaches to fraud and social responsibility
 
How to make profitable games in 2019
How to make profitable games in 2019How to make profitable games in 2019
How to make profitable games in 2019
 
How to Make your Gaming App a Success
How to Make your Gaming App a SuccessHow to Make your Gaming App a Success
How to Make your Gaming App a Success
 
Emily Greer at GDC 2018: Data-Driven or Data-Blinded?
Emily Greer at GDC 2018: Data-Driven or Data-Blinded?Emily Greer at GDC 2018: Data-Driven or Data-Blinded?
Emily Greer at GDC 2018: Data-Driven or Data-Blinded?
 
Quick to Market – 1 Game Every 8 Weeks | Jesse Divnich
Quick to Market – 1 Game Every 8 Weeks | Jesse DivnichQuick to Market – 1 Game Every 8 Weeks | Jesse Divnich
Quick to Market – 1 Game Every 8 Weeks | Jesse Divnich
 
Double Game Revenue & Engagement:10 Killer Insights
Double Game Revenue & Engagement:10 Killer InsightsDouble Game Revenue & Engagement:10 Killer Insights
Double Game Revenue & Engagement:10 Killer Insights
 

Similar to Understanding and improving games through machine learning - Natasha Latysheva

Leszek Szczepański (Guerrilla Games) - Creating quests in the open world of H...
Leszek Szczepański (Guerrilla Games) - Creating quests in the open world of H...Leszek Szczepański (Guerrilla Games) - Creating quests in the open world of H...
Leszek Szczepański (Guerrilla Games) - Creating quests in the open world of H...DevGAMM Conference
 
What We Talk About When We Talk About Mid-Core
What We Talk About When We Talk About Mid-CoreWhat We Talk About When We Talk About Mid-Core
What We Talk About When We Talk About Mid-CoreAdam Gutterman
 
Artificial Intelligence in Gaming
Artificial Intelligence in GamingArtificial Intelligence in Gaming
Artificial Intelligence in GamingAnmol Sawhney
 
VDP2016 - Lecture 13 Data driven game design
VDP2016 - Lecture 13 Data driven game designVDP2016 - Lecture 13 Data driven game design
VDP2016 - Lecture 13 Data driven game designPier Luca Lanzi
 
Building Non-Linear Narratives in Horizon Zero Dawn
Building Non-Linear Narratives in Horizon Zero DawnBuilding Non-Linear Narratives in Horizon Zero Dawn
Building Non-Linear Narratives in Horizon Zero DawnGuerrilla
 
Procedural Processes - Lessons Learnt from Automated Content Generation in "E...
Procedural Processes - Lessons Learnt from Automated Content Generation in "E...Procedural Processes - Lessons Learnt from Automated Content Generation in "E...
Procedural Processes - Lessons Learnt from Automated Content Generation in "E...Luke Dicken
 
Intro to Games Based Learning - Week 1
Intro to Games Based Learning  - Week 1Intro to Games Based Learning  - Week 1
Intro to Games Based Learning - Week 1center4edupunx
 
Science and Videogames. Computational intelligence in videogames
Science and Videogames. Computational intelligence in videogamesScience and Videogames. Computational intelligence in videogames
Science and Videogames. Computational intelligence in videogamesAntonio Mora
 
Game Modding Lecture 2
Game Modding Lecture 2Game Modding Lecture 2
Game Modding Lecture 2Charles Palmer
 
Developing applications and games in Unity engine - Matej Jariabka, Rudolf Ka...
Developing applications and games in Unity engine - Matej Jariabka, Rudolf Ka...Developing applications and games in Unity engine - Matej Jariabka, Rudolf Ka...
Developing applications and games in Unity engine - Matej Jariabka, Rudolf Ka...gamifi.cc
 
MattEkinsJumpstartWork
MattEkinsJumpstartWorkMattEkinsJumpstartWork
MattEkinsJumpstartWorkMatt Ekins
 
Technical aspectof game design (Game Architecture)
Technical aspectof game design (Game Architecture)Technical aspectof game design (Game Architecture)
Technical aspectof game design (Game Architecture)Rajkumar Pawar
 
LearningKit.ppt
LearningKit.pptLearningKit.ppt
LearningKit.pptbutest
 
Making A Game Engine Is Easier Than You Think
Making A Game Engine Is Easier Than You ThinkMaking A Game Engine Is Easier Than You Think
Making A Game Engine Is Easier Than You ThinkGorm Lai
 
Maximize Your Production Effort (English)
Maximize Your Production Effort (English)Maximize Your Production Effort (English)
Maximize Your Production Effort (English)slantsixgames
 
Long Lin at AI Frontiers : AI in Gaming
Long Lin at AI Frontiers : AI in GamingLong Lin at AI Frontiers : AI in Gaming
Long Lin at AI Frontiers : AI in GamingAI Frontiers
 

Similar to Understanding and improving games through machine learning - Natasha Latysheva (20)

Leszek Szczepański (Guerrilla Games) - Creating quests in the open world of H...
Leszek Szczepański (Guerrilla Games) - Creating quests in the open world of H...Leszek Szczepański (Guerrilla Games) - Creating quests in the open world of H...
Leszek Szczepański (Guerrilla Games) - Creating quests in the open world of H...
 
What We Talk About When We Talk About Mid-Core
What We Talk About When We Talk About Mid-CoreWhat We Talk About When We Talk About Mid-Core
What We Talk About When We Talk About Mid-Core
 
Data Driven Game Design
Data Driven Game DesignData Driven Game Design
Data Driven Game Design
 
Artificial Intelligence in Gaming
Artificial Intelligence in GamingArtificial Intelligence in Gaming
Artificial Intelligence in Gaming
 
VDP2016 - Lecture 13 Data driven game design
VDP2016 - Lecture 13 Data driven game designVDP2016 - Lecture 13 Data driven game design
VDP2016 - Lecture 13 Data driven game design
 
Building Non-Linear Narratives in Horizon Zero Dawn
Building Non-Linear Narratives in Horizon Zero DawnBuilding Non-Linear Narratives in Horizon Zero Dawn
Building Non-Linear Narratives in Horizon Zero Dawn
 
Procedural Processes - Lessons Learnt from Automated Content Generation in "E...
Procedural Processes - Lessons Learnt from Automated Content Generation in "E...Procedural Processes - Lessons Learnt from Automated Content Generation in "E...
Procedural Processes - Lessons Learnt from Automated Content Generation in "E...
 
Intro to Games Based Learning - Week 1
Intro to Games Based Learning  - Week 1Intro to Games Based Learning  - Week 1
Intro to Games Based Learning - Week 1
 
Science and Videogames. Computational intelligence in videogames
Science and Videogames. Computational intelligence in videogamesScience and Videogames. Computational intelligence in videogames
Science and Videogames. Computational intelligence in videogames
 
Game Modding Lecture 2
Game Modding Lecture 2Game Modding Lecture 2
Game Modding Lecture 2
 
Developing applications and games in Unity engine - Matej Jariabka, Rudolf Ka...
Developing applications and games in Unity engine - Matej Jariabka, Rudolf Ka...Developing applications and games in Unity engine - Matej Jariabka, Rudolf Ka...
Developing applications and games in Unity engine - Matej Jariabka, Rudolf Ka...
 
Creating Casual Games for Windows 8
Creating Casual Games for Windows 8Creating Casual Games for Windows 8
Creating Casual Games for Windows 8
 
CoGame starter
CoGame starterCoGame starter
CoGame starter
 
MattEkinsJumpstartWork
MattEkinsJumpstartWorkMattEkinsJumpstartWork
MattEkinsJumpstartWork
 
Technical aspectof game design (Game Architecture)
Technical aspectof game design (Game Architecture)Technical aspectof game design (Game Architecture)
Technical aspectof game design (Game Architecture)
 
LearningKit.ppt
LearningKit.pptLearningKit.ppt
LearningKit.ppt
 
Augernaut js
Augernaut jsAugernaut js
Augernaut js
 
Making A Game Engine Is Easier Than You Think
Making A Game Engine Is Easier Than You ThinkMaking A Game Engine Is Easier Than You Think
Making A Game Engine Is Easier Than You Think
 
Maximize Your Production Effort (English)
Maximize Your Production Effort (English)Maximize Your Production Effort (English)
Maximize Your Production Effort (English)
 
Long Lin at AI Frontiers : AI in Gaming
Long Lin at AI Frontiers : AI in GamingLong Lin at AI Frontiers : AI in Gaming
Long Lin at AI Frontiers : AI in Gaming
 

More from Lauren Cormack

Agile Marketing For The Real World event - Signal - 6th Nov 2019
Agile Marketing For The Real World event - Signal - 6th Nov 2019Agile Marketing For The Real World event - Signal - 6th Nov 2019
Agile Marketing For The Real World event - Signal - 6th Nov 2019Lauren Cormack
 
GIAF UK Winter 2015 - Slot machines: Tweaking randomness in social casino
GIAF UK Winter 2015 - Slot machines: Tweaking randomness in social casinoGIAF UK Winter 2015 - Slot machines: Tweaking randomness in social casino
GIAF UK Winter 2015 - Slot machines: Tweaking randomness in social casinoLauren Cormack
 
GIAF UK Winter 2015 - Analytical techniques: A practical guide to answering b...
GIAF UK Winter 2015 - Analytical techniques: A practical guide to answering b...GIAF UK Winter 2015 - Analytical techniques: A practical guide to answering b...
GIAF UK Winter 2015 - Analytical techniques: A practical guide to answering b...Lauren Cormack
 
GIAF USA Winter 2015 - Measuring collaboration in a multiplayer game
GIAF USA Winter 2015 - Measuring collaboration in a multiplayer gameGIAF USA Winter 2015 - Measuring collaboration in a multiplayer game
GIAF USA Winter 2015 - Measuring collaboration in a multiplayer gameLauren Cormack
 
UK GIAF Summer 2015 - Trends in game analytics: What’s happening and why?
UK GIAF Summer 2015 - Trends in game analytics: What’s happening and why?UK GIAF Summer 2015 - Trends in game analytics: What’s happening and why?
UK GIAF Summer 2015 - Trends in game analytics: What’s happening and why?Lauren Cormack
 
Making games pay: Data secrets for monetization
Making games pay: Data secrets for monetization Making games pay: Data secrets for monetization
Making games pay: Data secrets for monetization Lauren Cormack
 

More from Lauren Cormack (6)

Agile Marketing For The Real World event - Signal - 6th Nov 2019
Agile Marketing For The Real World event - Signal - 6th Nov 2019Agile Marketing For The Real World event - Signal - 6th Nov 2019
Agile Marketing For The Real World event - Signal - 6th Nov 2019
 
GIAF UK Winter 2015 - Slot machines: Tweaking randomness in social casino
GIAF UK Winter 2015 - Slot machines: Tweaking randomness in social casinoGIAF UK Winter 2015 - Slot machines: Tweaking randomness in social casino
GIAF UK Winter 2015 - Slot machines: Tweaking randomness in social casino
 
GIAF UK Winter 2015 - Analytical techniques: A practical guide to answering b...
GIAF UK Winter 2015 - Analytical techniques: A practical guide to answering b...GIAF UK Winter 2015 - Analytical techniques: A practical guide to answering b...
GIAF UK Winter 2015 - Analytical techniques: A practical guide to answering b...
 
GIAF USA Winter 2015 - Measuring collaboration in a multiplayer game
GIAF USA Winter 2015 - Measuring collaboration in a multiplayer gameGIAF USA Winter 2015 - Measuring collaboration in a multiplayer game
GIAF USA Winter 2015 - Measuring collaboration in a multiplayer game
 
UK GIAF Summer 2015 - Trends in game analytics: What’s happening and why?
UK GIAF Summer 2015 - Trends in game analytics: What’s happening and why?UK GIAF Summer 2015 - Trends in game analytics: What’s happening and why?
UK GIAF Summer 2015 - Trends in game analytics: What’s happening and why?
 
Making games pay: Data secrets for monetization
Making games pay: Data secrets for monetization Making games pay: Data secrets for monetization
Making games pay: Data secrets for monetization
 

Recently uploaded

CebaBaby dropshipping via API with DroFX.pptx
CebaBaby dropshipping via API with DroFX.pptxCebaBaby dropshipping via API with DroFX.pptx
CebaBaby dropshipping via API with DroFX.pptxolyaivanovalion
 
Week-01-2.ppt BBB human Computer interaction
Week-01-2.ppt BBB human Computer interactionWeek-01-2.ppt BBB human Computer interaction
Week-01-2.ppt BBB human Computer interactionfulawalesam
 
Zuja dropshipping via API with DroFx.pptx
Zuja dropshipping via API with DroFx.pptxZuja dropshipping via API with DroFx.pptx
Zuja dropshipping via API with DroFx.pptxolyaivanovalion
 
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...Valters Lauzums
 
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Callshivangimorya083
 
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...amitlee9823
 
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdf
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdfMarket Analysis in the 5 Largest Economic Countries in Southeast Asia.pdf
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdfRachmat Ramadhan H
 
April 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's AnalysisApril 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's Analysismanisha194592
 
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...amitlee9823
 
Ravak dropshipping via API with DroFx.pptx
Ravak dropshipping via API with DroFx.pptxRavak dropshipping via API with DroFx.pptx
Ravak dropshipping via API with DroFx.pptxolyaivanovalion
 
Best VIP Call Girls Noida Sector 22 Call Me: 8448380779
Best VIP Call Girls Noida Sector 22 Call Me: 8448380779Best VIP Call Girls Noida Sector 22 Call Me: 8448380779
Best VIP Call Girls Noida Sector 22 Call Me: 8448380779Delhi Call girls
 
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...SUHANI PANDEY
 
Smarteg dropshipping via API with DroFx.pptx
Smarteg dropshipping via API with DroFx.pptxSmarteg dropshipping via API with DroFx.pptx
Smarteg dropshipping via API with DroFx.pptxolyaivanovalion
 
Introduction-to-Machine-Learning (1).pptx
Introduction-to-Machine-Learning (1).pptxIntroduction-to-Machine-Learning (1).pptx
Introduction-to-Machine-Learning (1).pptxfirstjob4
 
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 nightCheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 nightDelhi Call girls
 
Data-Analysis for Chicago Crime Data 2023
Data-Analysis for Chicago Crime Data  2023Data-Analysis for Chicago Crime Data  2023
Data-Analysis for Chicago Crime Data 2023ymrp368
 
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% SecureCall me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% SecurePooja Nehwal
 
Discover Why Less is More in B2B Research
Discover Why Less is More in B2B ResearchDiscover Why Less is More in B2B Research
Discover Why Less is More in B2B Researchmichael115558
 
Mature dropshipping via API with DroFx.pptx
Mature dropshipping via API with DroFx.pptxMature dropshipping via API with DroFx.pptx
Mature dropshipping via API with DroFx.pptxolyaivanovalion
 

Recently uploaded (20)

CebaBaby dropshipping via API with DroFX.pptx
CebaBaby dropshipping via API with DroFX.pptxCebaBaby dropshipping via API with DroFX.pptx
CebaBaby dropshipping via API with DroFX.pptx
 
Week-01-2.ppt BBB human Computer interaction
Week-01-2.ppt BBB human Computer interactionWeek-01-2.ppt BBB human Computer interaction
Week-01-2.ppt BBB human Computer interaction
 
Zuja dropshipping via API with DroFx.pptx
Zuja dropshipping via API with DroFx.pptxZuja dropshipping via API with DroFx.pptx
Zuja dropshipping via API with DroFx.pptx
 
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
 
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
 
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
 
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdf
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdfMarket Analysis in the 5 Largest Economic Countries in Southeast Asia.pdf
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdf
 
April 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's AnalysisApril 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's Analysis
 
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
 
Ravak dropshipping via API with DroFx.pptx
Ravak dropshipping via API with DroFx.pptxRavak dropshipping via API with DroFx.pptx
Ravak dropshipping via API with DroFx.pptx
 
Best VIP Call Girls Noida Sector 22 Call Me: 8448380779
Best VIP Call Girls Noida Sector 22 Call Me: 8448380779Best VIP Call Girls Noida Sector 22 Call Me: 8448380779
Best VIP Call Girls Noida Sector 22 Call Me: 8448380779
 
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
 
Smarteg dropshipping via API with DroFx.pptx
Smarteg dropshipping via API with DroFx.pptxSmarteg dropshipping via API with DroFx.pptx
Smarteg dropshipping via API with DroFx.pptx
 
Introduction-to-Machine-Learning (1).pptx
Introduction-to-Machine-Learning (1).pptxIntroduction-to-Machine-Learning (1).pptx
Introduction-to-Machine-Learning (1).pptx
 
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts ServiceCall Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
 
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 nightCheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
 
Data-Analysis for Chicago Crime Data 2023
Data-Analysis for Chicago Crime Data  2023Data-Analysis for Chicago Crime Data  2023
Data-Analysis for Chicago Crime Data 2023
 
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% SecureCall me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
 
Discover Why Less is More in B2B Research
Discover Why Less is More in B2B ResearchDiscover Why Less is More in B2B Research
Discover Why Less is More in B2B Research
 
Mature dropshipping via API with DroFx.pptx
Mature dropshipping via API with DroFx.pptxMature dropshipping via API with DroFx.pptx
Mature dropshipping via API with DroFx.pptx
 

Understanding and improving games through machine learning - Natasha Latysheva

  • 1.
  • 2. Understanding and improving games through machine learning Natasha Latysheva Data Scientist Jagex Games Studio
  • 3. This talk: 1. Introduction to Jagex 2. Recap of main machine learning fields + examples 3. Fun ML in video games in general 4. ML projects at Jagex Data Science • Identifying player personas • Deep learning player lifecycle sequences • Automatic bot and abuse detection • Trading card deck analysis • Quest recommender systems
  • 4. Jagex Game Studios • Video game development company based in Cambridge • Best known for Runescape, the world's largest free-to-play massively multiplayer online role-playing game (MMORPG). First released in 2001! • Extremely community oriented game • Old School Runescape was released in 2013
  • 8.
  • 9.
  • 10.
  • 11.
  • 13. Machine learning recap Essentially learning patterns from data. Branches of ML: • 1. Supervised learning. • Most familiar names, e.g. linear regression, logistic regression, decision trees, random forests, SVMs, many neural nets. • Algorithm is presented with input data and explicit labels on that input. Learn signals associating input data with labels. • Everything from good ole iris classification to detecting diseased patients from complex medical images.
  • 14. Machine learning recap 2. Unsupervised learning. • No explicitly labelled data, instead often seeking to find natural sub-groups of similar data points within the data. • Describing the structure of the dataset. • Objective evaluation of accuracy often difficult/not possible • Common methods: • Clustering methods like k-means and hierarchical clustering • Dimensionality reduction methods like principal components analysis • Outlier/anomaly detection • Some NNs, e.g. generative adversarial networks (GANs) Larsen et al. 2016
  • 15. Machine learning recap 3. Reinforcement learning. • Agent must maximise cumulative reward by learning to optimally interact with an environment by choosing ‘good’ actions • E.g. robot must come up with correct limb positions and joint torque to move efficiently/quickly • Manufacturing program must maximise total units of product produced each day by controlling/tuning sub-processes • Video game player agent must process the information from pixels on the screen to operate virtual keyboard + mouse to choose when to turn, apply brakes, gas, etc. DuskDrive (OpenAI Universe, 2016) Houthooft et al. 2017
  • 16. Fun machine learning in video games examples
  • 17. 1. DeepMind • Classic Atari games • Learning from raw pixel feeds to maximise future cumulative reward (i.e. score), no previous information encoded • Ability to generalise skill playing across games • In some cases, outperforming human players • Deep Q-network approach • Combining deep learning of the value function Q(s, a) with RL + experience replay • Deep NN is Q(s, a) approximator, trained with Bellman updates Compulsory DeepMind demo: https://www.youtube.com/watch?v=V1eYniJ0Rnk Mnih et al., 2015
  • 18. DeepMind handling quite complex games
  • 19. DeepMind handling quite complex games
  • 20. • 2. Hitman: NPC locomotion learning with RL
  • 21. • 3. Hearthstone (collectible card game)
  • 22. • 3. Hearthstone (collectible card game) Bursztein, 2014 5. Predicting outcome: Domain experts (like casters) generate metrics (per turn + cumulative) that seem important to winning a game: • Mana advantage (delta mana spent in turn) • Board advantage (delta # minions) • Hand size advantage • Board mana advantage (delta total mana spent), etc. • No info on hero class or health
  • 23. • 4. Candy Crush (King)
  • 24. Recent and upcoming ML projects at Jagex
  • 26. . Identifying player personas • Understand different archetypes of players in Runescape • Ultimately we would like to have a better sense of our customer base • Helps games devs • Helps us understand the motivations, churn behaviours, and value of our customers
  • 27. . Identifying player personas • Draw inspiration from Bartel types • Generated ~280 features to quantify our player behaviour • Loosely based on Bartle Types (Killers, Achievers, Socializers, Explorers) • Quickly abandoned • Example behavioural features • Chat Rank Score • Skill Heterogeneity • Forum Interactions • Economic Activity • Social Clustering Coefficients • Abilities Used During Play
  • 28. . Identifying player personas • Data cleaning: • Normalising by total and that year play time, logging certain variables • Dimensionality reduction using principal components analysis • Identifying optimal number of clusters using silhouette plots or tSNE Then… doing the clustering in PC space!
  • 29. Life stages • Differences in playtime both overall and recently are such a strong differentiating factor between players that you first need to cluster on life cycle stages
  • 30. Life stages Name % Median Lifetime Playtime Median Yearly Playtime Little Activity Short Lifetime Playtime 30.7% 3h 3h Little Activity Long Lifetime Playtime 22.1% 590h 4h Active Mid Lifetime Playtime 22.2% 75h 35h Extremely Active Extreme Lifetime Playtime 25% 2130h 320h • The extremely dedicated players make up a huge proportion of total revenue.
  • 31. Playstyles interacting with lifecycle stages • Can observe which play styles emerge or dominate at which lifecycle stages • Can characterise transitions between the different personas in consecutive years • Importantly: Quantify which types of players tend to abandon the game
  • 32. 2. Deep learning player lifecycle sequences
  • 33. Player lifecycle sequences Matt Project • Players can undergo a variety of business relevant lifecycle transitions.
  • 34. Player lifecycle sequences Matt Project • Number of possible combinations, complexity of transitions, scale of data, etc. leads to a difficult modelling problem • Goal: We want to learn more about the player base and how their lifecycle stages change. • Two approaches: • 1. Building transition probability matrices to examine trends and project player states forward into the future
  • 35. Matt Project • Transition matrix approach does a surprisingly good job.
  • 36. Deep learning player lifecycle sequences Matt Project • 2. Building a recurrent neural network (specifically, an LSTM RNN) to learn the types of transitions that happen and project these forward into the future • Inherent memory to the system. • But - difficult and time-consuming to train! GPUs help. • On the plus side, can generate sequences seeded with multiple states. Also, in theory can learn quite complex patterns. • Models operational but need to tune hyperparameters and compare performance to transition matrices. [Colah’s blog]
  • 37. 3. Sentiment, bot and abuse detection work Matt Project
  • 38. Sentiment, bot and abuse detection work Matt Project • At the moment we: • Help community team understand the popularity of updates using sentiment detection • Very simple model – Naïve Bayes classifier run over in-game chat to identify emotional valence • Detect instances of harassment • Search through text with preset list of regular expressions • Try to learn more complex language models • Using word2vec to identify words with similar semantic meanings, identify harassment using learned vector embeddings Matt Project [Saed Sayad]
  • 39. In progress… Training deep convolutional neural nets to identify bot-like mouse movements [Adit Deshpande] Common CNN architecture [Also working to automate bot removal in other ways]
  • 40. . 4. Trading card deck analysis • Play a sequence of cards in a sequence to create a quest for your legend • Many cards have additional effects that buff your character, provide weapons, alter creature power, or grief / damage your opponent • Games span 5 chapters where each player places up to 4 cards per chapter • The gameplay is combo-oriented where card play sequence is very important Miro Project
  • 41. . Build card vectors with word2vec • Learn card vectors using Word2Vec algorithm: • Given a card vector, predict the remaining cards that were played by the player in that chapter. This worked surprisingly well! • Cards with similar effects clustered together • Legend specific cards clustered together • Common cards that combo well with Legend specific cards are located in a region of space close to the Legend Miro Project
  • 42. . Build deck vectors with word2vec • Tweak Word2Vec algorithm (more akin to Paragraph2Vec) to learn vector representation for custom decks • Deck vectors naturally learned archetype clusters without being explicitly taught • Decks from different legends that play by similar strategies tend to cluster in the same region of space • Deck vectors can be used down-stream in other ML tasks • Matchmaking • assessing deck quality • recommending cards • predicting churn Miro Project
  • 43. • Card and deck vectors userful for game devs for exploring the space of decks real players use • Interactive web application for exploring decks by hovering over decks, filtering by cards, player rank, and win rate • Built clustering tool on top of deck vectors to allow devs to quickly identify common cards within a region of ‘deck space’ • View summary statistics on the clusters (win rates, play rates, cluster sizes) • This is used to identify balance issues in game, identify how players are playing decks, and categorize player play-styles Miro Project Chronicle project conclusions
  • 45. • Ultimate goal: help guide players towards appropriate and interest-relevant content • Starting point: recommend appropriate quests to players. • Modelling using 2 approaches: • 1. Restricted Boltzmann Machine (RBM) trained on past quest data • 2. Matrix factorisation on past quest data with a REST API built to interface with game Miro Project Quest recommender system Matt and Miro Project [deeplearning4j]
  • 46. Acknowledgements • Data Science Team! • Miroslaw Horbal • Matt Dixon • Babis Georgiadis • Katie Scott • Joel Graham • Ilian Mitev • Analytics Team 