SlideShare a Scribd company logo
Now Looking
for Players…
By: Margery (Midge) Hines
Now Looking
for Players…
By: Margery (Midge) Hines
Now Looking
for Players…
By: Margery (Midge) Hines
Now Looking
for Players…
By: Margery (Midge) Hines
Measuring Similarity𝑢𝑠𝑒𝑟𝑠
𝑔𝑎𝑚𝑒𝑠
𝑢1 𝑢2 𝑢3 𝑢4 …
𝑢1
𝑢2
𝑢3
𝑢4
⋮
1
𝑚32
𝑚42
𝑚12
𝑚21
𝑚41
1
1
𝑚23
1
𝑚31
𝑚13 𝑚14
𝑚42 𝑚43
𝑚34
mij = 𝑤𝑃𝑖𝑗 + 1 − w 𝑅𝑖𝑗
Rank 𝑚𝑖𝑗 to find top
user matches!
𝑝𝑖𝑗 = 𝑁𝑜𝑟𝑚𝑎𝑙𝑖𝑧𝑒𝑑 𝑃𝑙𝑎𝑦𝑡𝑖𝑚𝑒
𝑟𝑖𝑗 = 𝑁𝑜𝑟𝑚𝑎𝑙𝑖𝑧𝑒𝑑 𝑅𝑒𝑐𝑒𝑛𝑡 𝑃𝑙𝑎𝑦𝑡𝑖𝑚𝑒
𝑢1 𝑢2 𝑢3 𝑢4 …
𝑔1
𝑔2
𝑔3
𝑔4
⋮
𝑝11
𝑝32
𝑝42
𝑝12
𝑝21
𝑝41
?
?
?
?
?
?
?
?
𝑝23
𝑝42
𝑢1 𝑢2 𝑢3 𝑢4 …
𝑔1
𝑔2
𝑔3
𝑔4
⋮
𝑟11
𝑟32
𝑟42
𝑟12
𝑟21
𝑟41
?
?
?
?
?
?
?
?
𝑟23
𝑟42
Pij =
𝑢𝑖 𝑢𝑗
𝑢𝑖 𝑢𝑗
Compute Cosine
Similarity
Rij =
𝑢𝑖 𝑢𝑗
𝑢𝑖 𝑢𝑗
Compute Cosine
Similarity
Validation
User Similarity
Distribution Profile Types
Obscure Gamers
AAA Gamers
Broad Gamers
Validation
User Similarity
Distribution Profile Types
Obscure Gamers
AAA Gamers
Broad Gamers
Validation
User Similarity
Distribution Profile Types
Obscure Gamers
AAA Gamers
Broad Gamers
Margery (Midge) Hines
PhD Electrical Engineering from Northeastern University
Dissertation: Autonomous landmine detection using GPR for humanitarian demining
Extra Slides
Improved Matching System: User Playtime Scores
• Score each user’s game by relative playtime compared to the set of people who own that game using deciles
𝑝𝑖𝑗 = 𝑃𝑙𝑎𝑦𝑡𝑖𝑚𝑒 𝑆𝑐𝑜𝑟𝑒 (𝑠𝑐𝑎𝑙𝑒 1 𝑡𝑜 10)
𝑟𝑖𝑗 = 𝑅𝑒𝑐𝑒𝑛𝑡 𝑃𝑙𝑎𝑦𝑡𝑖𝑚𝑒 𝑆𝑐𝑜𝑟𝑒 (𝑠𝑐𝑎𝑙𝑒 1 𝑡𝑜 10)
𝑝𝑖𝑗 = 𝑁𝑜𝑟𝑚𝑎𝑙𝑖𝑧𝑒𝑑 𝑃𝑙𝑎𝑦𝑡𝑖𝑚𝑒
𝑟𝑖𝑗 = 𝑁𝑜𝑟𝑚𝑎𝑙𝑖𝑧𝑒𝑑 𝑅𝑒𝑐𝑒𝑛𝑡 𝑃𝑙𝑎𝑦𝑡𝑖𝑚𝑒
Improved Matching System: Results
• On average all similarity scores are lower
• Random Pairing < Friend Pairing < Algorithm Pairing
Similarity Matrix
Future Improvements
Additional User Matching Features
• Number and/or type of steam achievements for each game
• Match based on features using SVD after filtering database for specific game of choice
• Before matching filter by location (low ping, time-zones)
Site Enhancement
• Include video game recommendations
• Add Steam open-id support
Play
Style
Skill
Level
Similarity Metric Visualization
𝑢𝑠𝑒𝑟𝑠
𝐴) 𝑂𝑟𝑖𝑔𝑖𝑛𝑎𝑙 𝑆𝑖𝑚𝑖𝑙𝑎𝑟𝑖𝑡𝑦 𝑀𝑎𝑡𝑟𝑖𝑥 𝐵) 𝐴 𝑤𝑖𝑡ℎ 𝑆𝑜𝑟𝑡𝑒𝑑 𝑅𝑜𝑤𝑠 𝐶) 𝐵 𝑤𝑖𝑡ℎ 𝑅𝑜𝑤𝑠 𝑅𝑎𝑛𝑘𝑒𝑑
𝑆𝑜𝑟𝑡𝑒𝑑 𝑏𝑦 𝐴𝑣𝑔. 𝑆𝑐𝑜𝑟𝑒
0 1
Note: The strong similarity in the diagonal of A and first column of B and C is due to users match with themselves
Alternative Method for Feature Matching: SVD
𝑢1 𝑢2 𝑢3 𝑢4 …
𝑔1
𝑔2
𝑔3
𝑔4
⋮
𝑠11
𝑠32
𝑠42
𝑠12
𝑠21
𝑠41
?
?
?
?
?
?
?
?
𝑠23
𝑠42
𝑓1 𝑓2 …
𝑢1
𝑢2
𝑢3
𝑢4
⋮
𝑢11
𝑢32
𝑢12
𝑢21
𝑢41
𝑢31
𝑢22
𝑢42
𝑢13
𝑢33
𝑢43
𝑢23
𝑓1 𝑓2 …
𝑓1
𝑓2
⋮
𝑤11
0
0
0
0
0
0
𝑔1 𝑔2 𝑔3 …
𝑓1
𝑓2
⋮
𝑔11
𝑔32
𝑔12
𝑔21
𝑔31
𝑔22
𝑔13
𝑔33
𝑔23
𝑢1 𝑢2 𝑢3 𝑢4 …
𝑢1
𝑢2
𝑢3
𝑢4
⋮
1
𝑚32
𝑚42
𝑚12
𝑚21
𝑚41
1
1
𝑚23
1
𝑚31
𝑚13 𝑚14
𝑚42 𝑚43
𝑚34
𝑤22
𝑤33
Validation
So why not SVD?
• Feature matching doesn’t guarantee that matched users will own or play the same games
User’s Game Preference
Distribution of User’s Maximum Game Preferences
Some users spend
all playtime on
Steam on Dota 2
Few users spend all
playtime on Steam
on Portal
User 1: Looking For Players
Best Match:
70% Compatibility 69% Compatibility
Suggestion: You might enjoy Borderlands !
Worst Match:
0.01% Compatibility
Actual Friend of User 1!
Example Comparison of User Match Result
Video Game Recommendations
Steam’s Current Game Recommendations: Personal Experience
Games Steam
Recommends Me
My Playtime by Title
Users’ Playtime for
“Tiny and Big: Grandpa’s Leftovers”
• Compared to my
other games, my
playtime of this
game seems
small
• Compared to
other people
who own this
game my
playtime is small
(lowest decile)
Implying User Scores Based on Playtime
• Score each user’s game by relative playtime compared to the set of people who own that game using deciles
Game Recommendations Using SVD
𝑢1 𝑢2 𝑢3 𝑢4 …
𝑔1
𝑔2
𝑔3
𝑔4
⋮
𝑠11
𝑠32
𝑠42
𝑠12
𝑠21
𝑠41
?
?
?
?
?
?
?
?
𝑠23
𝑠42
Compute SVD
𝑓1 𝑓2 …
𝑢1
𝑢2
𝑢3
𝑢4
⋮
𝑢11
𝑢32
𝑢12
𝑢21
𝑢41
𝑢31
𝑢22
𝑢42
𝑢13
𝑢33
𝑢43
𝑢23
𝑔1 𝑔2 𝑔3 …
𝑓1
𝑓2
⋮
𝑔11
𝑔32
𝑔12
𝑔21
𝑔31
𝑔22
𝑔13
𝑔33
𝑔23
𝑓1 𝑓2 …
𝑓1
𝑓2
⋮
𝑤11
0
0
0
0
0
0𝑤22
𝑤33
Train SVD with 80% of Data
Test SVD with 20% of Data
𝑢1 𝑢2 𝑢3 …
𝑔1
𝑔2
⋮
𝑠11 𝑠12
𝑠21 ?
?
𝑠23
Predict SVD
𝑢1 𝑢2 𝑢3 …
𝑔1
𝑔2
⋮
𝑠11 𝑠12
𝑠21 ?
?
𝑠23 Calculate RMSE
RMSE = 2.7
NRMSE = 0.31
Netflix’s NRMSE = 0.21
𝑅𝑀𝑆𝐸 =
1
𝑛 𝑖𝑗
𝑠𝑖𝑗 − 𝑠𝑖𝑗
2
More Exploratory Analysis!
Independent Game Development is on the Rise!
Only 31% of Steam games are rated on Metacritic
124 games have been purchased but never been played!
Not all games are played; Not all games are rated
Strictly Single Player
Multiplayer
The playtime on only 6 games is equal to the
total playtime on all others
Multiplayer games tend to have greater
playtime than strictly single-player games
Steam Games by Genre
• MMOs account for
few games on
Steam, but have
high playtime per
title
• Over half of Steam’s
game are Indie, but
Indie games have
very little playtime
per title
Steam Games by Genre
• Sports games have
the highest average
cost, and MMOs
have the lowest
(note subscriptions
not included)
• MMOs and Action
games have the best
“bang-for-the-buck”
in terms of hours of
playtime/dollar

More Related Content

Similar to Looking For Steam Players - Insight Project

Knowing When to Hold 'Em, When to Fold 'Em and When to Blow 'Em Up
Knowing When to Hold 'Em, When to Fold 'Em and When to Blow 'Em UpKnowing When to Hold 'Em, When to Fold 'Em and When to Blow 'Em Up
Knowing When to Hold 'Em, When to Fold 'Em and When to Blow 'Em Up
Luke Dicken
 
[Pandora 22] Boosting Game Design with Analytics - Nikola Vasiljevic
[Pandora 22] Boosting Game Design with Analytics - Nikola Vasiljevic[Pandora 22] Boosting Game Design with Analytics - Nikola Vasiljevic
[Pandora 22] Boosting Game Design with Analytics - Nikola Vasiljevic
DataScienceConferenc1
 
HOW TO CREATE A GAME DESIGN?
HOW TO CREATE A GAME DESIGN?HOW TO CREATE A GAME DESIGN?
HOW TO CREATE A GAME DESIGN?
Eva Handriyantini
 
IndieRecommender Demo
IndieRecommender DemoIndieRecommender Demo
IndieRecommender Demo
rmredd
 
Which Console will take over
Which Console will take overWhich Console will take over
Which Console will take over
Fred Sosa
 
Recommender system
Recommender systemRecommender system
Recommender system
Yinghan Fu
 
Localisation sentiment analysis - best practices and challenges
Localisation sentiment analysis - best practices and challengesLocalisation sentiment analysis - best practices and challenges
Localisation sentiment analysis - best practices and challenges
Allcorrect Group
 
My console
My consoleMy console
My console
BenWhite101
 
How Healthy is Your Metagame? Testing Metagame Bounds on Products With Comple...
How Healthy is Your Metagame? Testing Metagame Bounds on Products With Comple...How Healthy is Your Metagame? Testing Metagame Bounds on Products With Comple...
How Healthy is Your Metagame? Testing Metagame Bounds on Products With Comple...
Jessica Tams
 
Adaptive First Person Shooter Game Content Generation
Adaptive First Person Shooter Game Content GenerationAdaptive First Person Shooter Game Content Generation
Adaptive First Person Shooter Game Content Generation
Mohammad Shaker
 
Engaging Twitch Streamers, Viewers, and Players with Metastream - TwitchCon D...
Engaging Twitch Streamers, Viewers, and Players with Metastream - TwitchCon D...Engaging Twitch Streamers, Viewers, and Players with Metastream - TwitchCon D...
Engaging Twitch Streamers, Viewers, and Players with Metastream - TwitchCon D...
Twitch Developers
 
Decision tree upload
Decision tree uploadDecision tree upload
Decision tree upload
nithum
 
Forecasting Online Game Addictiveness
Forecasting Online Game AddictivenessForecasting Online Game Addictiveness
Forecasting Online Game Addictiveness
Academia Sinica
 
Serious Games Presentation Web
Serious Games Presentation WebSerious Games Presentation Web
Serious Games Presentation Web
iil07
 
Game Analytics & Machine Learning
Game Analytics & Machine LearningGame Analytics & Machine Learning
Game Analytics & Machine Learning
Ben Weber
 
Nature of Games.pptx
Nature of Games.pptxNature of Games.pptx
Nature of Games.pptx
UgurKaplancali
 
Showcase of My Research on Games & AI "till the end of Oct. 2014"
Showcase of My Research on Games & AI "till the end of Oct. 2014"Showcase of My Research on Games & AI "till the end of Oct. 2014"
Showcase of My Research on Games & AI "till the end of Oct. 2014"
Mohammad Shaker
 
[系列活動] 資料探勘速遊 - Session4 case-studies
[系列活動] 資料探勘速遊 - Session4 case-studies[系列活動] 資料探勘速遊 - Session4 case-studies
[系列活動] 資料探勘速遊 - Session4 case-studies
台灣資料科學年會
 
What We Talk About When We Talk About Social
What We Talk About When We Talk About SocialWhat We Talk About When We Talk About Social
What We Talk About When We Talk About Social
Adam Gutterman
 
My console
My consoleMy console
My console
BenWhite101
 

Similar to Looking For Steam Players - Insight Project (20)

Knowing When to Hold 'Em, When to Fold 'Em and When to Blow 'Em Up
Knowing When to Hold 'Em, When to Fold 'Em and When to Blow 'Em UpKnowing When to Hold 'Em, When to Fold 'Em and When to Blow 'Em Up
Knowing When to Hold 'Em, When to Fold 'Em and When to Blow 'Em Up
 
[Pandora 22] Boosting Game Design with Analytics - Nikola Vasiljevic
[Pandora 22] Boosting Game Design with Analytics - Nikola Vasiljevic[Pandora 22] Boosting Game Design with Analytics - Nikola Vasiljevic
[Pandora 22] Boosting Game Design with Analytics - Nikola Vasiljevic
 
HOW TO CREATE A GAME DESIGN?
HOW TO CREATE A GAME DESIGN?HOW TO CREATE A GAME DESIGN?
HOW TO CREATE A GAME DESIGN?
 
IndieRecommender Demo
IndieRecommender DemoIndieRecommender Demo
IndieRecommender Demo
 
Which Console will take over
Which Console will take overWhich Console will take over
Which Console will take over
 
Recommender system
Recommender systemRecommender system
Recommender system
 
Localisation sentiment analysis - best practices and challenges
Localisation sentiment analysis - best practices and challengesLocalisation sentiment analysis - best practices and challenges
Localisation sentiment analysis - best practices and challenges
 
My console
My consoleMy console
My console
 
How Healthy is Your Metagame? Testing Metagame Bounds on Products With Comple...
How Healthy is Your Metagame? Testing Metagame Bounds on Products With Comple...How Healthy is Your Metagame? Testing Metagame Bounds on Products With Comple...
How Healthy is Your Metagame? Testing Metagame Bounds on Products With Comple...
 
Adaptive First Person Shooter Game Content Generation
Adaptive First Person Shooter Game Content GenerationAdaptive First Person Shooter Game Content Generation
Adaptive First Person Shooter Game Content Generation
 
Engaging Twitch Streamers, Viewers, and Players with Metastream - TwitchCon D...
Engaging Twitch Streamers, Viewers, and Players with Metastream - TwitchCon D...Engaging Twitch Streamers, Viewers, and Players with Metastream - TwitchCon D...
Engaging Twitch Streamers, Viewers, and Players with Metastream - TwitchCon D...
 
Decision tree upload
Decision tree uploadDecision tree upload
Decision tree upload
 
Forecasting Online Game Addictiveness
Forecasting Online Game AddictivenessForecasting Online Game Addictiveness
Forecasting Online Game Addictiveness
 
Serious Games Presentation Web
Serious Games Presentation WebSerious Games Presentation Web
Serious Games Presentation Web
 
Game Analytics & Machine Learning
Game Analytics & Machine LearningGame Analytics & Machine Learning
Game Analytics & Machine Learning
 
Nature of Games.pptx
Nature of Games.pptxNature of Games.pptx
Nature of Games.pptx
 
Showcase of My Research on Games & AI "till the end of Oct. 2014"
Showcase of My Research on Games & AI "till the end of Oct. 2014"Showcase of My Research on Games & AI "till the end of Oct. 2014"
Showcase of My Research on Games & AI "till the end of Oct. 2014"
 
[系列活動] 資料探勘速遊 - Session4 case-studies
[系列活動] 資料探勘速遊 - Session4 case-studies[系列活動] 資料探勘速遊 - Session4 case-studies
[系列活動] 資料探勘速遊 - Session4 case-studies
 
What We Talk About When We Talk About Social
What We Talk About When We Talk About SocialWhat We Talk About When We Talk About Social
What We Talk About When We Talk About Social
 
My console
My consoleMy console
My console
 

Recently uploaded

Global Situational Awareness of A.I. and where its headed
Global Situational Awareness of A.I. and where its headedGlobal Situational Awareness of A.I. and where its headed
Global Situational Awareness of A.I. and where its headed
vikram sood
 
一比一原版(Coventry毕业证书)考文垂大学毕业证如何办理
一比一原版(Coventry毕业证书)考文垂大学毕业证如何办理一比一原版(Coventry毕业证书)考文垂大学毕业证如何办理
一比一原版(Coventry毕业证书)考文垂大学毕业证如何办理
74nqk8xf
 
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
nuttdpt
 
一比一原版(Dalhousie毕业证书)达尔豪斯大学毕业证如何办理
一比一原版(Dalhousie毕业证书)达尔豪斯大学毕业证如何办理一比一原版(Dalhousie毕业证书)达尔豪斯大学毕业证如何办理
一比一原版(Dalhousie毕业证书)达尔豪斯大学毕业证如何办理
mzpolocfi
 
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
bopyb
 
Intelligence supported media monitoring in veterinary medicine
Intelligence supported media monitoring in veterinary medicineIntelligence supported media monitoring in veterinary medicine
Intelligence supported media monitoring in veterinary medicine
AndrzejJarynowski
 
End-to-end pipeline agility - Berlin Buzzwords 2024
End-to-end pipeline agility - Berlin Buzzwords 2024End-to-end pipeline agility - Berlin Buzzwords 2024
End-to-end pipeline agility - Berlin Buzzwords 2024
Lars Albertsson
 
Learn SQL from basic queries to Advance queries
Learn SQL from basic queries to Advance queriesLearn SQL from basic queries to Advance queries
Learn SQL from basic queries to Advance queries
manishkhaire30
 
Influence of Marketing Strategy and Market Competition on Business Plan
Influence of Marketing Strategy and Market Competition on Business PlanInfluence of Marketing Strategy and Market Competition on Business Plan
Influence of Marketing Strategy and Market Competition on Business Plan
jerlynmaetalle
 
一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理
一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理
一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理
74nqk8xf
 
原版制作(swinburne毕业证书)斯威本科技大学毕业证毕业完成信一模一样
原版制作(swinburne毕业证书)斯威本科技大学毕业证毕业完成信一模一样原版制作(swinburne毕业证书)斯威本科技大学毕业证毕业完成信一模一样
原版制作(swinburne毕业证书)斯威本科技大学毕业证毕业完成信一模一样
u86oixdj
 
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
nuttdpt
 
一比一原版(Chester毕业证书)切斯特大学毕业证如何办理
一比一原版(Chester毕业证书)切斯特大学毕业证如何办理一比一原版(Chester毕业证书)切斯特大学毕业证如何办理
一比一原版(Chester毕业证书)切斯特大学毕业证如何办理
74nqk8xf
 
My burning issue is homelessness K.C.M.O.
My burning issue is homelessness K.C.M.O.My burning issue is homelessness K.C.M.O.
My burning issue is homelessness K.C.M.O.
rwarrenll
 
一比一原版(UO毕业证)渥太华大学毕业证如何办理
一比一原版(UO毕业证)渥太华大学毕业证如何办理一比一原版(UO毕业证)渥太华大学毕业证如何办理
一比一原版(UO毕业证)渥太华大学毕业证如何办理
aqzctr7x
 
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
Timothy Spann
 
Analysis insight about a Flyball dog competition team's performance
Analysis insight about a Flyball dog competition team's performanceAnalysis insight about a Flyball dog competition team's performance
Analysis insight about a Flyball dog competition team's performance
roli9797
 
Population Growth in Bataan: The effects of population growth around rural pl...
Population Growth in Bataan: The effects of population growth around rural pl...Population Growth in Bataan: The effects of population growth around rural pl...
Population Growth in Bataan: The effects of population growth around rural pl...
Bill641377
 
Predictably Improve Your B2B Tech Company's Performance by Leveraging Data
Predictably Improve Your B2B Tech Company's Performance by Leveraging DataPredictably Improve Your B2B Tech Company's Performance by Leveraging Data
Predictably Improve Your B2B Tech Company's Performance by Leveraging Data
Kiwi Creative
 
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
g4dpvqap0
 

Recently uploaded (20)

Global Situational Awareness of A.I. and where its headed
Global Situational Awareness of A.I. and where its headedGlobal Situational Awareness of A.I. and where its headed
Global Situational Awareness of A.I. and where its headed
 
一比一原版(Coventry毕业证书)考文垂大学毕业证如何办理
一比一原版(Coventry毕业证书)考文垂大学毕业证如何办理一比一原版(Coventry毕业证书)考文垂大学毕业证如何办理
一比一原版(Coventry毕业证书)考文垂大学毕业证如何办理
 
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
 
一比一原版(Dalhousie毕业证书)达尔豪斯大学毕业证如何办理
一比一原版(Dalhousie毕业证书)达尔豪斯大学毕业证如何办理一比一原版(Dalhousie毕业证书)达尔豪斯大学毕业证如何办理
一比一原版(Dalhousie毕业证书)达尔豪斯大学毕业证如何办理
 
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
 
Intelligence supported media monitoring in veterinary medicine
Intelligence supported media monitoring in veterinary medicineIntelligence supported media monitoring in veterinary medicine
Intelligence supported media monitoring in veterinary medicine
 
End-to-end pipeline agility - Berlin Buzzwords 2024
End-to-end pipeline agility - Berlin Buzzwords 2024End-to-end pipeline agility - Berlin Buzzwords 2024
End-to-end pipeline agility - Berlin Buzzwords 2024
 
Learn SQL from basic queries to Advance queries
Learn SQL from basic queries to Advance queriesLearn SQL from basic queries to Advance queries
Learn SQL from basic queries to Advance queries
 
Influence of Marketing Strategy and Market Competition on Business Plan
Influence of Marketing Strategy and Market Competition on Business PlanInfluence of Marketing Strategy and Market Competition on Business Plan
Influence of Marketing Strategy and Market Competition on Business Plan
 
一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理
一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理
一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理
 
原版制作(swinburne毕业证书)斯威本科技大学毕业证毕业完成信一模一样
原版制作(swinburne毕业证书)斯威本科技大学毕业证毕业完成信一模一样原版制作(swinburne毕业证书)斯威本科技大学毕业证毕业完成信一模一样
原版制作(swinburne毕业证书)斯威本科技大学毕业证毕业完成信一模一样
 
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
 
一比一原版(Chester毕业证书)切斯特大学毕业证如何办理
一比一原版(Chester毕业证书)切斯特大学毕业证如何办理一比一原版(Chester毕业证书)切斯特大学毕业证如何办理
一比一原版(Chester毕业证书)切斯特大学毕业证如何办理
 
My burning issue is homelessness K.C.M.O.
My burning issue is homelessness K.C.M.O.My burning issue is homelessness K.C.M.O.
My burning issue is homelessness K.C.M.O.
 
一比一原版(UO毕业证)渥太华大学毕业证如何办理
一比一原版(UO毕业证)渥太华大学毕业证如何办理一比一原版(UO毕业证)渥太华大学毕业证如何办理
一比一原版(UO毕业证)渥太华大学毕业证如何办理
 
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
 
Analysis insight about a Flyball dog competition team's performance
Analysis insight about a Flyball dog competition team's performanceAnalysis insight about a Flyball dog competition team's performance
Analysis insight about a Flyball dog competition team's performance
 
Population Growth in Bataan: The effects of population growth around rural pl...
Population Growth in Bataan: The effects of population growth around rural pl...Population Growth in Bataan: The effects of population growth around rural pl...
Population Growth in Bataan: The effects of population growth around rural pl...
 
Predictably Improve Your B2B Tech Company's Performance by Leveraging Data
Predictably Improve Your B2B Tech Company's Performance by Leveraging DataPredictably Improve Your B2B Tech Company's Performance by Leveraging Data
Predictably Improve Your B2B Tech Company's Performance by Leveraging Data
 
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
 

Looking For Steam Players - Insight Project

  • 1. Now Looking for Players… By: Margery (Midge) Hines
  • 2. Now Looking for Players… By: Margery (Midge) Hines
  • 3. Now Looking for Players… By: Margery (Midge) Hines
  • 4. Now Looking for Players… By: Margery (Midge) Hines
  • 5.
  • 6.
  • 7.
  • 8.
  • 9. Measuring Similarity𝑢𝑠𝑒𝑟𝑠 𝑔𝑎𝑚𝑒𝑠 𝑢1 𝑢2 𝑢3 𝑢4 … 𝑢1 𝑢2 𝑢3 𝑢4 ⋮ 1 𝑚32 𝑚42 𝑚12 𝑚21 𝑚41 1 1 𝑚23 1 𝑚31 𝑚13 𝑚14 𝑚42 𝑚43 𝑚34 mij = 𝑤𝑃𝑖𝑗 + 1 − w 𝑅𝑖𝑗 Rank 𝑚𝑖𝑗 to find top user matches! 𝑝𝑖𝑗 = 𝑁𝑜𝑟𝑚𝑎𝑙𝑖𝑧𝑒𝑑 𝑃𝑙𝑎𝑦𝑡𝑖𝑚𝑒 𝑟𝑖𝑗 = 𝑁𝑜𝑟𝑚𝑎𝑙𝑖𝑧𝑒𝑑 𝑅𝑒𝑐𝑒𝑛𝑡 𝑃𝑙𝑎𝑦𝑡𝑖𝑚𝑒 𝑢1 𝑢2 𝑢3 𝑢4 … 𝑔1 𝑔2 𝑔3 𝑔4 ⋮ 𝑝11 𝑝32 𝑝42 𝑝12 𝑝21 𝑝41 ? ? ? ? ? ? ? ? 𝑝23 𝑝42 𝑢1 𝑢2 𝑢3 𝑢4 … 𝑔1 𝑔2 𝑔3 𝑔4 ⋮ 𝑟11 𝑟32 𝑟42 𝑟12 𝑟21 𝑟41 ? ? ? ? ? ? ? ? 𝑟23 𝑟42 Pij = 𝑢𝑖 𝑢𝑗 𝑢𝑖 𝑢𝑗 Compute Cosine Similarity Rij = 𝑢𝑖 𝑢𝑗 𝑢𝑖 𝑢𝑗 Compute Cosine Similarity
  • 10. Validation User Similarity Distribution Profile Types Obscure Gamers AAA Gamers Broad Gamers
  • 11. Validation User Similarity Distribution Profile Types Obscure Gamers AAA Gamers Broad Gamers
  • 12. Validation User Similarity Distribution Profile Types Obscure Gamers AAA Gamers Broad Gamers
  • 13. Margery (Midge) Hines PhD Electrical Engineering from Northeastern University Dissertation: Autonomous landmine detection using GPR for humanitarian demining
  • 15. Improved Matching System: User Playtime Scores • Score each user’s game by relative playtime compared to the set of people who own that game using deciles 𝑝𝑖𝑗 = 𝑃𝑙𝑎𝑦𝑡𝑖𝑚𝑒 𝑆𝑐𝑜𝑟𝑒 (𝑠𝑐𝑎𝑙𝑒 1 𝑡𝑜 10) 𝑟𝑖𝑗 = 𝑅𝑒𝑐𝑒𝑛𝑡 𝑃𝑙𝑎𝑦𝑡𝑖𝑚𝑒 𝑆𝑐𝑜𝑟𝑒 (𝑠𝑐𝑎𝑙𝑒 1 𝑡𝑜 10) 𝑝𝑖𝑗 = 𝑁𝑜𝑟𝑚𝑎𝑙𝑖𝑧𝑒𝑑 𝑃𝑙𝑎𝑦𝑡𝑖𝑚𝑒 𝑟𝑖𝑗 = 𝑁𝑜𝑟𝑚𝑎𝑙𝑖𝑧𝑒𝑑 𝑅𝑒𝑐𝑒𝑛𝑡 𝑃𝑙𝑎𝑦𝑡𝑖𝑚𝑒
  • 16. Improved Matching System: Results • On average all similarity scores are lower • Random Pairing < Friend Pairing < Algorithm Pairing Similarity Matrix
  • 17. Future Improvements Additional User Matching Features • Number and/or type of steam achievements for each game • Match based on features using SVD after filtering database for specific game of choice • Before matching filter by location (low ping, time-zones) Site Enhancement • Include video game recommendations • Add Steam open-id support Play Style Skill Level
  • 18. Similarity Metric Visualization 𝑢𝑠𝑒𝑟𝑠 𝐴) 𝑂𝑟𝑖𝑔𝑖𝑛𝑎𝑙 𝑆𝑖𝑚𝑖𝑙𝑎𝑟𝑖𝑡𝑦 𝑀𝑎𝑡𝑟𝑖𝑥 𝐵) 𝐴 𝑤𝑖𝑡ℎ 𝑆𝑜𝑟𝑡𝑒𝑑 𝑅𝑜𝑤𝑠 𝐶) 𝐵 𝑤𝑖𝑡ℎ 𝑅𝑜𝑤𝑠 𝑅𝑎𝑛𝑘𝑒𝑑 𝑆𝑜𝑟𝑡𝑒𝑑 𝑏𝑦 𝐴𝑣𝑔. 𝑆𝑐𝑜𝑟𝑒 0 1 Note: The strong similarity in the diagonal of A and first column of B and C is due to users match with themselves
  • 19. Alternative Method for Feature Matching: SVD 𝑢1 𝑢2 𝑢3 𝑢4 … 𝑔1 𝑔2 𝑔3 𝑔4 ⋮ 𝑠11 𝑠32 𝑠42 𝑠12 𝑠21 𝑠41 ? ? ? ? ? ? ? ? 𝑠23 𝑠42 𝑓1 𝑓2 … 𝑢1 𝑢2 𝑢3 𝑢4 ⋮ 𝑢11 𝑢32 𝑢12 𝑢21 𝑢41 𝑢31 𝑢22 𝑢42 𝑢13 𝑢33 𝑢43 𝑢23 𝑓1 𝑓2 … 𝑓1 𝑓2 ⋮ 𝑤11 0 0 0 0 0 0 𝑔1 𝑔2 𝑔3 … 𝑓1 𝑓2 ⋮ 𝑔11 𝑔32 𝑔12 𝑔21 𝑔31 𝑔22 𝑔13 𝑔33 𝑔23 𝑢1 𝑢2 𝑢3 𝑢4 … 𝑢1 𝑢2 𝑢3 𝑢4 ⋮ 1 𝑚32 𝑚42 𝑚12 𝑚21 𝑚41 1 1 𝑚23 1 𝑚31 𝑚13 𝑚14 𝑚42 𝑚43 𝑚34 𝑤22 𝑤33 Validation
  • 20. So why not SVD? • Feature matching doesn’t guarantee that matched users will own or play the same games
  • 21. User’s Game Preference Distribution of User’s Maximum Game Preferences Some users spend all playtime on Steam on Dota 2 Few users spend all playtime on Steam on Portal
  • 22. User 1: Looking For Players Best Match: 70% Compatibility 69% Compatibility Suggestion: You might enjoy Borderlands ! Worst Match: 0.01% Compatibility Actual Friend of User 1! Example Comparison of User Match Result
  • 24. Steam’s Current Game Recommendations: Personal Experience Games Steam Recommends Me My Playtime by Title Users’ Playtime for “Tiny and Big: Grandpa’s Leftovers” • Compared to my other games, my playtime of this game seems small • Compared to other people who own this game my playtime is small (lowest decile)
  • 25. Implying User Scores Based on Playtime • Score each user’s game by relative playtime compared to the set of people who own that game using deciles
  • 26. Game Recommendations Using SVD 𝑢1 𝑢2 𝑢3 𝑢4 … 𝑔1 𝑔2 𝑔3 𝑔4 ⋮ 𝑠11 𝑠32 𝑠42 𝑠12 𝑠21 𝑠41 ? ? ? ? ? ? ? ? 𝑠23 𝑠42 Compute SVD 𝑓1 𝑓2 … 𝑢1 𝑢2 𝑢3 𝑢4 ⋮ 𝑢11 𝑢32 𝑢12 𝑢21 𝑢41 𝑢31 𝑢22 𝑢42 𝑢13 𝑢33 𝑢43 𝑢23 𝑔1 𝑔2 𝑔3 … 𝑓1 𝑓2 ⋮ 𝑔11 𝑔32 𝑔12 𝑔21 𝑔31 𝑔22 𝑔13 𝑔33 𝑔23 𝑓1 𝑓2 … 𝑓1 𝑓2 ⋮ 𝑤11 0 0 0 0 0 0𝑤22 𝑤33 Train SVD with 80% of Data Test SVD with 20% of Data 𝑢1 𝑢2 𝑢3 … 𝑔1 𝑔2 ⋮ 𝑠11 𝑠12 𝑠21 ? ? 𝑠23 Predict SVD 𝑢1 𝑢2 𝑢3 … 𝑔1 𝑔2 ⋮ 𝑠11 𝑠12 𝑠21 ? ? 𝑠23 Calculate RMSE RMSE = 2.7 NRMSE = 0.31 Netflix’s NRMSE = 0.21 𝑅𝑀𝑆𝐸 = 1 𝑛 𝑖𝑗 𝑠𝑖𝑗 − 𝑠𝑖𝑗 2
  • 28. Independent Game Development is on the Rise!
  • 29. Only 31% of Steam games are rated on Metacritic 124 games have been purchased but never been played! Not all games are played; Not all games are rated
  • 30. Strictly Single Player Multiplayer The playtime on only 6 games is equal to the total playtime on all others Multiplayer games tend to have greater playtime than strictly single-player games
  • 31. Steam Games by Genre • MMOs account for few games on Steam, but have high playtime per title • Over half of Steam’s game are Indie, but Indie games have very little playtime per title
  • 32. Steam Games by Genre • Sports games have the highest average cost, and MMOs have the lowest (note subscriptions not included) • MMOs and Action games have the best “bang-for-the-buck” in terms of hours of playtime/dollar

Editor's Notes

  1. Say “I saw this as a problem and decided to come up with a solution”
  2. Say “I saw this as a problem and decided to come up with a solution”
  3. Say “I saw this as a problem and decided to come up with a solution”
  4. Say “I saw this as a problem and decided to come up with a solution”
  5. Add link to blog
  6. Bubble plot needs a legend
  7. Bubble plot needs a legend
  8. Bubble plot needs a legend
  9. Bubble plot needs a legend
  10. Bubble plot needs a legend
  11. Bubble plot needs a legend
  12. Bubble plot needs a legend