SlideShare a Scribd company logo
1 of 25
Emirates Advanced Analytics Hackathon
Vera Ekimenko
Hackathon Use Case 1: Problem statement
Use case #1 Social media image analytics to uncover valuable customer insights
Description
More than 3 billion photos are shared daily on social media and an estimated 85% of those photos lack text
references. It becomes increasingly important to incorporate social images analytics to draw better
customer insights.
Use of image analytics to identify and categorize the scenes, faces, logos, objects, and actions that
passengers post to social media every day.
Classify images from passenger posts as places, brands, food, events and action. The model should be able
to identify the places the passengers visited / like, the brands the passenger like, the events the passenger
attended.
Business Benefits
Provide exciting opportunities to uncover more valuable consumer insights from social media
 What places passengers visited
 What kind of places does passengers like
 Special events passengers attending
 What kind of food does the passenger like
 What brands does the passenger like
 Whom does the passenger travel with
 And much more.
This will help in target marketing to increase revenue
Data set to use Social Media posting of passengers
Success criteria Able to identify at least 3 of the above benefits
Social profiles provide information about customer’s interests, hobbies, music
preferences, places they like, role models they follow and etc. This will allow you
to segment your customers going beyond demographics and communicate with
them in a new very personalized manner.
Enrich Customer Genome with social IDs
Target customers with the most
relevant offers
Detect and predict emerging trends among the
target audience
Turn new customers into loyal ones through
personalized up-sell and cross-sell offers.
Random public Instagram account - 1
Brands
Random public Instagram account - 2
Food Food Food
BrandsFood
FoodFood
Food
Random public Instagram account - 3
Events
Brands
Food
Food
Food
Image categories I picked to train my models
Concert
Show
Theatre
Opera
Ballet
Football Rugby
TennisHorse racing
Racing
Gucci
Fendi
Chanel
Hermes
Dior
Events Brands Food
Dessert
Wine
Coffee
Seafood
Pizza
Salad
Pasta
Steak
Cake
Chicken
Burger
Fish
Sushi
Chocolate
Beer
Meat
Cheese
Ice cream
Beef
Vegetables
Fries
salmon
Rice
Bread
Pork
Soup
Pancakes
Tacos
Sandwich
Sports
Sample Sports images
Sample Event images
Sample Brands images
Sample Food images
All food images are multi-labelled
Bread
Sea food
Fries
The prediction system architecture (17 models)
Food/Non-food
Multi-label food
Fendi
Dior
Chanel
Gucci
Hermes
Ballet
Opera
Concert
Show
Theatre
Football
Rugby
Tennis
Horses
Racing
Multi-class brands Multi-class events
Transfer Learning using Keras
Places365 model
Version 1
Version 2
The projects stages and resources
Collection
• Download
Instagram
images
Labelling
• Manually
group
images
Training
• Light
version of
EGG16
Lenovo X220
64-bit Windows 10
Memory: 12GB
No GPU
Collection
15,000 images
for each hashtag
(total number 18)
150
150
Concert Show
Theatre
Opera Ballet
Football
Rugby
TennisHorse racing
Racing
Gucci
Fendi
Chanel
Hermes
Dior
EatingOut Food
Restaurant
270,000 images (10GB)
Labelling
Manual labelling
• Manual labelling 200
images for each category:
• 100 - ‘positive’
• 100 - ‘negative’
Helper model
• Trained a helper model
• 5-10 epochs
• 85-90% accuracy
Final labelling
• With the helper model
predict/ label all 15,000
images
• Manually correct the final
labelling
chanel not chanel
100 + 100
Labelling – Instagram noise ratio
hashtag labelled ratio
concert 627 1/24
show 1046 1/14
theatre 768 1/20
opera 225 1/66
ballet 969 1/15
football 1247 1/12
rugby 245 1/60
tennis 368 1/40
horseracing 1550 1/10
racing 339 1/44
gucci 492 1/30
fendi 348 1/43
chanel 307 1/50
hermes 1862 1/8
dior 350 1/43

Labelling helper model
a
Food labelling
Hashtags processing
• Using NLTK define a word category for
each hashtag
• Select images with hashtag category
‘food’
Manual labelling
• Group and select top 50 food hashtags
• For each food category manually label
images (true/false)
Fries 
Stake 
Bread 
Red wine 
Training – VGG16 for Brands and Events (v1)
Training – a unified model for Events
It didn’t train well no matter of parameters or base model used
Training – Places365 for Events (v2)
Places: A 10 million Image Database for Scene Recognition
Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., & Torralba, A.
IEEE Transactions on Pattern Analysis and Machine Intelligence
Food model (multi-label)
Next step - Segmentation
Customer profile
Thank you

More Related Content

Similar to Deep Learning Hackathon

Understanding, Characterizing, and Detecting Facebook Like Farms
Understanding, Characterizing, and Detecting Facebook Like FarmsUnderstanding, Characterizing, and Detecting Facebook Like Farms
Understanding, Characterizing, and Detecting Facebook Like FarmsEmiliano De Cristofaro
 
Content marketing strategy pitch
Content marketing strategy pitchContent marketing strategy pitch
Content marketing strategy pitchAngeliki Douratsou
 
Social Media Industry Report Running Shoes - Replise Content Finder
Social Media Industry Report Running Shoes - Replise Content FinderSocial Media Industry Report Running Shoes - Replise Content Finder
Social Media Industry Report Running Shoes - Replise Content FinderReplise.com
 
Scott DeRoche - Eastern Michigan University - SMW 2014 presentation
Scott DeRoche - Eastern Michigan University - SMW 2014 presentationScott DeRoche - Eastern Michigan University - SMW 2014 presentation
Scott DeRoche - Eastern Michigan University - SMW 2014 presentationScott DeRoche
 
Digital immersion for elt 3 29-10
Digital immersion for elt 3 29-10Digital immersion for elt 3 29-10
Digital immersion for elt 3 29-10Murilo Cappucci
 
Week 6 Tameka Kee Presentation
Week 6 Tameka Kee PresentationWeek 6 Tameka Kee Presentation
Week 6 Tameka Kee PresentationMediabistro
 
Instagram Social Spotlight
Instagram Social SpotlightInstagram Social Spotlight
Instagram Social SpotlightNick Westergaard
 
11 06-14 capabilities-deck
11 06-14 capabilities-deck11 06-14 capabilities-deck
11 06-14 capabilities-deckenternewmedia
 
Hivetree introduction (Mar 2014)
Hivetree introduction (Mar 2014)Hivetree introduction (Mar 2014)
Hivetree introduction (Mar 2014)HIVENEST
 
How to get started with social media
How to get started with social mediaHow to get started with social media
How to get started with social mediaEric Ritter
 
Yamaha New Female Bike (Social Stigma vs. strong will) Case Study
Yamaha New Female Bike (Social Stigma vs. strong will) Case StudyYamaha New Female Bike (Social Stigma vs. strong will) Case Study
Yamaha New Female Bike (Social Stigma vs. strong will) Case StudyMd Abrar Jahin
 
Social Media in a Corporate Context 2010 - Leesa Fogarty, Augure
Social Media in a Corporate Context 2010 - Leesa Fogarty, AugureSocial Media in a Corporate Context 2010 - Leesa Fogarty, Augure
Social Media in a Corporate Context 2010 - Leesa Fogarty, AugureCommunicate Magazine
 
Web Analytics and Google AdWords 101
Web Analytics and Google AdWords 101Web Analytics and Google AdWords 101
Web Analytics and Google AdWords 101Dvir Reznik
 
PeopleBrowsr Summary Deck
PeopleBrowsr Summary DeckPeopleBrowsr Summary Deck
PeopleBrowsr Summary DeckPeopleBrowsr
 
Social Websites And Seo Social Dev Camp Chicago2008 By John Fairley
Social Websites And Seo Social Dev Camp Chicago2008 By John FairleySocial Websites And Seo Social Dev Camp Chicago2008 By John Fairley
Social Websites And Seo Social Dev Camp Chicago2008 By John FairleyJohn Fairley
 
Creating a Social Media Analytics Action Plan
Creating a Social Media Analytics Action PlanCreating a Social Media Analytics Action Plan
Creating a Social Media Analytics Action PlanTaylor Pratt
 

Similar to Deep Learning Hackathon (20)

Understanding, Characterizing, and Detecting Facebook Like Farms
Understanding, Characterizing, and Detecting Facebook Like FarmsUnderstanding, Characterizing, and Detecting Facebook Like Farms
Understanding, Characterizing, and Detecting Facebook Like Farms
 
Content marketing strategy pitch
Content marketing strategy pitchContent marketing strategy pitch
Content marketing strategy pitch
 
Social Media Industry Report Running Shoes - Replise Content Finder
Social Media Industry Report Running Shoes - Replise Content FinderSocial Media Industry Report Running Shoes - Replise Content Finder
Social Media Industry Report Running Shoes - Replise Content Finder
 
Scott DeRoche - Eastern Michigan University - SMW 2014 presentation
Scott DeRoche - Eastern Michigan University - SMW 2014 presentationScott DeRoche - Eastern Michigan University - SMW 2014 presentation
Scott DeRoche - Eastern Michigan University - SMW 2014 presentation
 
Digital immersion for elt 3 29-10
Digital immersion for elt 3 29-10Digital immersion for elt 3 29-10
Digital immersion for elt 3 29-10
 
Amazon Mobile Analytics
Amazon Mobile AnalyticsAmazon Mobile Analytics
Amazon Mobile Analytics
 
Week 6 Tameka Kee Presentation
Week 6 Tameka Kee PresentationWeek 6 Tameka Kee Presentation
Week 6 Tameka Kee Presentation
 
Instagram Social Spotlight
Instagram Social SpotlightInstagram Social Spotlight
Instagram Social Spotlight
 
11 06-14 capabilities-deck
11 06-14 capabilities-deck11 06-14 capabilities-deck
11 06-14 capabilities-deck
 
Hivetree introduction (Mar 2014)
Hivetree introduction (Mar 2014)Hivetree introduction (Mar 2014)
Hivetree introduction (Mar 2014)
 
Social Media Marketing for Malls
Social Media Marketing for Malls Social Media Marketing for Malls
Social Media Marketing for Malls
 
How to get started with social media
How to get started with social mediaHow to get started with social media
How to get started with social media
 
Yamaha New Female Bike (Social Stigma vs. strong will) Case Study
Yamaha New Female Bike (Social Stigma vs. strong will) Case StudyYamaha New Female Bike (Social Stigma vs. strong will) Case Study
Yamaha New Female Bike (Social Stigma vs. strong will) Case Study
 
SMICC Manchester
SMICC ManchesterSMICC Manchester
SMICC Manchester
 
Social Media in a Corporate Context 2010 - Leesa Fogarty, Augure
Social Media in a Corporate Context 2010 - Leesa Fogarty, AugureSocial Media in a Corporate Context 2010 - Leesa Fogarty, Augure
Social Media in a Corporate Context 2010 - Leesa Fogarty, Augure
 
Web Analytics and Google AdWords 101
Web Analytics and Google AdWords 101Web Analytics and Google AdWords 101
Web Analytics and Google AdWords 101
 
PeopleBrowsr Summary Deck
PeopleBrowsr Summary DeckPeopleBrowsr Summary Deck
PeopleBrowsr Summary Deck
 
Social Websites And Seo Social Dev Camp Chicago2008 By John Fairley
Social Websites And Seo Social Dev Camp Chicago2008 By John FairleySocial Websites And Seo Social Dev Camp Chicago2008 By John Fairley
Social Websites And Seo Social Dev Camp Chicago2008 By John Fairley
 
Creating a Social Media Analytics Action Plan
Creating a Social Media Analytics Action PlanCreating a Social Media Analytics Action Plan
Creating a Social Media Analytics Action Plan
 
Ch 3 pps
Ch 3 ppsCh 3 pps
Ch 3 pps
 

More from Vera Ekimenko

Data Quality with AI
Data Quality with AIData Quality with AI
Data Quality with AIVera Ekimenko
 
Deep Reinforcement Learning for Portfolio Optimization
Deep Reinforcement Learning for Portfolio OptimizationDeep Reinforcement Learning for Portfolio Optimization
Deep Reinforcement Learning for Portfolio OptimizationVera Ekimenko
 
Artificial Intelligence for Data Quality
Artificial Intelligence for Data QualityArtificial Intelligence for Data Quality
Artificial Intelligence for Data QualityVera Ekimenko
 
Unsupervised AI for Data Quality
Unsupervised AI for Data QualityUnsupervised AI for Data Quality
Unsupervised AI for Data QualityVera Ekimenko
 
Cloudera migration oozie_hadoop_ci_cd_pipeline
Cloudera migration oozie_hadoop_ci_cd_pipelineCloudera migration oozie_hadoop_ci_cd_pipeline
Cloudera migration oozie_hadoop_ci_cd_pipelineVera Ekimenko
 
Artificial Intelligence Hackathon
Artificial Intelligence HackathonArtificial Intelligence Hackathon
Artificial Intelligence HackathonVera Ekimenko
 
KeyAchivementsMimecast
KeyAchivementsMimecastKeyAchivementsMimecast
KeyAchivementsMimecastVera Ekimenko
 
KeyAchivementsJustisPublishing
KeyAchivementsJustisPublishingKeyAchivementsJustisPublishing
KeyAchivementsJustisPublishingVera Ekimenko
 
HCM Access Insight Dashboard
HCM Access Insight DashboardHCM Access Insight Dashboard
HCM Access Insight DashboardVera Ekimenko
 

More from Vera Ekimenko (13)

Data Quality with AI
Data Quality with AIData Quality with AI
Data Quality with AI
 
AML Knowledge Graph
AML Knowledge GraphAML Knowledge Graph
AML Knowledge Graph
 
Deep Reinforcement Learning for Portfolio Optimization
Deep Reinforcement Learning for Portfolio OptimizationDeep Reinforcement Learning for Portfolio Optimization
Deep Reinforcement Learning for Portfolio Optimization
 
Artificial Intelligence for Data Quality
Artificial Intelligence for Data QualityArtificial Intelligence for Data Quality
Artificial Intelligence for Data Quality
 
Unsupervised AI for Data Quality
Unsupervised AI for Data QualityUnsupervised AI for Data Quality
Unsupervised AI for Data Quality
 
Cloudera migration oozie_hadoop_ci_cd_pipeline
Cloudera migration oozie_hadoop_ci_cd_pipelineCloudera migration oozie_hadoop_ci_cd_pipeline
Cloudera migration oozie_hadoop_ci_cd_pipeline
 
Artificial Intelligence Hackathon
Artificial Intelligence HackathonArtificial Intelligence Hackathon
Artificial Intelligence Hackathon
 
CSharp
CSharpCSharp
CSharp
 
DWHRestructure
DWHRestructureDWHRestructure
DWHRestructure
 
KeyAchivementsMimecast
KeyAchivementsMimecastKeyAchivementsMimecast
KeyAchivementsMimecast
 
KeyAchivementsJustisPublishing
KeyAchivementsJustisPublishingKeyAchivementsJustisPublishing
KeyAchivementsJustisPublishing
 
buy_in
buy_inbuy_in
buy_in
 
HCM Access Insight Dashboard
HCM Access Insight DashboardHCM Access Insight Dashboard
HCM Access Insight Dashboard
 

Recently uploaded

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
 
Customer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptxCustomer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptxEmmanuel Dauda
 
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝soniya singh
 
PKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptxPKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptxPramod Kumar Srivastava
 
Dubai Call Girls Wifey O52&786472 Call Girls Dubai
Dubai Call Girls Wifey O52&786472 Call Girls DubaiDubai Call Girls Wifey O52&786472 Call Girls Dubai
Dubai Call Girls Wifey O52&786472 Call Girls Dubaihf8803863
 
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Sapana Sha
 
Spark3's new memory model/management
Spark3's new memory model/managementSpark3's new memory model/management
Spark3's new memory model/managementakshesh doshi
 
Low Rate Call Girls Bhilai Anika 8250192130 Independent Escort Service Bhilai
Low Rate Call Girls Bhilai Anika 8250192130 Independent Escort Service BhilaiLow Rate Call Girls Bhilai Anika 8250192130 Independent Escort Service Bhilai
Low Rate Call Girls Bhilai Anika 8250192130 Independent Escort Service BhilaiSuhani Kapoor
 
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /WhatsappsBeautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsappssapnasaifi408
 
代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改
代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改
代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改atducpo
 
Schema on read is obsolete. Welcome metaprogramming..pdf
Schema on read is obsolete. Welcome metaprogramming..pdfSchema on read is obsolete. Welcome metaprogramming..pdf
Schema on read is obsolete. Welcome metaprogramming..pdfLars Albertsson
 
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
 
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...dajasot375
 
From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...Florian Roscheck
 
(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service
(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service
(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Serviceranjana rawat
 
{Pooja: 9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
{Pooja:  9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...{Pooja:  9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
{Pooja: 9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...Pooja Nehwal
 
20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdf20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdfHuman37
 

Recently uploaded (20)

꧁❤ Aerocity Call Girls Service Aerocity Delhi ❤꧂ 9999965857 ☎️ Hard And Sexy ...
꧁❤ Aerocity Call Girls Service Aerocity Delhi ❤꧂ 9999965857 ☎️ Hard And Sexy ...꧁❤ Aerocity Call Girls Service Aerocity Delhi ❤꧂ 9999965857 ☎️ Hard And Sexy ...
꧁❤ Aerocity Call Girls Service Aerocity Delhi ❤꧂ 9999965857 ☎️ Hard And Sexy ...
 
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
 
Deep Generative Learning for All - The Gen AI Hype (Spring 2024)
Deep Generative Learning for All - The Gen AI Hype (Spring 2024)Deep Generative Learning for All - The Gen AI Hype (Spring 2024)
Deep Generative Learning for All - The Gen AI Hype (Spring 2024)
 
Customer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptxCustomer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptx
 
E-Commerce Order PredictionShraddha Kamble.pptx
E-Commerce Order PredictionShraddha Kamble.pptxE-Commerce Order PredictionShraddha Kamble.pptx
E-Commerce Order PredictionShraddha Kamble.pptx
 
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
 
PKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptxPKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptx
 
Dubai Call Girls Wifey O52&786472 Call Girls Dubai
Dubai Call Girls Wifey O52&786472 Call Girls DubaiDubai Call Girls Wifey O52&786472 Call Girls Dubai
Dubai Call Girls Wifey O52&786472 Call Girls Dubai
 
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
 
Spark3's new memory model/management
Spark3's new memory model/managementSpark3's new memory model/management
Spark3's new memory model/management
 
Low Rate Call Girls Bhilai Anika 8250192130 Independent Escort Service Bhilai
Low Rate Call Girls Bhilai Anika 8250192130 Independent Escort Service BhilaiLow Rate Call Girls Bhilai Anika 8250192130 Independent Escort Service Bhilai
Low Rate Call Girls Bhilai Anika 8250192130 Independent Escort Service Bhilai
 
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /WhatsappsBeautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsapps
 
代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改
代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改
代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改
 
Schema on read is obsolete. Welcome metaprogramming..pdf
Schema on read is obsolete. Welcome metaprogramming..pdfSchema on read is obsolete. Welcome metaprogramming..pdf
Schema on read is obsolete. Welcome metaprogramming..pdf
 
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
 
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
 
From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...
 
(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service
(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service
(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service
 
{Pooja: 9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
{Pooja:  9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...{Pooja:  9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
{Pooja: 9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
 
20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdf20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdf
 

Deep Learning Hackathon

  • 1. Emirates Advanced Analytics Hackathon Vera Ekimenko
  • 2. Hackathon Use Case 1: Problem statement Use case #1 Social media image analytics to uncover valuable customer insights Description More than 3 billion photos are shared daily on social media and an estimated 85% of those photos lack text references. It becomes increasingly important to incorporate social images analytics to draw better customer insights. Use of image analytics to identify and categorize the scenes, faces, logos, objects, and actions that passengers post to social media every day. Classify images from passenger posts as places, brands, food, events and action. The model should be able to identify the places the passengers visited / like, the brands the passenger like, the events the passenger attended. Business Benefits Provide exciting opportunities to uncover more valuable consumer insights from social media  What places passengers visited  What kind of places does passengers like  Special events passengers attending  What kind of food does the passenger like  What brands does the passenger like  Whom does the passenger travel with  And much more. This will help in target marketing to increase revenue Data set to use Social Media posting of passengers Success criteria Able to identify at least 3 of the above benefits
  • 3. Social profiles provide information about customer’s interests, hobbies, music preferences, places they like, role models they follow and etc. This will allow you to segment your customers going beyond demographics and communicate with them in a new very personalized manner. Enrich Customer Genome with social IDs Target customers with the most relevant offers Detect and predict emerging trends among the target audience Turn new customers into loyal ones through personalized up-sell and cross-sell offers.
  • 4. Random public Instagram account - 1 Brands
  • 5. Random public Instagram account - 2 Food Food Food BrandsFood FoodFood Food
  • 6. Random public Instagram account - 3 Events Brands Food Food Food
  • 7. Image categories I picked to train my models Concert Show Theatre Opera Ballet Football Rugby TennisHorse racing Racing Gucci Fendi Chanel Hermes Dior Events Brands Food Dessert Wine Coffee Seafood Pizza Salad Pasta Steak Cake Chicken Burger Fish Sushi Chocolate Beer Meat Cheese Ice cream Beef Vegetables Fries salmon Rice Bread Pork Soup Pancakes Tacos Sandwich Sports
  • 12. All food images are multi-labelled Bread Sea food Fries
  • 13. The prediction system architecture (17 models) Food/Non-food Multi-label food Fendi Dior Chanel Gucci Hermes Ballet Opera Concert Show Theatre Football Rugby Tennis Horses Racing Multi-class brands Multi-class events Transfer Learning using Keras Places365 model Version 1 Version 2
  • 14. The projects stages and resources Collection • Download Instagram images Labelling • Manually group images Training • Light version of EGG16 Lenovo X220 64-bit Windows 10 Memory: 12GB No GPU
  • 15. Collection 15,000 images for each hashtag (total number 18) 150 150 Concert Show Theatre Opera Ballet Football Rugby TennisHorse racing Racing Gucci Fendi Chanel Hermes Dior EatingOut Food Restaurant 270,000 images (10GB)
  • 16. Labelling Manual labelling • Manual labelling 200 images for each category: • 100 - ‘positive’ • 100 - ‘negative’ Helper model • Trained a helper model • 5-10 epochs • 85-90% accuracy Final labelling • With the helper model predict/ label all 15,000 images • Manually correct the final labelling chanel not chanel 100 + 100
  • 17. Labelling – Instagram noise ratio hashtag labelled ratio concert 627 1/24 show 1046 1/14 theatre 768 1/20 opera 225 1/66 ballet 969 1/15 football 1247 1/12 rugby 245 1/60 tennis 368 1/40 horseracing 1550 1/10 racing 339 1/44 gucci 492 1/30 fendi 348 1/43 chanel 307 1/50 hermes 1862 1/8 dior 350 1/43 
  • 19. Food labelling Hashtags processing • Using NLTK define a word category for each hashtag • Select images with hashtag category ‘food’ Manual labelling • Group and select top 50 food hashtags • For each food category manually label images (true/false) Fries  Stake  Bread  Red wine 
  • 20. Training – VGG16 for Brands and Events (v1)
  • 21. Training – a unified model for Events It didn’t train well no matter of parameters or base model used
  • 22. Training – Places365 for Events (v2) Places: A 10 million Image Database for Scene Recognition Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., & Torralba, A. IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 24. Next step - Segmentation Customer profile