SlideShare a Scribd company logo
Knowledge Graphs
--Enter-->
The Hype Cycle
@GeorgeCushen
PyData London 2019
Image: HBO
4
The Hype Cycle
Proof
Mr Porter
Eminem
P Diddy
DJ
Khaled
Notorious
B.I.G.
DJ
Khaled
Image: Meghan Roberts
Rihanna
collaborated_with
wants_to_collaborate_with
Image: Paramount Pictures
6
Outfit available from
https://www.farfetch.com
Farfetch at a glance
7
> 3,000*
Employees across 13 countries
$1.4 Billion*
Gross Merchandise Value
> 3,000*
Brands available for consumers
to shop
> 1,000**
Luxury sellers on the
Marketplace
$601**
AOV on Marketplace
> 2.9 Million*
Orders on Marketplace
1.7 million**
Active Marketplace consumers
$307 Billion
Size of personal luxury good
industry (Bain estimates)
*Correct for full year 2018 **As at Q1 2019
15**
Marketplace language sites
8
What is this graph thing?
“Hey, I’ve got this lit bar graph visualization for you! It’s 🔥🔥🔥!”
A New Perspective: Emphasising Relationships
● Businesses and their products/services are all about Entities and Relationships
● Examples of entities and relationships in industry:
Farfetch Consumer searches Product with Terms
Amazon Seller sells Product to Consumer
Uber Driver provides Trip to Rider
Facebook Person shares Status with Friend
● How can we represent, analyse, and visualise this kind of data?
10
What is a knowledge graph?
A knowledge graph can describe
● a collection of nodes (entities) representing business and fashion entities
has_term
● and with labeled relationships between the nodes
Product
D&G
tote bag
Attribute
Leopard
Print Attribute
Leopard
Spots
Attribute
Animal
Print
Properties:
Language = “EN”
● each containing information (properties)
Properties:
ProductID = 123
11
Dots and Lines
Image: ICIJ
The Panama Papers
14
16
Discovering the pearl
DELFINA DELETTREZ 'Trillion' earring
17
Discovering the diamond
JIMMY CHOO Diamond sneakers
18
Generic vs Domain Specific Knowledge Graphs
Generic vs Domain Specific
Generic
Domain Specific:
Fashion Products
Products
Brands
Categories
Editorials
...
Attributes
Synonyms
Colours
Materials
Concepts
...
Customers
Orders
Payments
Promotions
Reviews
...
19
Example Use Cases
Free Text Search
Increase product discovery with
synonyms and rich attributes for
material, occasion (e.g. skiing), etc.
Semantic Search
Increase product discovery based
by using graph to understand
consumer’s intent
Ranking
Leverage rich product connections to
increase relevance on listing pages
Recommendations
Increase relevance based on richer
product attributes and deep graph
relationships
20
Building the fashion knowledge graph
Search Recommendations ...
F-Graph
(Associates taxonomy entities with business entities)
AI Knowledge cleaning Entity resolution Schema mapping
Applications
Taxonomy &
Graph
Construction
Knowledge
Collection
Expert Knowledge Data-Driven Insights
Skinny
21
Universal Fashion Taxonomy
Fashion
Taxonomy
Synonyms
Descriptive
attributes
Brand DNA
Materials
ColoursTrends
Editorial,
emotive,
seasonal
concepts
Textile Cotton Denim
Product
2
Swedish
Design
Acne
Glastonbury Festival
Summer
Product
1
PrintsSnake
Blue
Light
Blue
Synonym Enrichment
Padded
coat
Down
coat
Duvet coat
Quilted
coat
Puffer
jacket
Down-filled
jacket
Down
jacket
Quilted
jacket
Duvet
jacket
Down-filled
coat
Padded
jacket
Puffer
coat
Techniques
📷 CV/DL +
📖 NLP +
✔️ Conflation +
👙 Inference +
👥 Crowdsourcing
23
24
Richer Product Data
Existing
catalog
External Enrichment
Internal Enrichment
25
Richer Product Data
Existing catalog
data
AI predicts richer and
more diverse attributes
The fashion knowledge graph,
F-Graph, connects and
enriches entities
Qualityof
ProductDNA
26
Building a simple graph in Python
import networkx as nx
import matplotlib.pyplot as plt
graph = nx.DiGraph()
graph.add_node(0, name='Product A'), graph.add_node(1),
graph.add_node(2), graph.add_node(3), graph.add_node(4)
graph.add_edge(0, 1, weight=0.75), graph.add_edge(0,
4),graph.add_edge(1, 2), graph.add_edge(0,
2),graph.add_edge(1, 4), graph.add_edge(1, 3),
graph.add_edge(3, 2), graph.add_edge(3,1),
graph.add_edge(4,3)
nx.draw(graph, with_labels=True, font_weight='bold')
plt.show()
$ pipenv install networkx matplotlib
27
Graph databases
● Neo4j
○ Packages: neo4j, py2neo
● AWS Neptune
○ Package: gremlinpython
● Azure Cosmos
○ Package: gremlinpython
28
Demo
https://github.com/gcushen/fortnite-fashionista
Image: Epic Games
29
30
31
32
Why use Pyenv + Pipenv for your projects?
Pipenv
● Officially recommended way of managing project
dependencies
● No requirements.txt and managing virtualenvs
● Instead a Pipfile in your project that performs this stuff
automatically
$ pip install -U pipenv # Install Pipenv
$ cd my_project # Go to your
project
$ pipenv install # Initialize Pipenv
$ pipenv install neo4j # Install a package
$ pipenv shell # Enter virtual env
$ python my_script.py # Run a script
Image: xkcd
33
Communicating a graph
Product Managers
“How can we improve the
customer experience?”
“How much can the
knowledge graph impact
GMV?”
Data Scientists
“Wow, looks like a NN,
hold my Pandas 🐼🐼🐼,
I’m onboard!!”
Backend Engineers
“Why do we need a
graph?”
“Which graph database
meets the requirements?”
Data Engineers
“Is your Airflow dizzy? It’s
traversing through cyclic
connections?!”
34
Where do I see most value
with the knowledge graph?
● Improving customer experience such as
by understanding consumer intent in search
queries
● Connecting further business entities (e.g.
content) for hyper-personalisation
● Deriving new knowledge via graph
analysis and graph-based AI
● Enabling new, innovative applications
35
Research
Image: Kim Albrecht
37
Why use a knowledge graph?
● Have naturally highly connected-data
● Derive new insights with Graph Analysis & Graph-based AI
● Enable stakeholders to easily visualise relationships and make informed decisions
● Flexible schema to facilitate evolution to expand business entities
● Optimized for storing and querying graphs
○ Significantly faster than SQL databases for querying relationships
○ Relationships are a fundamental structure, so following relationships is a
single lookup, making this operation blazingly fast
38
The future
39
Bonus
The Tool to Create Professional Websites
From Markdown, Jupyter, and RStudio
https://github.com/gcushen/hugo-academic
40
100,000+ websites. 2,000+ GitHub Stars. 80+ Contributors. 40+ Widgets, Themes, and Languages.
Used by academics and labs at Stanford, MIT, Cambridge. Featured on GitHub’s Blog.
41
42
Install Hugo as Prerequisite
● Windows
○ choco install hugo-extended -confirm
● Mac
○ brew update && brew install hugo
● Linux
○ sudo snap install hugo --channel=extended/stable
43
Build your site with Academic
1. Fork https://github.com/sourcethemes/academic-kickstart
2. Setup and view your site locally:
a. git clone https://github.com/<YOUR-USERNAME>/academic-kickstart.git My_Website
b. cd My_Website
c. git submodule update --init --recursive
d. cp -av themes/academic/exampleSite/* .
e. hugo server
3. Edit your Markdown content in Jupyter Labs, Visual Studio Code, or Typora
4. Commit and push your changes to GitHub
5. Go to Netlify.com and select the repository to publish
44
Questions
@GeorgeCushen
GeorgeCushen.com
We’re hiring!

More Related Content

What's hot

A critical review of digital marketing
A critical review of digital marketingA critical review of digital marketing
A critical review of digital marketing
Deepak Verma
 
Omma metrics joe_laszio
Omma metrics joe_laszioOmma metrics joe_laszio
Omma metrics joe_laszio
MediaPost
 
Webinar: "Data Driven Marketing Research Techniques"
Webinar:  "Data Driven Marketing Research Techniques"Webinar:  "Data Driven Marketing Research Techniques"
Webinar: "Data Driven Marketing Research Techniques"
Good Rebels
 

What's hot (20)

Value creation in_e-business
Value creation in_e-businessValue creation in_e-business
Value creation in_e-business
 
How To Optimize Your Marketing Technology
How To Optimize Your Marketing TechnologyHow To Optimize Your Marketing Technology
How To Optimize Your Marketing Technology
 
Big Data Intelligence for Exceptional Engagement Performance
Big Data Intelligence for Exceptional Engagement PerformanceBig Data Intelligence for Exceptional Engagement Performance
Big Data Intelligence for Exceptional Engagement Performance
 
Literature review
Literature reviewLiterature review
Literature review
 
A Study on Customer Statisfication on Digital Marketing
A Study on Customer Statisfication on Digital MarketingA Study on Customer Statisfication on Digital Marketing
A Study on Customer Statisfication on Digital Marketing
 
Making the most of search insights, online and offline
Making the most of search insights, online and offlineMaking the most of search insights, online and offline
Making the most of search insights, online and offline
 
MBA Capstone Project Ideas
MBA Capstone Project IdeasMBA Capstone Project Ideas
MBA Capstone Project Ideas
 
Baidu the world's second largest search engine
Baidu the world's second largest search engineBaidu the world's second largest search engine
Baidu the world's second largest search engine
 
Running head marketing mix for docu signmarketing mix for
Running head marketing mix for docu signmarketing mix for Running head marketing mix for docu signmarketing mix for
Running head marketing mix for docu signmarketing mix for
 
European Marketing Agenda 2022
European Marketing Agenda 2022European Marketing Agenda 2022
European Marketing Agenda 2022
 
Study of Online Performance Marketing in China 2012: the Year in Review and l...
Study of Online Performance Marketing in China 2012: the Year in Review and l...Study of Online Performance Marketing in China 2012: the Year in Review and l...
Study of Online Performance Marketing in China 2012: the Year in Review and l...
 
A critical review of digital marketing
A critical review of digital marketingA critical review of digital marketing
A critical review of digital marketing
 
Omma metrics joe_laszio
Omma metrics joe_laszioOmma metrics joe_laszio
Omma metrics joe_laszio
 
Search Engine Marketing in China - Baidu v. Google
Search Engine Marketing in China - Baidu v. GoogleSearch Engine Marketing in China - Baidu v. Google
Search Engine Marketing in China - Baidu v. Google
 
How digital is impacting market strategy
How digital is impacting market strategyHow digital is impacting market strategy
How digital is impacting market strategy
 
HEC Digital Business. Digital Marketing
HEC Digital Business. Digital MarketingHEC Digital Business. Digital Marketing
HEC Digital Business. Digital Marketing
 
Interactive content Marketing in 2021
Interactive content Marketing in 2021Interactive content Marketing in 2021
Interactive content Marketing in 2021
 
Webinar: "Data Driven Marketing Research Techniques"
Webinar:  "Data Driven Marketing Research Techniques"Webinar:  "Data Driven Marketing Research Techniques"
Webinar: "Data Driven Marketing Research Techniques"
 
Digital Strategy Lecture 5 1920
Digital Strategy Lecture 5 1920Digital Strategy Lecture 5 1920
Digital Strategy Lecture 5 1920
 
GroupM POV Martech grows
GroupM POV Martech growsGroupM POV Martech grows
GroupM POV Martech grows
 

Similar to Knowledge Graphs --Enter--> The Hype Cycle (PyData 2019)

Getting started-jan-9-2018
Getting started-jan-9-2018Getting started-jan-9-2018
Getting started-jan-9-2018
Thinkful
 
Driving AI Competency - Key Considerations for B2B Marketers - Rosemary Brisco
Driving AI Competency - Key Considerations for B2B Marketers - Rosemary BriscoDriving AI Competency - Key Considerations for B2B Marketers - Rosemary Brisco
Driving AI Competency - Key Considerations for B2B Marketers - Rosemary Brisco
DigiMarCon - Digital Marketing, Media and Advertising Conferences & Exhibitions
 
Phx-techtalk
Phx-techtalkPhx-techtalk
Phx-techtalk
Thinkful
 
Why gpj is embracing digital
Why gpj is embracing digitalWhy gpj is embracing digital
Why gpj is embracing digital
Independant
 

Similar to Knowledge Graphs --Enter--> The Hype Cycle (PyData 2019) (20)

started-in-tech
started-in-techstarted-in-tech
started-in-tech
 
iSPORTiSTiCS investment opportunity 2020
iSPORTiSTiCS investment opportunity 2020iSPORTiSTiCS investment opportunity 2020
iSPORTiSTiCS investment opportunity 2020
 
Tech Job Conference: Software Engineer @Criteo
Tech Job Conference: Software Engineer @CriteoTech Job Conference: Software Engineer @Criteo
Tech Job Conference: Software Engineer @Criteo
 
Getting Started in Tech
Getting Started in TechGetting Started in Tech
Getting Started in Tech
 
Getting started-jan-9-2018
Getting started-jan-9-2018Getting started-jan-9-2018
Getting started-jan-9-2018
 
Driving AI Competency - Key Considerations for B2B Marketers - Rosemary Brisco
Driving AI Competency - Key Considerations for B2B Marketers - Rosemary BriscoDriving AI Competency - Key Considerations for B2B Marketers - Rosemary Brisco
Driving AI Competency - Key Considerations for B2B Marketers - Rosemary Brisco
 
Content Marketing - Link building through scalable strategies and processes
Content Marketing - Link building through scalable strategies and processesContent Marketing - Link building through scalable strategies and processes
Content Marketing - Link building through scalable strategies and processes
 
Knowledge Graphs Webinar- 11/7/2017
Knowledge Graphs Webinar- 11/7/2017Knowledge Graphs Webinar- 11/7/2017
Knowledge Graphs Webinar- 11/7/2017
 
Diversification of Digital, by LeapFrog Interactive
Diversification of Digital, by LeapFrog InteractiveDiversification of Digital, by LeapFrog Interactive
Diversification of Digital, by LeapFrog Interactive
 
PHXTECH830
PHXTECH830PHXTECH830
PHXTECH830
 
Phxtech830
Phxtech830Phxtech830
Phxtech830
 
Diversification of Digital Advertising
Diversification of Digital AdvertisingDiversification of Digital Advertising
Diversification of Digital Advertising
 
gtintpdx0816
gtintpdx0816gtintpdx0816
gtintpdx0816
 
Wall Street Mastermind Sector Spotlight - Technology (October 2023).pdf
Wall Street Mastermind Sector Spotlight - Technology (October 2023).pdfWall Street Mastermind Sector Spotlight - Technology (October 2023).pdf
Wall Street Mastermind Sector Spotlight - Technology (October 2023).pdf
 
Phx-techtalk
Phx-techtalkPhx-techtalk
Phx-techtalk
 
42DM Credentials: Fintech marketing
42DM Credentials: Fintech marketing42DM Credentials: Fintech marketing
42DM Credentials: Fintech marketing
 
Open Data and News Analytics Demo
Open Data and News Analytics DemoOpen Data and News Analytics Demo
Open Data and News Analytics Demo
 
Why gpj is embracing digital
Why gpj is embracing digitalWhy gpj is embracing digital
Why gpj is embracing digital
 
Accelerating the Packaging Design Process with Artificial Intelligence
Accelerating the Packaging Design Process with Artificial IntelligenceAccelerating the Packaging Design Process with Artificial Intelligence
Accelerating the Packaging Design Process with Artificial Intelligence
 
Social Media Presentation to SCAD
Social Media Presentation to SCADSocial Media Presentation to SCAD
Social Media Presentation to SCAD
 

Recently uploaded

Exploratory Data Analysis - Dilip S.pptx
Exploratory Data Analysis - Dilip S.pptxExploratory Data Analysis - Dilip S.pptx
Exploratory Data Analysis - Dilip S.pptx
DilipVasan
 
一比一原版麦考瑞大学毕业证成绩单如何办理
一比一原版麦考瑞大学毕业证成绩单如何办理一比一原版麦考瑞大学毕业证成绩单如何办理
一比一原版麦考瑞大学毕业证成绩单如何办理
cyebo
 
一比一原版阿德莱德大学毕业证成绩单如何办理
一比一原版阿德莱德大学毕业证成绩单如何办理一比一原版阿德莱德大学毕业证成绩单如何办理
一比一原版阿德莱德大学毕业证成绩单如何办理
pyhepag
 
Fuzzy Sets decision making under information of uncertainty
Fuzzy Sets decision making under information of uncertaintyFuzzy Sets decision making under information of uncertainty
Fuzzy Sets decision making under information of uncertainty
RafigAliyev2
 
Abortion pills in Dammam Saudi Arabia// +966572737505 // buy cytotec
Abortion pills in Dammam Saudi Arabia// +966572737505 // buy cytotecAbortion pills in Dammam Saudi Arabia// +966572737505 // buy cytotec
Abortion pills in Dammam Saudi Arabia// +966572737505 // buy cytotec
Abortion pills in Riyadh +966572737505 get cytotec
 
Machine Learning For Career Growth..pptx
Machine Learning For Career Growth..pptxMachine Learning For Career Growth..pptx
Machine Learning For Career Growth..pptx
benishzehra469
 
一比一原版纽卡斯尔大学毕业证成绩单如何办理
一比一原版纽卡斯尔大学毕业证成绩单如何办理一比一原版纽卡斯尔大学毕业证成绩单如何办理
一比一原版纽卡斯尔大学毕业证成绩单如何办理
cyebo
 

Recently uploaded (20)

Exploratory Data Analysis - Dilip S.pptx
Exploratory Data Analysis - Dilip S.pptxExploratory Data Analysis - Dilip S.pptx
Exploratory Data Analysis - Dilip S.pptx
 
Atlantic Grupa Case Study (Mintec Data AI)
Atlantic Grupa Case Study (Mintec Data AI)Atlantic Grupa Case Study (Mintec Data AI)
Atlantic Grupa Case Study (Mintec Data AI)
 
MALL CUSTOMER SEGMENTATION USING K-MEANS CLUSTERING.pptx
MALL CUSTOMER SEGMENTATION USING K-MEANS CLUSTERING.pptxMALL CUSTOMER SEGMENTATION USING K-MEANS CLUSTERING.pptx
MALL CUSTOMER SEGMENTATION USING K-MEANS CLUSTERING.pptx
 
Webinar One View, Multiple Systems No-Code Integration of Salesforce and ERPs
Webinar One View, Multiple Systems No-Code Integration of Salesforce and ERPsWebinar One View, Multiple Systems No-Code Integration of Salesforce and ERPs
Webinar One View, Multiple Systems No-Code Integration of Salesforce and ERPs
 
2024 Q1 Tableau User Group Leader Quarterly Call
2024 Q1 Tableau User Group Leader Quarterly Call2024 Q1 Tableau User Group Leader Quarterly Call
2024 Q1 Tableau User Group Leader Quarterly Call
 
how can i exchange pi coins for others currency like Bitcoin
how can i exchange pi coins for others currency like Bitcoinhow can i exchange pi coins for others currency like Bitcoin
how can i exchange pi coins for others currency like Bitcoin
 
How I opened a fake bank account and didn't go to prison
How I opened a fake bank account and didn't go to prisonHow I opened a fake bank account and didn't go to prison
How I opened a fake bank account and didn't go to prison
 
一比一原版麦考瑞大学毕业证成绩单如何办理
一比一原版麦考瑞大学毕业证成绩单如何办理一比一原版麦考瑞大学毕业证成绩单如何办理
一比一原版麦考瑞大学毕业证成绩单如何办理
 
一比一原版阿德莱德大学毕业证成绩单如何办理
一比一原版阿德莱德大学毕业证成绩单如何办理一比一原版阿德莱德大学毕业证成绩单如何办理
一比一原版阿德莱德大学毕业证成绩单如何办理
 
2024-05-14 - Tableau User Group - TC24 Hot Topics - Tableau Pulse and Einstei...
2024-05-14 - Tableau User Group - TC24 Hot Topics - Tableau Pulse and Einstei...2024-05-14 - Tableau User Group - TC24 Hot Topics - Tableau Pulse and Einstei...
2024-05-14 - Tableau User Group - TC24 Hot Topics - Tableau Pulse and Einstei...
 
How can I successfully sell my pi coins in Philippines?
How can I successfully sell my pi coins in Philippines?How can I successfully sell my pi coins in Philippines?
How can I successfully sell my pi coins in Philippines?
 
Supply chain analytics to combat the effects of Ukraine-Russia-conflict
Supply chain analytics to combat the effects of Ukraine-Russia-conflictSupply chain analytics to combat the effects of Ukraine-Russia-conflict
Supply chain analytics to combat the effects of Ukraine-Russia-conflict
 
Machine Learning for Accident Severity Prediction
Machine Learning for Accident Severity PredictionMachine Learning for Accident Severity Prediction
Machine Learning for Accident Severity Prediction
 
Jpolillo Amazon PPC - Bid Optimization Sample
Jpolillo Amazon PPC - Bid Optimization SampleJpolillo Amazon PPC - Bid Optimization Sample
Jpolillo Amazon PPC - Bid Optimization Sample
 
Artificial_General_Intelligence__storm_gen_article.pdf
Artificial_General_Intelligence__storm_gen_article.pdfArtificial_General_Intelligence__storm_gen_article.pdf
Artificial_General_Intelligence__storm_gen_article.pdf
 
Fuzzy Sets decision making under information of uncertainty
Fuzzy Sets decision making under information of uncertaintyFuzzy Sets decision making under information of uncertainty
Fuzzy Sets decision making under information of uncertainty
 
AI Imagen for data-storytelling Infographics.pdf
AI Imagen for data-storytelling Infographics.pdfAI Imagen for data-storytelling Infographics.pdf
AI Imagen for data-storytelling Infographics.pdf
 
Abortion pills in Dammam Saudi Arabia// +966572737505 // buy cytotec
Abortion pills in Dammam Saudi Arabia// +966572737505 // buy cytotecAbortion pills in Dammam Saudi Arabia// +966572737505 // buy cytotec
Abortion pills in Dammam Saudi Arabia// +966572737505 // buy cytotec
 
Machine Learning For Career Growth..pptx
Machine Learning For Career Growth..pptxMachine Learning For Career Growth..pptx
Machine Learning For Career Growth..pptx
 
一比一原版纽卡斯尔大学毕业证成绩单如何办理
一比一原版纽卡斯尔大学毕业证成绩单如何办理一比一原版纽卡斯尔大学毕业证成绩单如何办理
一比一原版纽卡斯尔大学毕业证成绩单如何办理
 

Knowledge Graphs --Enter--> The Hype Cycle (PyData 2019)

  • 1. Knowledge Graphs --Enter--> The Hype Cycle @GeorgeCushen PyData London 2019
  • 3.
  • 4. 4 The Hype Cycle Proof Mr Porter Eminem P Diddy DJ Khaled Notorious B.I.G. DJ Khaled Image: Meghan Roberts Rihanna collaborated_with wants_to_collaborate_with
  • 7. Farfetch at a glance 7 > 3,000* Employees across 13 countries $1.4 Billion* Gross Merchandise Value > 3,000* Brands available for consumers to shop > 1,000** Luxury sellers on the Marketplace $601** AOV on Marketplace > 2.9 Million* Orders on Marketplace 1.7 million** Active Marketplace consumers $307 Billion Size of personal luxury good industry (Bain estimates) *Correct for full year 2018 **As at Q1 2019 15** Marketplace language sites
  • 8. 8 What is this graph thing? “Hey, I’ve got this lit bar graph visualization for you! It’s 🔥🔥🔥!”
  • 9. A New Perspective: Emphasising Relationships ● Businesses and their products/services are all about Entities and Relationships ● Examples of entities and relationships in industry: Farfetch Consumer searches Product with Terms Amazon Seller sells Product to Consumer Uber Driver provides Trip to Rider Facebook Person shares Status with Friend ● How can we represent, analyse, and visualise this kind of data?
  • 10. 10 What is a knowledge graph? A knowledge graph can describe ● a collection of nodes (entities) representing business and fashion entities has_term ● and with labeled relationships between the nodes Product D&G tote bag Attribute Leopard Print Attribute Leopard Spots Attribute Animal Print Properties: Language = “EN” ● each containing information (properties) Properties: ProductID = 123
  • 12.
  • 15.
  • 16. 16 Discovering the pearl DELFINA DELETTREZ 'Trillion' earring
  • 17. 17 Discovering the diamond JIMMY CHOO Diamond sneakers
  • 18. 18 Generic vs Domain Specific Knowledge Graphs Generic vs Domain Specific Generic Domain Specific: Fashion Products Products Brands Categories Editorials ... Attributes Synonyms Colours Materials Concepts ... Customers Orders Payments Promotions Reviews ...
  • 19. 19 Example Use Cases Free Text Search Increase product discovery with synonyms and rich attributes for material, occasion (e.g. skiing), etc. Semantic Search Increase product discovery based by using graph to understand consumer’s intent Ranking Leverage rich product connections to increase relevance on listing pages Recommendations Increase relevance based on richer product attributes and deep graph relationships
  • 20. 20 Building the fashion knowledge graph Search Recommendations ... F-Graph (Associates taxonomy entities with business entities) AI Knowledge cleaning Entity resolution Schema mapping Applications Taxonomy & Graph Construction Knowledge Collection Expert Knowledge Data-Driven Insights
  • 21. Skinny 21 Universal Fashion Taxonomy Fashion Taxonomy Synonyms Descriptive attributes Brand DNA Materials ColoursTrends Editorial, emotive, seasonal concepts Textile Cotton Denim Product 2 Swedish Design Acne Glastonbury Festival Summer Product 1 PrintsSnake Blue Light Blue
  • 23. Techniques 📷 CV/DL + 📖 NLP + ✔️ Conflation + 👙 Inference + 👥 Crowdsourcing 23
  • 24. 24 Richer Product Data Existing catalog External Enrichment Internal Enrichment
  • 25. 25 Richer Product Data Existing catalog data AI predicts richer and more diverse attributes The fashion knowledge graph, F-Graph, connects and enriches entities Qualityof ProductDNA
  • 26. 26 Building a simple graph in Python import networkx as nx import matplotlib.pyplot as plt graph = nx.DiGraph() graph.add_node(0, name='Product A'), graph.add_node(1), graph.add_node(2), graph.add_node(3), graph.add_node(4) graph.add_edge(0, 1, weight=0.75), graph.add_edge(0, 4),graph.add_edge(1, 2), graph.add_edge(0, 2),graph.add_edge(1, 4), graph.add_edge(1, 3), graph.add_edge(3, 2), graph.add_edge(3,1), graph.add_edge(4,3) nx.draw(graph, with_labels=True, font_weight='bold') plt.show() $ pipenv install networkx matplotlib
  • 27. 27 Graph databases ● Neo4j ○ Packages: neo4j, py2neo ● AWS Neptune ○ Package: gremlinpython ● Azure Cosmos ○ Package: gremlinpython
  • 29. 29
  • 30. 30
  • 31. 31
  • 32. 32 Why use Pyenv + Pipenv for your projects? Pipenv ● Officially recommended way of managing project dependencies ● No requirements.txt and managing virtualenvs ● Instead a Pipfile in your project that performs this stuff automatically $ pip install -U pipenv # Install Pipenv $ cd my_project # Go to your project $ pipenv install # Initialize Pipenv $ pipenv install neo4j # Install a package $ pipenv shell # Enter virtual env $ python my_script.py # Run a script Image: xkcd
  • 33. 33 Communicating a graph Product Managers “How can we improve the customer experience?” “How much can the knowledge graph impact GMV?” Data Scientists “Wow, looks like a NN, hold my Pandas 🐼🐼🐼, I’m onboard!!” Backend Engineers “Why do we need a graph?” “Which graph database meets the requirements?” Data Engineers “Is your Airflow dizzy? It’s traversing through cyclic connections?!”
  • 34. 34 Where do I see most value with the knowledge graph? ● Improving customer experience such as by understanding consumer intent in search queries ● Connecting further business entities (e.g. content) for hyper-personalisation ● Deriving new knowledge via graph analysis and graph-based AI ● Enabling new, innovative applications
  • 37. 37 Why use a knowledge graph? ● Have naturally highly connected-data ● Derive new insights with Graph Analysis & Graph-based AI ● Enable stakeholders to easily visualise relationships and make informed decisions ● Flexible schema to facilitate evolution to expand business entities ● Optimized for storing and querying graphs ○ Significantly faster than SQL databases for querying relationships ○ Relationships are a fundamental structure, so following relationships is a single lookup, making this operation blazingly fast
  • 40. The Tool to Create Professional Websites From Markdown, Jupyter, and RStudio https://github.com/gcushen/hugo-academic 40 100,000+ websites. 2,000+ GitHub Stars. 80+ Contributors. 40+ Widgets, Themes, and Languages. Used by academics and labs at Stanford, MIT, Cambridge. Featured on GitHub’s Blog.
  • 41. 41
  • 42. 42 Install Hugo as Prerequisite ● Windows ○ choco install hugo-extended -confirm ● Mac ○ brew update && brew install hugo ● Linux ○ sudo snap install hugo --channel=extended/stable
  • 43. 43 Build your site with Academic 1. Fork https://github.com/sourcethemes/academic-kickstart 2. Setup and view your site locally: a. git clone https://github.com/<YOUR-USERNAME>/academic-kickstart.git My_Website b. cd My_Website c. git submodule update --init --recursive d. cp -av themes/academic/exampleSite/* . e. hugo server 3. Edit your Markdown content in Jupyter Labs, Visual Studio Code, or Typora 4. Commit and push your changes to GitHub 5. Go to Netlify.com and select the repository to publish