SlideShare a Scribd company logo
1 of 37
Download to read offline
How we do it:
1) Monitoring and Measuring with Metrics
2) User Modelling to improve retailer and Metail user
experience
3) Predictive modelling
a) Predicting customer mood (logistic
regression)
b) Graph models and garment recommendation
How we do it:
1) Monitoring and Measuring with Metrics
2) User Modelling to improve retailer and Metail user
experience
3) Predictive modelling
a) Predicting customer mood (logistic
regression)
b) Graph models and garment recommendation
•
•
•
•
•
-
How we do it:
1) Monitoring and Measuring with Metrics
2) User Modelling to improve retailer and Metail
user experience
3) Predictive modelling
a) Predicting customer mood (logistic
regression)
b) Graph models and garment
recommendation
How we do it:
1) Monitoring and Measuring with Metrics
2) User Modelling to improve retailer and Metail
user experience
3) Predictive modelling
a) Predicting customer mood (logistic
regression)
b) Graph models and garment recommendation
•
•
•
•
●
●
16
User and Garment Flow through Retailer Website
New
Users
Garments
Website
User Flow
Garment Flow
New Popular Discount ...
Unsold
Garments
Dream
No Revisit
Users
Sold
Garments
Returned
Garments
Revisit
Users
Browse Buy
…
(Try?)
How we do it:
1) Monitoring and Measuring with Metrics
2) User Modelling to improve retailer and Metail user
experience
3) Predictive modelling
a) Predicting customer mood (logistic
regression)
b) Graph models and garment recommendation
How we do it:
1) Monitoring and Measuring with Metrics
2) User Modelling to improve retailer and Metail user
experience
3) Predictive modelling
a) Predicting customer mood (logistic
regression)
b) Graph models and garment recommendation
22
Predicting Customer Mood
23
A browser?
Predicting Customer Mood Instagram, Facebook “You look fabulous!”
Glamorous, trendy
“I love this”
24
or a buyer?
Predicting Customer Mood
Details
Price
Fit
25
A browser or a buyer?
Problem: 4 out of 5 customers are
new to the site
How do you decide what user
experience they need in the first 90
seconds?
Predicting Customer Mood Instagram, Facebook “You look fabulous!”
Glamorous, trendy
“I love this”
Details
Price
Fit
26
Predict customer mood using Metail clickstream data
S SALE
S
Conversion
Non-Conversion
We know some information at first click...
...and a lot of information by the end of the
session...
...but can we make an
accurate prediction just
based on the first 5 events?
27
Identified 174 features of
importance
Machine Learning approach to detect customer mood
Turning the
model around
to view tried
on clothes
Likely to convert
Unlikely to convert
Facebook
marketing
source
Tested predictive accuracy
Random
chance
Accuracy
of early detection
model is nearly
as good as full
session data
How we do it:
1) Monitoring and Measuring with Metrics
2) User Modelling to improve retailer and Metail user
experience
3) Aggregating and describing user data
4) Predictive modelling
a) Predicting customer mood (logistic
regression)
b) Graph models and garment recommendation
How we do it:
1) Monitoring and Measuring with Metrics
2) User Modelling to improve retailer and Metail user
experience
3) Aggregating and describing user data
4) Predictive modelling
a) Predicting customer mood (logistic regression)
b) Graph models and garment recommendation
30
Which garment is most popular?
31
Look for events where a user removes one garment and
replaces it with another
Aggregate count across all users
Calculate net flow into each garment e.g. if 10 users
swap garment A for B, 15 swap B for A then net we
have 5 users swapping from B to A
Ignore swaps with small number of garments
Result: a simple collaborative filter
‘Other users who tried this garment also were interested
in this other garment’
Example at right shows this for Tops on a sample retailer
Garment Recommendation from User Behaviour
32
Looking at multiple garment
categories, can we see any
trends based on try on
preferences?
On the right we see some
indication of users moving
away from the most visible
garment at top of page and
towards red summer dresses
We can see the garment
features visually from the
thumbnails but can we
automatically detect them?
Fashion Trend Detection
33
Deep Learning: Extract Garment Features from Images
SKU image SKU features SKU feature vectors
~100 dimension
DNN Unstack
34
Check whether the Garment
Attribute Predictor features are
reasonable
It looks like visually similar garments
are close together in t-SNE
Garment recommendation:
For any given SKU find ‘close’ SKUs
Outfit recommendation:
For any given SKU find ‘close’ SKUs
that are of a different garment
category
Problem: feature space has high
dimension so ‘close’ is tricky
Solution: dimensionality reduction
Dimension reduction of feature space
35
Style Space Decomposition
A
B
½
User SKU
Project onto SKUs
Probability of SKUs being related maps to distance in Style
Space
Use optimization to find mapping from ~100 dimensional feature
space to ~10 dimensional Style Space
See 'Image-based recommendation on styles and substitutes' by Julian McAuley et al.
How we do it:
1) Monitoring and Measuring with Metrics
2) User Modelling to improve retailer and Metail user
experience
3) Predictive modelling
a) Predicting customer mood (logistic regression)
b) Graph models and garment recommendation
From Metrics to Models:  Data Science at Metail

More Related Content

Similar to From Metrics to Models: Data Science at Metail

Big Data LDN 2017: Advanced Analytics Applied to Marketing Attribution
Big Data LDN 2017: Advanced Analytics Applied to Marketing AttributionBig Data LDN 2017: Advanced Analytics Applied to Marketing Attribution
Big Data LDN 2017: Advanced Analytics Applied to Marketing AttributionMatt Stubbs
 
Funnels Workshop Web Summit 2014 @geckoboard @GA
Funnels Workshop Web Summit 2014 @geckoboard @GAFunnels Workshop Web Summit 2014 @geckoboard @GA
Funnels Workshop Web Summit 2014 @geckoboard @GASofia Quintero
 
UK Online Fashion UX Benchmarking slides
UK Online Fashion UX Benchmarking slidesUK Online Fashion UX Benchmarking slides
UK Online Fashion UX Benchmarking slidesarthurmoan
 
Fashion Bangla- A digital Fashion Sourcing Platform.pptx
Fashion Bangla- A digital Fashion Sourcing Platform.pptxFashion Bangla- A digital Fashion Sourcing Platform.pptx
Fashion Bangla- A digital Fashion Sourcing Platform.pptxAjazBanna
 
6 th project navigating, reports, and dashboards
6 th project navigating, reports, and dashboards6 th project navigating, reports, and dashboards
6 th project navigating, reports, and dashboardsMostafa A.
 
Sales Forecasting for Management Consultants & Business Analysts
Sales Forecasting for Management Consultants & Business AnalystsSales Forecasting for Management Consultants & Business Analysts
Sales Forecasting for Management Consultants & Business AnalystsAsen Gyczew
 
MCN2017 Workshop: Web Analytics and SEO
MCN2017 Workshop: Web Analytics and SEOMCN2017 Workshop: Web Analytics and SEO
MCN2017 Workshop: Web Analytics and SEOBrian Alpert
 
How eCommerce Businesses Can Make Best Use of Google Analytics data
How eCommerce Businesses Can Make Best Use of Google Analytics dataHow eCommerce Businesses Can Make Best Use of Google Analytics data
How eCommerce Businesses Can Make Best Use of Google Analytics dataTatvic Analytics
 
The Upside to Cross-Selling: How MVMT Watches Boosted Revenue
The Upside to Cross-Selling: How MVMT Watches Boosted RevenueThe Upside to Cross-Selling: How MVMT Watches Boosted Revenue
The Upside to Cross-Selling: How MVMT Watches Boosted RevenueOptimizely
 
Rèvolange the Ideal Fashion Suggestion for Customers
Rèvolange the Ideal Fashion Suggestion for CustomersRèvolange the Ideal Fashion Suggestion for Customers
Rèvolange the Ideal Fashion Suggestion for CustomersIRJET Journal
 
A Brief about How to design a Strategic Branded Content management system
A Brief about How to design a Strategic Branded Content management systemA Brief about How to design a Strategic Branded Content management system
A Brief about How to design a Strategic Branded Content management systemH Joshi
 
Simply Data driven behavioural algorithms
Simply Data driven behavioural algorithmsSimply Data driven behavioural algorithms
Simply Data driven behavioural algorithmsNana Bianca
 
Dbs challange stage 1
Dbs challange stage 1Dbs challange stage 1
Dbs challange stage 1Jatinder Bedi
 
Business Research Methods: Marketing Strategy for The ShoppingPro
Business Research Methods: Marketing Strategy for The ShoppingPro Business Research Methods: Marketing Strategy for The ShoppingPro
Business Research Methods: Marketing Strategy for The ShoppingPro Devansh Doshi
 
Digital marketing, SEO, Social Media, Blogging Campaign
Digital marketing, SEO, Social Media, Blogging CampaignDigital marketing, SEO, Social Media, Blogging Campaign
Digital marketing, SEO, Social Media, Blogging CampaignTechnians
 
Assignment on establish a brand
Assignment on establish a brandAssignment on establish a brand
Assignment on establish a brandSmart Safayet
 
Industrially custom made clothing
Industrially custom made clothingIndustrially custom made clothing
Industrially custom made clothingdr Gordana Colovic
 
Order Finalization & Pre Merchandising
Order Finalization & Pre MerchandisingOrder Finalization & Pre Merchandising
Order Finalization & Pre MerchandisingZia Uddin Mahmud
 

Similar to From Metrics to Models: Data Science at Metail (20)

Big Data LDN 2017: Advanced Analytics Applied to Marketing Attribution
Big Data LDN 2017: Advanced Analytics Applied to Marketing AttributionBig Data LDN 2017: Advanced Analytics Applied to Marketing Attribution
Big Data LDN 2017: Advanced Analytics Applied to Marketing Attribution
 
Funnels Workshop Web Summit 2014 @geckoboard @GA
Funnels Workshop Web Summit 2014 @geckoboard @GAFunnels Workshop Web Summit 2014 @geckoboard @GA
Funnels Workshop Web Summit 2014 @geckoboard @GA
 
UK Online Fashion UX Benchmarking slides
UK Online Fashion UX Benchmarking slidesUK Online Fashion UX Benchmarking slides
UK Online Fashion UX Benchmarking slides
 
Fashion Bangla- A digital Fashion Sourcing Platform.pptx
Fashion Bangla- A digital Fashion Sourcing Platform.pptxFashion Bangla- A digital Fashion Sourcing Platform.pptx
Fashion Bangla- A digital Fashion Sourcing Platform.pptx
 
LinkedIn Portfolio
LinkedIn PortfolioLinkedIn Portfolio
LinkedIn Portfolio
 
6 th project navigating, reports, and dashboards
6 th project navigating, reports, and dashboards6 th project navigating, reports, and dashboards
6 th project navigating, reports, and dashboards
 
Sales Forecasting for Management Consultants & Business Analysts
Sales Forecasting for Management Consultants & Business AnalystsSales Forecasting for Management Consultants & Business Analysts
Sales Forecasting for Management Consultants & Business Analysts
 
Phase 2, JOCKEY
Phase 2, JOCKEYPhase 2, JOCKEY
Phase 2, JOCKEY
 
MCN2017 Workshop: Web Analytics and SEO
MCN2017 Workshop: Web Analytics and SEOMCN2017 Workshop: Web Analytics and SEO
MCN2017 Workshop: Web Analytics and SEO
 
How eCommerce Businesses Can Make Best Use of Google Analytics data
How eCommerce Businesses Can Make Best Use of Google Analytics dataHow eCommerce Businesses Can Make Best Use of Google Analytics data
How eCommerce Businesses Can Make Best Use of Google Analytics data
 
The Upside to Cross-Selling: How MVMT Watches Boosted Revenue
The Upside to Cross-Selling: How MVMT Watches Boosted RevenueThe Upside to Cross-Selling: How MVMT Watches Boosted Revenue
The Upside to Cross-Selling: How MVMT Watches Boosted Revenue
 
Rèvolange the Ideal Fashion Suggestion for Customers
Rèvolange the Ideal Fashion Suggestion for CustomersRèvolange the Ideal Fashion Suggestion for Customers
Rèvolange the Ideal Fashion Suggestion for Customers
 
A Brief about How to design a Strategic Branded Content management system
A Brief about How to design a Strategic Branded Content management systemA Brief about How to design a Strategic Branded Content management system
A Brief about How to design a Strategic Branded Content management system
 
Simply Data driven behavioural algorithms
Simply Data driven behavioural algorithmsSimply Data driven behavioural algorithms
Simply Data driven behavioural algorithms
 
Dbs challange stage 1
Dbs challange stage 1Dbs challange stage 1
Dbs challange stage 1
 
Business Research Methods: Marketing Strategy for The ShoppingPro
Business Research Methods: Marketing Strategy for The ShoppingPro Business Research Methods: Marketing Strategy for The ShoppingPro
Business Research Methods: Marketing Strategy for The ShoppingPro
 
Digital marketing, SEO, Social Media, Blogging Campaign
Digital marketing, SEO, Social Media, Blogging CampaignDigital marketing, SEO, Social Media, Blogging Campaign
Digital marketing, SEO, Social Media, Blogging Campaign
 
Assignment on establish a brand
Assignment on establish a brandAssignment on establish a brand
Assignment on establish a brand
 
Industrially custom made clothing
Industrially custom made clothingIndustrially custom made clothing
Industrially custom made clothing
 
Order Finalization & Pre Merchandising
Order Finalization & Pre MerchandisingOrder Finalization & Pre Merchandising
Order Finalization & Pre Merchandising
 

Recently uploaded

Introduction-to-Machine-Learning (1).pptx
Introduction-to-Machine-Learning (1).pptxIntroduction-to-Machine-Learning (1).pptx
Introduction-to-Machine-Learning (1).pptxfirstjob4
 
Log Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptxLog Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptxJohnnyPlasten
 
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
 
BabyOno dropshipping via API with DroFx.pptx
BabyOno dropshipping via API with DroFx.pptxBabyOno dropshipping via API with DroFx.pptx
BabyOno dropshipping via API with DroFx.pptxolyaivanovalion
 
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Callshivangimorya083
 
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
 
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...Suhani Kapoor
 
Industrialised data - the key to AI success.pdf
Industrialised data - the key to AI success.pdfIndustrialised data - the key to AI success.pdf
Industrialised data - the key to AI success.pdfLars Albertsson
 
Ukraine War presentation: KNOW THE BASICS
Ukraine War presentation: KNOW THE BASICSUkraine War presentation: KNOW THE BASICS
Ukraine War presentation: KNOW THE BASICSAishani27
 
100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptxAnupama Kate
 
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Callshivangimorya083
 
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
 
VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...
VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...
VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...Suhani Kapoor
 
Edukaciniai dropshipping via API with DroFx
Edukaciniai dropshipping via API with DroFxEdukaciniai dropshipping via API with DroFx
Edukaciniai dropshipping via API with DroFxolyaivanovalion
 
定制英国白金汉大学毕业证(UCB毕业证书) 成绩单原版一比一
定制英国白金汉大学毕业证(UCB毕业证书)																			成绩单原版一比一定制英国白金汉大学毕业证(UCB毕业证书)																			成绩单原版一比一
定制英国白金汉大学毕业证(UCB毕业证书) 成绩单原版一比一ffjhghh
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...apidays
 
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
 

Recently uploaded (20)

Introduction-to-Machine-Learning (1).pptx
Introduction-to-Machine-Learning (1).pptxIntroduction-to-Machine-Learning (1).pptx
Introduction-to-Machine-Learning (1).pptx
 
Log Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptxLog Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptx
 
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
 
BabyOno dropshipping via API with DroFx.pptx
BabyOno dropshipping via API with DroFx.pptxBabyOno dropshipping via API with DroFx.pptx
BabyOno dropshipping via API with DroFx.pptx
 
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
 
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
 
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
 
Industrialised data - the key to AI success.pdf
Industrialised data - the key to AI success.pdfIndustrialised data - the key to AI success.pdf
Industrialised data - the key to AI success.pdf
 
VIP Call Girls Service Charbagh { Lucknow Call Girls Service 9548273370 } Boo...
VIP Call Girls Service Charbagh { Lucknow Call Girls Service 9548273370 } Boo...VIP Call Girls Service Charbagh { Lucknow Call Girls Service 9548273370 } Boo...
VIP Call Girls Service Charbagh { Lucknow Call Girls Service 9548273370 } Boo...
 
Delhi 99530 vip 56974 Genuine Escort Service Call Girls in Kishangarh
Delhi 99530 vip 56974 Genuine Escort Service Call Girls in  KishangarhDelhi 99530 vip 56974 Genuine Escort Service Call Girls in  Kishangarh
Delhi 99530 vip 56974 Genuine Escort Service Call Girls in Kishangarh
 
Ukraine War presentation: KNOW THE BASICS
Ukraine War presentation: KNOW THE BASICSUkraine War presentation: KNOW THE BASICS
Ukraine War presentation: KNOW THE BASICS
 
100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx
 
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
 
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
 
꧁❤ 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 ...
 
VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...
VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...
VIP High Profile Call Girls Amravati Aarushi 8250192130 Independent Escort Se...
 
Edukaciniai dropshipping via API with DroFx
Edukaciniai dropshipping via API with DroFxEdukaciniai dropshipping via API with DroFx
Edukaciniai dropshipping via API with DroFx
 
定制英国白金汉大学毕业证(UCB毕业证书) 成绩单原版一比一
定制英国白金汉大学毕业证(UCB毕业证书)																			成绩单原版一比一定制英国白金汉大学毕业证(UCB毕业证书)																			成绩单原版一比一
定制英国白金汉大学毕业证(UCB毕业证书) 成绩单原版一比一
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 
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
 

From Metrics to Models: Data Science at Metail

  • 1.
  • 2.
  • 3.
  • 4.
  • 5.
  • 6. How we do it: 1) Monitoring and Measuring with Metrics 2) User Modelling to improve retailer and Metail user experience 3) Predictive modelling a) Predicting customer mood (logistic regression) b) Graph models and garment recommendation
  • 7. How we do it: 1) Monitoring and Measuring with Metrics 2) User Modelling to improve retailer and Metail user experience 3) Predictive modelling a) Predicting customer mood (logistic regression) b) Graph models and garment recommendation
  • 8.
  • 10.
  • 11. How we do it: 1) Monitoring and Measuring with Metrics 2) User Modelling to improve retailer and Metail user experience 3) Predictive modelling a) Predicting customer mood (logistic regression) b) Graph models and garment recommendation
  • 12. How we do it: 1) Monitoring and Measuring with Metrics 2) User Modelling to improve retailer and Metail user experience 3) Predictive modelling a) Predicting customer mood (logistic regression) b) Graph models and garment recommendation
  • 14.
  • 16. 16 User and Garment Flow through Retailer Website New Users Garments Website User Flow Garment Flow New Popular Discount ... Unsold Garments Dream No Revisit Users Sold Garments Returned Garments Revisit Users Browse Buy … (Try?)
  • 17.
  • 18.
  • 19.
  • 20. How we do it: 1) Monitoring and Measuring with Metrics 2) User Modelling to improve retailer and Metail user experience 3) Predictive modelling a) Predicting customer mood (logistic regression) b) Graph models and garment recommendation
  • 21. How we do it: 1) Monitoring and Measuring with Metrics 2) User Modelling to improve retailer and Metail user experience 3) Predictive modelling a) Predicting customer mood (logistic regression) b) Graph models and garment recommendation
  • 23. 23 A browser? Predicting Customer Mood Instagram, Facebook “You look fabulous!” Glamorous, trendy “I love this”
  • 24. 24 or a buyer? Predicting Customer Mood Details Price Fit
  • 25. 25 A browser or a buyer? Problem: 4 out of 5 customers are new to the site How do you decide what user experience they need in the first 90 seconds? Predicting Customer Mood Instagram, Facebook “You look fabulous!” Glamorous, trendy “I love this” Details Price Fit
  • 26. 26 Predict customer mood using Metail clickstream data S SALE S Conversion Non-Conversion We know some information at first click... ...and a lot of information by the end of the session... ...but can we make an accurate prediction just based on the first 5 events?
  • 27. 27 Identified 174 features of importance Machine Learning approach to detect customer mood Turning the model around to view tried on clothes Likely to convert Unlikely to convert Facebook marketing source Tested predictive accuracy Random chance Accuracy of early detection model is nearly as good as full session data
  • 28. How we do it: 1) Monitoring and Measuring with Metrics 2) User Modelling to improve retailer and Metail user experience 3) Aggregating and describing user data 4) Predictive modelling a) Predicting customer mood (logistic regression) b) Graph models and garment recommendation
  • 29. How we do it: 1) Monitoring and Measuring with Metrics 2) User Modelling to improve retailer and Metail user experience 3) Aggregating and describing user data 4) Predictive modelling a) Predicting customer mood (logistic regression) b) Graph models and garment recommendation
  • 30. 30 Which garment is most popular?
  • 31. 31 Look for events where a user removes one garment and replaces it with another Aggregate count across all users Calculate net flow into each garment e.g. if 10 users swap garment A for B, 15 swap B for A then net we have 5 users swapping from B to A Ignore swaps with small number of garments Result: a simple collaborative filter ‘Other users who tried this garment also were interested in this other garment’ Example at right shows this for Tops on a sample retailer Garment Recommendation from User Behaviour
  • 32. 32 Looking at multiple garment categories, can we see any trends based on try on preferences? On the right we see some indication of users moving away from the most visible garment at top of page and towards red summer dresses We can see the garment features visually from the thumbnails but can we automatically detect them? Fashion Trend Detection
  • 33. 33 Deep Learning: Extract Garment Features from Images SKU image SKU features SKU feature vectors ~100 dimension DNN Unstack
  • 34. 34 Check whether the Garment Attribute Predictor features are reasonable It looks like visually similar garments are close together in t-SNE Garment recommendation: For any given SKU find ‘close’ SKUs Outfit recommendation: For any given SKU find ‘close’ SKUs that are of a different garment category Problem: feature space has high dimension so ‘close’ is tricky Solution: dimensionality reduction Dimension reduction of feature space
  • 35. 35 Style Space Decomposition A B ½ User SKU Project onto SKUs Probability of SKUs being related maps to distance in Style Space Use optimization to find mapping from ~100 dimensional feature space to ~10 dimensional Style Space See 'Image-based recommendation on styles and substitutes' by Julian McAuley et al.
  • 36. How we do it: 1) Monitoring and Measuring with Metrics 2) User Modelling to improve retailer and Metail user experience 3) Predictive modelling a) Predicting customer mood (logistic regression) b) Graph models and garment recommendation