SlideShare ist ein Scribd-Unternehmen logo
1 von 16
|
kernixdigital factory + data lab
Flexible recommender systems
based on graphs
|
KERNIX
45
co-workers
500projects
2co-founders
3,5M€ revenue
15years
experience
10books
published
Digital factory Data lab
CO-FOUNDERS
Fabrice Métayer and François-Xavier
Bois, two EPITA engineers, gathered
their complementary profiles to create
Kernix in 2001.
ABOUT KERNIX
Kernix’s core business consists in a
digital factory and a data lab.
This double skill allows us to
accompany our clients from upstream
phases (consulting, study, POC) to
downstream phases (industrialization
by production teams).
|
3
DATA LAB
Clients Collaborations
EXPERTISE
Data Pipelines
Cop21
TerraRush
Predictive maintenance
ERDF
Data Vizualisation
SolarImpulse
Recommender systems
PriceMinister
WikiDistrict
Clickalto
HobbyStreet
Marketing Automation
Performics
RadiumOne
Open Data
Accessible.net
|
• Graph database
– data stored as nodes
• label : “type” of data stored in the node
• properties : collection of information describing
the node
– nodes are linked together by edges
• type : describes the nature of the relation
– query language : allows to perform graph traversals
• Why graph-oriented recommender
systems ?
– gather heterogeneous data in the same structure
– explicitly take advantage of relationships
– "meaningful" for humans
– easy implementation
– fast execution (no training)
GRAPH-ORIENTED RECOMMENDER SYSTEM
|
USE CASE 1 : HOBBYSTREET
|
Facilitate connections between craftsmen and private individuals
• Craftsmen : propose workshops (different categories, dates, prices)
• Individuals : follow workshops/categories, sign up at workshops
• Hobbystreet : handle registrations, plannings, payments, propose customized suggestions
CONTEXT
|
DATA STRUCTURE
User
name
city
Carftman
name
activity
Workshop
name
description
GPS coordinates
Session
date, time
price
status
stock
Category
name
activity
follows
proposes
related to instance of
participates
|
SUGGESTIONS : OVERALL STRATEGY
Category
User
Workshop 1
Category 1
Category 2
Workshop 2
Workshop 3
Workshop 4
Similar descriptions
User
Workshop 1
Workshop 2
Workshop 3
Workshop 4
Workshop 5
Workshop 6
from LSA
Similar users
User 1
Workshop 1
Workshop 2
Workshop 3
User 2
User 3
Workshop 4
Workshop 5
Workshop 6
Usim
|
USE CASE 2 : KONBINI
|
Context
“... multi format media company
producing its own mix of culture, art
and news content. It promotes
online journalism, advocating an
emphasis on pop culture and a
commitment to develop local
emerging talents.”
“... became one of the first
websites to put Social Media
platforms at the heart of their
strategy.”Issue: ~90% bounce rate (users going back after viewing a
page)
Solution: Recommend interesting articles on the visited
pages will help user experience.
|
Entities
French posts [693]
Authors [56]
Categories [534] Mexican posts [149]
English posts [417]
Examples of node properties
blog_id: 9
post_id: 217628
post_date: 20151007
slug: rihanna-thinks-rachel...
boost: 0
viewed_count: 0
facebook_count: 148
twitter_count: 0
Multiple web sites [US,
England, Mexic, France]
US posts [364]
|
Recommendations principles
For each posts, we will recommend a list of other posts
based on relations shared with the initial post:
- semantic similarity of the contents [LSA]
- number of common categories
- number of common authors
And also on their own properties:
- the freshness
- social counts
- manual boost
Once the graph constructed, these recommendations
can be obtained thanks to a single Cypher query.
|
Conclusion and outlook
|
Stacks and Workflows
Konbini web siteHobbystreet web site
POST content GET recommendations POST content
Daily cached
recommendadions
GET recommendations
Live recommendation for dynamic
interactions
Cached recommendation for high
availability needs
|
Improve semantic analysis:
• exploit similarity of short descriptions (tweets, comments, …). PhD thesis on the subject.
Assess recommendation quality:
• A/B testing but Needs production deployment.
• Offline testing ? No real assessment on the impact of the recommendations performed.
• Rating of pool of testers ?
Outlook
THANK YOU !
Kernix Data Lab
+33 (0)1 53 98 73 43
lab@kernix.com

Weitere ähnliche Inhalte

Was ist angesagt?

BDE SC6-hang out - technology part-SWC - Martin
BDE SC6-hang out - technology part-SWC - MartinBDE SC6-hang out - technology part-SWC - Martin
BDE SC6-hang out - technology part-SWC - MartinBigData_Europe
 
SC7 Workshop 2: Demo of the BigDataEurope pilot for Secure Societies
SC7 Workshop 2: Demo of the BigDataEurope pilot for Secure SocietiesSC7 Workshop 2: Demo of the BigDataEurope pilot for Secure Societies
SC7 Workshop 2: Demo of the BigDataEurope pilot for Secure SocietiesBigData_Europe
 
SC7 Hangout 3: The BDE Secure Societies Pilot
SC7 Hangout 3: The BDE Secure Societies PilotSC7 Hangout 3: The BDE Secure Societies Pilot
SC7 Hangout 3: The BDE Secure Societies PilotBigData_Europe
 
Making the most of Open Data
Making the most of Open DataMaking the most of Open Data
Making the most of Open DataLouise Corti
 
Why should I care about open data?
Why should I care about open data?Why should I care about open data?
Why should I care about open data?Andy Dickinson
 
Wikidata: A New Way to Disseminate Structured Data
Wikidata: A New Way to Disseminate Structured DataWikidata: A New Way to Disseminate Structured Data
Wikidata: A New Way to Disseminate Structured DataLuca Martinelli
 
IPTC Semantic Web Working Group Autumn 2013
IPTC Semantic Web Working Group Autumn 2013IPTC Semantic Web Working Group Autumn 2013
IPTC Semantic Web Working Group Autumn 2013Stuart Myles
 
Local Open Data. Presentation for Cambridgeshire Insight
Local Open Data. Presentation for Cambridgeshire InsightLocal Open Data. Presentation for Cambridgeshire Insight
Local Open Data. Presentation for Cambridgeshire InsightMark Braggins
 
SC7 Workshop 3: Big Data Value -Big Data and SC7-
SC7 Workshop 3: Big Data Value -Big Data and SC7-SC7 Workshop 3: Big Data Value -Big Data and SC7-
SC7 Workshop 3: Big Data Value -Big Data and SC7-BigData_Europe
 
Why is Open Data Important? - Michael Soper, Cambridgeshire County Council
Why is Open Data Important? - Michael Soper,Cambridgeshire County CouncilWhy is Open Data Important? - Michael Soper,Cambridgeshire County Council
Why is Open Data Important? - Michael Soper, Cambridgeshire County CouncilCambridgeshireInsight
 
Open data : from Insight to Visualisation with Google BigQuery and Carto.com ...
Open data : from Insight to Visualisation with Google BigQuery and Carto.com ...Open data : from Insight to Visualisation with Google BigQuery and Carto.com ...
Open data : from Insight to Visualisation with Google BigQuery and Carto.com ...Big Data Spain
 
Discovering Related Data Sources in Data Portals
Discovering Related Data Sources in Data PortalsDiscovering Related Data Sources in Data Portals
Discovering Related Data Sources in Data PortalsPeter Haase
 
The Open Journey - Opengov Through Open Source and Open Data
The Open Journey - Opengov Through Open Source and Open DataThe Open Journey - Opengov Through Open Source and Open Data
The Open Journey - Opengov Through Open Source and Open DataClaire Foulquier-Gazagnes
 
Let's downscale the semantic web !
Let's downscale the semantic web !Let's downscale the semantic web !
Let's downscale the semantic web !Christophe Guéret
 
IPTC New Taxonomies Ideas
IPTC New Taxonomies IdeasIPTC New Taxonomies Ideas
IPTC New Taxonomies IdeasStuart Myles
 
New ways to communicate in science: perspectives from biodiversity research
New ways to communicate in science: perspectives from biodiversity researchNew ways to communicate in science: perspectives from biodiversity research
New ways to communicate in science: perspectives from biodiversity researchVince Smith
 
SC7 Workshop 3: Workshop Presentation
SC7 Workshop 3: Workshop PresentationSC7 Workshop 3: Workshop Presentation
SC7 Workshop 3: Workshop PresentationBigData_Europe
 
Linking the 20th century paper history to the sum of all knowledge
Linking the 20th century paper history to the sum of all knowledgeLinking the 20th century paper history to the sum of all knowledge
Linking the 20th century paper history to the sum of all knowledgeJoachim Neubert
 

Was ist angesagt? (20)

BDE SC6-hang out - technology part-SWC - Martin
BDE SC6-hang out - technology part-SWC - MartinBDE SC6-hang out - technology part-SWC - Martin
BDE SC6-hang out - technology part-SWC - Martin
 
SC7 Workshop 2: Demo of the BigDataEurope pilot for Secure Societies
SC7 Workshop 2: Demo of the BigDataEurope pilot for Secure SocietiesSC7 Workshop 2: Demo of the BigDataEurope pilot for Secure Societies
SC7 Workshop 2: Demo of the BigDataEurope pilot for Secure Societies
 
SC7 Hangout 3: The BDE Secure Societies Pilot
SC7 Hangout 3: The BDE Secure Societies PilotSC7 Hangout 3: The BDE Secure Societies Pilot
SC7 Hangout 3: The BDE Secure Societies Pilot
 
Making the most of Open Data
Making the most of Open DataMaking the most of Open Data
Making the most of Open Data
 
Why should I care about open data?
Why should I care about open data?Why should I care about open data?
Why should I care about open data?
 
Wikidata: A New Way to Disseminate Structured Data
Wikidata: A New Way to Disseminate Structured DataWikidata: A New Way to Disseminate Structured Data
Wikidata: A New Way to Disseminate Structured Data
 
IPTC Semantic Web Working Group Autumn 2013
IPTC Semantic Web Working Group Autumn 2013IPTC Semantic Web Working Group Autumn 2013
IPTC Semantic Web Working Group Autumn 2013
 
Local Open Data. Presentation for Cambridgeshire Insight
Local Open Data. Presentation for Cambridgeshire InsightLocal Open Data. Presentation for Cambridgeshire Insight
Local Open Data. Presentation for Cambridgeshire Insight
 
SC7 Workshop 3: Big Data Value -Big Data and SC7-
SC7 Workshop 3: Big Data Value -Big Data and SC7-SC7 Workshop 3: Big Data Value -Big Data and SC7-
SC7 Workshop 3: Big Data Value -Big Data and SC7-
 
Why is Open Data Important? - Michael Soper, Cambridgeshire County Council
Why is Open Data Important? - Michael Soper,Cambridgeshire County CouncilWhy is Open Data Important? - Michael Soper,Cambridgeshire County Council
Why is Open Data Important? - Michael Soper, Cambridgeshire County Council
 
Open data : from Insight to Visualisation with Google BigQuery and Carto.com ...
Open data : from Insight to Visualisation with Google BigQuery and Carto.com ...Open data : from Insight to Visualisation with Google BigQuery and Carto.com ...
Open data : from Insight to Visualisation with Google BigQuery and Carto.com ...
 
Discovering Related Data Sources in Data Portals
Discovering Related Data Sources in Data PortalsDiscovering Related Data Sources in Data Portals
Discovering Related Data Sources in Data Portals
 
The Open Journey - Opengov Through Open Source and Open Data
The Open Journey - Opengov Through Open Source and Open DataThe Open Journey - Opengov Through Open Source and Open Data
The Open Journey - Opengov Through Open Source and Open Data
 
Let's downscale the semantic web !
Let's downscale the semantic web !Let's downscale the semantic web !
Let's downscale the semantic web !
 
IPTC New Taxonomies Ideas
IPTC New Taxonomies IdeasIPTC New Taxonomies Ideas
IPTC New Taxonomies Ideas
 
Edison madrid 15032017
Edison madrid 15032017Edison madrid 15032017
Edison madrid 15032017
 
New ways to communicate in science: perspectives from biodiversity research
New ways to communicate in science: perspectives from biodiversity researchNew ways to communicate in science: perspectives from biodiversity research
New ways to communicate in science: perspectives from biodiversity research
 
Linked Data
Linked DataLinked Data
Linked Data
 
SC7 Workshop 3: Workshop Presentation
SC7 Workshop 3: Workshop PresentationSC7 Workshop 3: Workshop Presentation
SC7 Workshop 3: Workshop Presentation
 
Linking the 20th century paper history to the sum of all knowledge
Linking the 20th century paper history to the sum of all knowledgeLinking the 20th century paper history to the sum of all knowledge
Linking the 20th century paper history to the sum of all knowledge
 

Andere mochten auch

Recommendation @Deezer
Recommendation @DeezerRecommendation @Deezer
Recommendation @Deezerrecsysfr
 
Preference Elicitation in Mangaki: Is Your Taste Kinda Weird?
Preference Elicitation in Mangaki: Is Your Taste Kinda Weird?Preference Elicitation in Mangaki: Is Your Taste Kinda Weird?
Preference Elicitation in Mangaki: Is Your Taste Kinda Weird?recsysfr
 
RecsysFR: Criteo presentation
RecsysFR: Criteo presentationRecsysFR: Criteo presentation
RecsysFR: Criteo presentationrecsysfr
 
What can bring library metadata to the web? Trust, links and love
What can bring library metadata to the web? Trust, links and loveWhat can bring library metadata to the web? Trust, links and love
What can bring library metadata to the web? Trust, links and loverecsysfr
 
Recommendation @ Meetic
Recommendation @ MeeticRecommendation @ Meetic
Recommendation @ Meeticrecsysfr
 
Using Neural Networks to predict user ratings
Using Neural Networks to predict user ratingsUsing Neural Networks to predict user ratings
Using Neural Networks to predict user ratingsrecsysfr
 
Dictionary Learning for Massive Matrix Factorization
Dictionary Learning for Massive Matrix FactorizationDictionary Learning for Massive Matrix Factorization
Dictionary Learning for Massive Matrix Factorizationrecsysfr
 
Meta-Prod2Vec: Simple Product Embeddings with Side-Information
Meta-Prod2Vec: Simple Product Embeddings with Side-InformationMeta-Prod2Vec: Simple Product Embeddings with Side-Information
Meta-Prod2Vec: Simple Product Embeddings with Side-Informationrecsysfr
 
Pulpix - Video Recommendation at Scale
Pulpix - Video Recommendation at ScalePulpix - Video Recommendation at Scale
Pulpix - Video Recommendation at Scalerecsysfr
 
Sequential Learning in the Position-Based Model
Sequential Learning in the Position-Based ModelSequential Learning in the Position-Based Model
Sequential Learning in the Position-Based Modelrecsysfr
 
CONTENT2VEC: a Joint Architecture to use Product Image and Text for the task ...
CONTENT2VEC: a Joint Architecture to use Product Image and Text for the task ...CONTENT2VEC: a Joint Architecture to use Product Image and Text for the task ...
CONTENT2VEC: a Joint Architecture to use Product Image and Text for the task ...recsysfr
 
Deezer - Big data as a streaming service
Deezer - Big data as a streaming serviceDeezer - Big data as a streaming service
Deezer - Big data as a streaming serviceJulie Knibbe
 
Tailor-made personalization and recommendation - Sailendra
Tailor-made personalization and recommendation - SailendraTailor-made personalization and recommendation - Sailendra
Tailor-made personalization and recommendation - Sailendrarecsysfr
 
Story of the algorithms behind Deezer Flow
Story of the algorithms behind Deezer FlowStory of the algorithms behind Deezer Flow
Story of the algorithms behind Deezer Flowrecsysfr
 
Recommendation @ PriceMinister-Rakuten - Road to personalization
Recommendation @ PriceMinister-Rakuten - Road to personalizationRecommendation @ PriceMinister-Rakuten - Road to personalization
Recommendation @ PriceMinister-Rakuten - Road to personalizationrecsysfr
 
Rakuten Institute of Technology Paris
Rakuten Institute of Technology ParisRakuten Institute of Technology Paris
Rakuten Institute of Technology Parisrecsysfr
 
New tools from the bandit literature to improve A/B Testing
New tools from the bandit literature to improve A/B TestingNew tools from the bandit literature to improve A/B Testing
New tools from the bandit literature to improve A/B Testingrecsysfr
 
Analysing Large Citation Network
Analysing Large Citation NetworkAnalysing Large Citation Network
Analysing Large Citation NetworkMilad Alshomary
 
Recommender systems
Recommender systemsRecommender systems
Recommender systemsrecsysfr
 
Data-Driven Recommender Systems
Data-Driven Recommender SystemsData-Driven Recommender Systems
Data-Driven Recommender Systemsrecsysfr
 

Andere mochten auch (20)

Recommendation @Deezer
Recommendation @DeezerRecommendation @Deezer
Recommendation @Deezer
 
Preference Elicitation in Mangaki: Is Your Taste Kinda Weird?
Preference Elicitation in Mangaki: Is Your Taste Kinda Weird?Preference Elicitation in Mangaki: Is Your Taste Kinda Weird?
Preference Elicitation in Mangaki: Is Your Taste Kinda Weird?
 
RecsysFR: Criteo presentation
RecsysFR: Criteo presentationRecsysFR: Criteo presentation
RecsysFR: Criteo presentation
 
What can bring library metadata to the web? Trust, links and love
What can bring library metadata to the web? Trust, links and loveWhat can bring library metadata to the web? Trust, links and love
What can bring library metadata to the web? Trust, links and love
 
Recommendation @ Meetic
Recommendation @ MeeticRecommendation @ Meetic
Recommendation @ Meetic
 
Using Neural Networks to predict user ratings
Using Neural Networks to predict user ratingsUsing Neural Networks to predict user ratings
Using Neural Networks to predict user ratings
 
Dictionary Learning for Massive Matrix Factorization
Dictionary Learning for Massive Matrix FactorizationDictionary Learning for Massive Matrix Factorization
Dictionary Learning for Massive Matrix Factorization
 
Meta-Prod2Vec: Simple Product Embeddings with Side-Information
Meta-Prod2Vec: Simple Product Embeddings with Side-InformationMeta-Prod2Vec: Simple Product Embeddings with Side-Information
Meta-Prod2Vec: Simple Product Embeddings with Side-Information
 
Pulpix - Video Recommendation at Scale
Pulpix - Video Recommendation at ScalePulpix - Video Recommendation at Scale
Pulpix - Video Recommendation at Scale
 
Sequential Learning in the Position-Based Model
Sequential Learning in the Position-Based ModelSequential Learning in the Position-Based Model
Sequential Learning in the Position-Based Model
 
CONTENT2VEC: a Joint Architecture to use Product Image and Text for the task ...
CONTENT2VEC: a Joint Architecture to use Product Image and Text for the task ...CONTENT2VEC: a Joint Architecture to use Product Image and Text for the task ...
CONTENT2VEC: a Joint Architecture to use Product Image and Text for the task ...
 
Deezer - Big data as a streaming service
Deezer - Big data as a streaming serviceDeezer - Big data as a streaming service
Deezer - Big data as a streaming service
 
Tailor-made personalization and recommendation - Sailendra
Tailor-made personalization and recommendation - SailendraTailor-made personalization and recommendation - Sailendra
Tailor-made personalization and recommendation - Sailendra
 
Story of the algorithms behind Deezer Flow
Story of the algorithms behind Deezer FlowStory of the algorithms behind Deezer Flow
Story of the algorithms behind Deezer Flow
 
Recommendation @ PriceMinister-Rakuten - Road to personalization
Recommendation @ PriceMinister-Rakuten - Road to personalizationRecommendation @ PriceMinister-Rakuten - Road to personalization
Recommendation @ PriceMinister-Rakuten - Road to personalization
 
Rakuten Institute of Technology Paris
Rakuten Institute of Technology ParisRakuten Institute of Technology Paris
Rakuten Institute of Technology Paris
 
New tools from the bandit literature to improve A/B Testing
New tools from the bandit literature to improve A/B TestingNew tools from the bandit literature to improve A/B Testing
New tools from the bandit literature to improve A/B Testing
 
Analysing Large Citation Network
Analysing Large Citation NetworkAnalysing Large Citation Network
Analysing Large Citation Network
 
Recommender systems
Recommender systemsRecommender systems
Recommender systems
 
Data-Driven Recommender Systems
Data-Driven Recommender SystemsData-Driven Recommender Systems
Data-Driven Recommender Systems
 

Ähnlich wie Flexible recommender systems based on graphs

Brussels Capital of Data Science
Brussels Capital of Data ScienceBrussels Capital of Data Science
Brussels Capital of Data ScienceDigitYser
 
Values & Vision - Cloud Sandboxes for BIG Earth Sciences
Values & Vision - Cloud Sandboxes for BIG Earth SciencesValues & Vision - Cloud Sandboxes for BIG Earth Sciences
Values & Vision - Cloud Sandboxes for BIG Earth Sciencesterradue
 
Digital Personalisation: Growing Revenue Faster with Digital Experiences That...
Digital Personalisation: Growing Revenue Faster with Digital Experiences That...Digital Personalisation: Growing Revenue Faster with Digital Experiences That...
Digital Personalisation: Growing Revenue Faster with Digital Experiences That...DRI - Discovery/Reinvention/Integration/
 
20191210 NDLI KEDL2019 Building the dutch digital heritage network
20191210 NDLI KEDL2019 Building the dutch digital heritage network20191210 NDLI KEDL2019 Building the dutch digital heritage network
20191210 NDLI KEDL2019 Building the dutch digital heritage networkEnno Meijers
 
Neo4j GraphTalks - Einführung in Graphdatenbanken
Neo4j GraphTalks - Einführung in GraphdatenbankenNeo4j GraphTalks - Einführung in Graphdatenbanken
Neo4j GraphTalks - Einführung in GraphdatenbankenNeo4j
 
Setting the Record Straight: Drupal as an Enterprise Web Content Management S...
Setting the Record Straight: Drupal as an Enterprise Web Content Management S...Setting the Record Straight: Drupal as an Enterprise Web Content Management S...
Setting the Record Straight: Drupal as an Enterprise Web Content Management S...Acquia
 
GraphTalks Hamburg - Einführung in Graphdatenbanken
GraphTalks Hamburg - Einführung in GraphdatenbankenGraphTalks Hamburg - Einführung in Graphdatenbanken
GraphTalks Hamburg - Einführung in GraphdatenbankenNeo4j
 
Great Expectations – The Sequel: Updates from the digital standards frontlines
Great Expectations – The Sequel: Updates from the digital standards frontlinesGreat Expectations – The Sequel: Updates from the digital standards frontlines
Great Expectations – The Sequel: Updates from the digital standards frontlinesBookNet Canada
 
From Essence to Assets. Making sense of an audiovisual archive
From Essence to Assets. Making sense of an audiovisual archiveFrom Essence to Assets. Making sense of an audiovisual archive
From Essence to Assets. Making sense of an audiovisual archiveBrecht Declercq
 
Neo4j PartnerDay Amsterdam 2017
Neo4j PartnerDay Amsterdam 2017Neo4j PartnerDay Amsterdam 2017
Neo4j PartnerDay Amsterdam 2017Neo4j
 
Introduction to Neo4j
Introduction to Neo4jIntroduction to Neo4j
Introduction to Neo4jNeo4j
 
Systems and Services: Adding Value For Research Data Assets
Systems and Services: Adding Value For Research Data AssetsSystems and Services: Adding Value For Research Data Assets
Systems and Services: Adding Value For Research Data AssetsLIBER Europe
 
CLARIAH Toogdag 2018: A distributed network of digital heritage information
CLARIAH Toogdag 2018: A distributed network of digital heritage informationCLARIAH Toogdag 2018: A distributed network of digital heritage information
CLARIAH Toogdag 2018: A distributed network of digital heritage informationEnno Meijers
 
OLX Group presentation for AWS Redshift meetup in London, 5 July 2017
OLX Group presentation for AWS Redshift meetup in London, 5 July 2017OLX Group presentation for AWS Redshift meetup in London, 5 July 2017
OLX Group presentation for AWS Redshift meetup in London, 5 July 2017Dobo Radichkov
 
Get In Spring Corporate Services
Get In Spring Corporate ServicesGet In Spring Corporate Services
Get In Spring Corporate ServicesPavlos Nomikos
 

Ähnlich wie Flexible recommender systems based on graphs (20)

Brussels Capital of Data Science
Brussels Capital of Data ScienceBrussels Capital of Data Science
Brussels Capital of Data Science
 
Values & Vision - Cloud Sandboxes for BIG Earth Sciences
Values & Vision - Cloud Sandboxes for BIG Earth SciencesValues & Vision - Cloud Sandboxes for BIG Earth Sciences
Values & Vision - Cloud Sandboxes for BIG Earth Sciences
 
Husqvarna Group
Husqvarna GroupHusqvarna Group
Husqvarna Group
 
Patrick Consorti for ISSIP
Patrick Consorti for ISSIPPatrick Consorti for ISSIP
Patrick Consorti for ISSIP
 
Membership Intro Presentation
Membership Intro PresentationMembership Intro Presentation
Membership Intro Presentation
 
Digital Personalisation: Growing Revenue Faster with Digital Experiences That...
Digital Personalisation: Growing Revenue Faster with Digital Experiences That...Digital Personalisation: Growing Revenue Faster with Digital Experiences That...
Digital Personalisation: Growing Revenue Faster with Digital Experiences That...
 
20191210 NDLI KEDL2019 Building the dutch digital heritage network
20191210 NDLI KEDL2019 Building the dutch digital heritage network20191210 NDLI KEDL2019 Building the dutch digital heritage network
20191210 NDLI KEDL2019 Building the dutch digital heritage network
 
5. open innov ict-platf
5. open innov ict-platf5. open innov ict-platf
5. open innov ict-platf
 
Neo4j GraphTalks - Einführung in Graphdatenbanken
Neo4j GraphTalks - Einführung in GraphdatenbankenNeo4j GraphTalks - Einführung in Graphdatenbanken
Neo4j GraphTalks - Einführung in Graphdatenbanken
 
Setting the Record Straight: Drupal as an Enterprise Web Content Management S...
Setting the Record Straight: Drupal as an Enterprise Web Content Management S...Setting the Record Straight: Drupal as an Enterprise Web Content Management S...
Setting the Record Straight: Drupal as an Enterprise Web Content Management S...
 
GraphTalks Hamburg - Einführung in Graphdatenbanken
GraphTalks Hamburg - Einführung in GraphdatenbankenGraphTalks Hamburg - Einführung in Graphdatenbanken
GraphTalks Hamburg - Einführung in Graphdatenbanken
 
Great Expectations – The Sequel: Updates from the digital standards frontlines
Great Expectations – The Sequel: Updates from the digital standards frontlinesGreat Expectations – The Sequel: Updates from the digital standards frontlines
Great Expectations – The Sequel: Updates from the digital standards frontlines
 
From Essence to Assets. Making sense of an audiovisual archive
From Essence to Assets. Making sense of an audiovisual archiveFrom Essence to Assets. Making sense of an audiovisual archive
From Essence to Assets. Making sense of an audiovisual archive
 
Neo4j PartnerDay Amsterdam 2017
Neo4j PartnerDay Amsterdam 2017Neo4j PartnerDay Amsterdam 2017
Neo4j PartnerDay Amsterdam 2017
 
Introduction to Neo4j
Introduction to Neo4jIntroduction to Neo4j
Introduction to Neo4j
 
DLCS
DLCSDLCS
DLCS
 
Systems and Services: Adding Value For Research Data Assets
Systems and Services: Adding Value For Research Data AssetsSystems and Services: Adding Value For Research Data Assets
Systems and Services: Adding Value For Research Data Assets
 
CLARIAH Toogdag 2018: A distributed network of digital heritage information
CLARIAH Toogdag 2018: A distributed network of digital heritage informationCLARIAH Toogdag 2018: A distributed network of digital heritage information
CLARIAH Toogdag 2018: A distributed network of digital heritage information
 
OLX Group presentation for AWS Redshift meetup in London, 5 July 2017
OLX Group presentation for AWS Redshift meetup in London, 5 July 2017OLX Group presentation for AWS Redshift meetup in London, 5 July 2017
OLX Group presentation for AWS Redshift meetup in London, 5 July 2017
 
Get In Spring Corporate Services
Get In Spring Corporate ServicesGet In Spring Corporate Services
Get In Spring Corporate Services
 

Mehr von recsysfr

Multi Task DPP for Basket Completion by Romain WARLOP, Fifty Five
Multi Task DPP for Basket Completion by Romain WARLOP, Fifty FiveMulti Task DPP for Basket Completion by Romain WARLOP, Fifty Five
Multi Task DPP for Basket Completion by Romain WARLOP, Fifty Fiverecsysfr
 
Building a recommender system with Annoy and Word2Vec by Cristian PEREZ, Kern...
Building a recommender system with Annoy and Word2Vec by Cristian PEREZ, Kern...Building a recommender system with Annoy and Word2Vec by Cristian PEREZ, Kern...
Building a recommender system with Annoy and Word2Vec by Cristian PEREZ, Kern...recsysfr
 
An Homophily-based Approach for Fast Post Recommendation in Microblogging Sys...
An Homophily-based Approach for Fast Post Recommendation in Microblogging Sys...An Homophily-based Approach for Fast Post Recommendation in Microblogging Sys...
An Homophily-based Approach for Fast Post Recommendation in Microblogging Sys...recsysfr
 
Predictive quality metrics @ tinyclues - Artem Kozhevnikov - Tinyclues
Predictive quality metrics @ tinyclues - Artem Kozhevnikov - TinycluesPredictive quality metrics @ tinyclues - Artem Kozhevnikov - Tinyclues
Predictive quality metrics @ tinyclues - Artem Kozhevnikov - Tinycluesrecsysfr
 
Highlights on most interesting RecSys papers - Elena Smirnova, Lowik Chanusso...
Highlights on most interesting RecSys papers - Elena Smirnova, Lowik Chanusso...Highlights on most interesting RecSys papers - Elena Smirnova, Lowik Chanusso...
Highlights on most interesting RecSys papers - Elena Smirnova, Lowik Chanusso...recsysfr
 
Injecting semantic links into a graph-based recommender system
Injecting semantic links into a graph-based recommender systemInjecting semantic links into a graph-based recommender system
Injecting semantic links into a graph-based recommender systemrecsysfr
 
Recommendations @ Rakuten Group
Recommendations @ Rakuten GroupRecommendations @ Rakuten Group
Recommendations @ Rakuten Grouprecsysfr
 

Mehr von recsysfr (7)

Multi Task DPP for Basket Completion by Romain WARLOP, Fifty Five
Multi Task DPP for Basket Completion by Romain WARLOP, Fifty FiveMulti Task DPP for Basket Completion by Romain WARLOP, Fifty Five
Multi Task DPP for Basket Completion by Romain WARLOP, Fifty Five
 
Building a recommender system with Annoy and Word2Vec by Cristian PEREZ, Kern...
Building a recommender system with Annoy and Word2Vec by Cristian PEREZ, Kern...Building a recommender system with Annoy and Word2Vec by Cristian PEREZ, Kern...
Building a recommender system with Annoy and Word2Vec by Cristian PEREZ, Kern...
 
An Homophily-based Approach for Fast Post Recommendation in Microblogging Sys...
An Homophily-based Approach for Fast Post Recommendation in Microblogging Sys...An Homophily-based Approach for Fast Post Recommendation in Microblogging Sys...
An Homophily-based Approach for Fast Post Recommendation in Microblogging Sys...
 
Predictive quality metrics @ tinyclues - Artem Kozhevnikov - Tinyclues
Predictive quality metrics @ tinyclues - Artem Kozhevnikov - TinycluesPredictive quality metrics @ tinyclues - Artem Kozhevnikov - Tinyclues
Predictive quality metrics @ tinyclues - Artem Kozhevnikov - Tinyclues
 
Highlights on most interesting RecSys papers - Elena Smirnova, Lowik Chanusso...
Highlights on most interesting RecSys papers - Elena Smirnova, Lowik Chanusso...Highlights on most interesting RecSys papers - Elena Smirnova, Lowik Chanusso...
Highlights on most interesting RecSys papers - Elena Smirnova, Lowik Chanusso...
 
Injecting semantic links into a graph-based recommender system
Injecting semantic links into a graph-based recommender systemInjecting semantic links into a graph-based recommender system
Injecting semantic links into a graph-based recommender system
 
Recommendations @ Rakuten Group
Recommendations @ Rakuten GroupRecommendations @ Rakuten Group
Recommendations @ Rakuten Group
 

Kürzlich hochgeladen

Film cover research (1).pptxsdasdasdasdasdasa
Film cover research (1).pptxsdasdasdasdasdasaFilm cover research (1).pptxsdasdasdasdasdasa
Film cover research (1).pptxsdasdasdasdasdasa494f574xmv
 
Potsdam FH学位证,波茨坦应用技术大学毕业证书1:1制作
Potsdam FH学位证,波茨坦应用技术大学毕业证书1:1制作Potsdam FH学位证,波茨坦应用技术大学毕业证书1:1制作
Potsdam FH学位证,波茨坦应用技术大学毕业证书1:1制作ys8omjxb
 
办理多伦多大学毕业证成绩单|购买加拿大UTSG文凭证书
办理多伦多大学毕业证成绩单|购买加拿大UTSG文凭证书办理多伦多大学毕业证成绩单|购买加拿大UTSG文凭证书
办理多伦多大学毕业证成绩单|购买加拿大UTSG文凭证书zdzoqco
 
Call Girls Near The Suryaa Hotel New Delhi 9873777170
Call Girls Near The Suryaa Hotel New Delhi 9873777170Call Girls Near The Suryaa Hotel New Delhi 9873777170
Call Girls Near The Suryaa Hotel New Delhi 9873777170Sonam Pathan
 
SCM Symposium PPT Format Customer loyalty is predi
SCM Symposium PPT Format Customer loyalty is prediSCM Symposium PPT Format Customer loyalty is predi
SCM Symposium PPT Format Customer loyalty is predieusebiomeyer
 
『澳洲文凭』买拉筹伯大学毕业证书成绩单办理澳洲LTU文凭学位证书
『澳洲文凭』买拉筹伯大学毕业证书成绩单办理澳洲LTU文凭学位证书『澳洲文凭』买拉筹伯大学毕业证书成绩单办理澳洲LTU文凭学位证书
『澳洲文凭』买拉筹伯大学毕业证书成绩单办理澳洲LTU文凭学位证书rnrncn29
 
办理(UofR毕业证书)罗切斯特大学毕业证成绩单原版一比一
办理(UofR毕业证书)罗切斯特大学毕业证成绩单原版一比一办理(UofR毕业证书)罗切斯特大学毕业证成绩单原版一比一
办理(UofR毕业证书)罗切斯特大学毕业证成绩单原版一比一z xss
 
Call Girls In The Ocean Pearl Retreat Hotel New Delhi 9873777170
Call Girls In The Ocean Pearl Retreat Hotel New Delhi 9873777170Call Girls In The Ocean Pearl Retreat Hotel New Delhi 9873777170
Call Girls In The Ocean Pearl Retreat Hotel New Delhi 9873777170Sonam Pathan
 
Q4-1-Illustrating-Hypothesis-Testing.pptx
Q4-1-Illustrating-Hypothesis-Testing.pptxQ4-1-Illustrating-Hypothesis-Testing.pptx
Q4-1-Illustrating-Hypothesis-Testing.pptxeditsforyah
 
NSX-T and Service Interfaces presentation
NSX-T and Service Interfaces presentationNSX-T and Service Interfaces presentation
NSX-T and Service Interfaces presentationMarko4394
 
PHP-based rendering of TYPO3 Documentation
PHP-based rendering of TYPO3 DocumentationPHP-based rendering of TYPO3 Documentation
PHP-based rendering of TYPO3 DocumentationLinaWolf1
 
Top 10 Interactive Website Design Trends in 2024.pptx
Top 10 Interactive Website Design Trends in 2024.pptxTop 10 Interactive Website Design Trends in 2024.pptx
Top 10 Interactive Website Design Trends in 2024.pptxDyna Gilbert
 
Contact Rya Baby for Call Girls New Delhi
Contact Rya Baby for Call Girls New DelhiContact Rya Baby for Call Girls New Delhi
Contact Rya Baby for Call Girls New Delhimiss dipika
 
Font Performance - NYC WebPerf Meetup April '24
Font Performance - NYC WebPerf Meetup April '24Font Performance - NYC WebPerf Meetup April '24
Font Performance - NYC WebPerf Meetup April '24Paul Calvano
 
『澳洲文凭』买詹姆士库克大学毕业证书成绩单办理澳洲JCU文凭学位证书
『澳洲文凭』买詹姆士库克大学毕业证书成绩单办理澳洲JCU文凭学位证书『澳洲文凭』买詹姆士库克大学毕业证书成绩单办理澳洲JCU文凭学位证书
『澳洲文凭』买詹姆士库克大学毕业证书成绩单办理澳洲JCU文凭学位证书rnrncn29
 

Kürzlich hochgeladen (17)

Film cover research (1).pptxsdasdasdasdasdasa
Film cover research (1).pptxsdasdasdasdasdasaFilm cover research (1).pptxsdasdasdasdasdasa
Film cover research (1).pptxsdasdasdasdasdasa
 
Potsdam FH学位证,波茨坦应用技术大学毕业证书1:1制作
Potsdam FH学位证,波茨坦应用技术大学毕业证书1:1制作Potsdam FH学位证,波茨坦应用技术大学毕业证书1:1制作
Potsdam FH学位证,波茨坦应用技术大学毕业证书1:1制作
 
young call girls in Uttam Nagar🔝 9953056974 🔝 Delhi escort Service
young call girls in Uttam Nagar🔝 9953056974 🔝 Delhi escort Serviceyoung call girls in Uttam Nagar🔝 9953056974 🔝 Delhi escort Service
young call girls in Uttam Nagar🔝 9953056974 🔝 Delhi escort Service
 
办理多伦多大学毕业证成绩单|购买加拿大UTSG文凭证书
办理多伦多大学毕业证成绩单|购买加拿大UTSG文凭证书办理多伦多大学毕业证成绩单|购买加拿大UTSG文凭证书
办理多伦多大学毕业证成绩单|购买加拿大UTSG文凭证书
 
Call Girls Near The Suryaa Hotel New Delhi 9873777170
Call Girls Near The Suryaa Hotel New Delhi 9873777170Call Girls Near The Suryaa Hotel New Delhi 9873777170
Call Girls Near The Suryaa Hotel New Delhi 9873777170
 
SCM Symposium PPT Format Customer loyalty is predi
SCM Symposium PPT Format Customer loyalty is prediSCM Symposium PPT Format Customer loyalty is predi
SCM Symposium PPT Format Customer loyalty is predi
 
『澳洲文凭』买拉筹伯大学毕业证书成绩单办理澳洲LTU文凭学位证书
『澳洲文凭』买拉筹伯大学毕业证书成绩单办理澳洲LTU文凭学位证书『澳洲文凭』买拉筹伯大学毕业证书成绩单办理澳洲LTU文凭学位证书
『澳洲文凭』买拉筹伯大学毕业证书成绩单办理澳洲LTU文凭学位证书
 
办理(UofR毕业证书)罗切斯特大学毕业证成绩单原版一比一
办理(UofR毕业证书)罗切斯特大学毕业证成绩单原版一比一办理(UofR毕业证书)罗切斯特大学毕业证成绩单原版一比一
办理(UofR毕业证书)罗切斯特大学毕业证成绩单原版一比一
 
Call Girls In The Ocean Pearl Retreat Hotel New Delhi 9873777170
Call Girls In The Ocean Pearl Retreat Hotel New Delhi 9873777170Call Girls In The Ocean Pearl Retreat Hotel New Delhi 9873777170
Call Girls In The Ocean Pearl Retreat Hotel New Delhi 9873777170
 
Q4-1-Illustrating-Hypothesis-Testing.pptx
Q4-1-Illustrating-Hypothesis-Testing.pptxQ4-1-Illustrating-Hypothesis-Testing.pptx
Q4-1-Illustrating-Hypothesis-Testing.pptx
 
NSX-T and Service Interfaces presentation
NSX-T and Service Interfaces presentationNSX-T and Service Interfaces presentation
NSX-T and Service Interfaces presentation
 
Hot Sexy call girls in Rk Puram 🔝 9953056974 🔝 Delhi escort Service
Hot Sexy call girls in  Rk Puram 🔝 9953056974 🔝 Delhi escort ServiceHot Sexy call girls in  Rk Puram 🔝 9953056974 🔝 Delhi escort Service
Hot Sexy call girls in Rk Puram 🔝 9953056974 🔝 Delhi escort Service
 
PHP-based rendering of TYPO3 Documentation
PHP-based rendering of TYPO3 DocumentationPHP-based rendering of TYPO3 Documentation
PHP-based rendering of TYPO3 Documentation
 
Top 10 Interactive Website Design Trends in 2024.pptx
Top 10 Interactive Website Design Trends in 2024.pptxTop 10 Interactive Website Design Trends in 2024.pptx
Top 10 Interactive Website Design Trends in 2024.pptx
 
Contact Rya Baby for Call Girls New Delhi
Contact Rya Baby for Call Girls New DelhiContact Rya Baby for Call Girls New Delhi
Contact Rya Baby for Call Girls New Delhi
 
Font Performance - NYC WebPerf Meetup April '24
Font Performance - NYC WebPerf Meetup April '24Font Performance - NYC WebPerf Meetup April '24
Font Performance - NYC WebPerf Meetup April '24
 
『澳洲文凭』买詹姆士库克大学毕业证书成绩单办理澳洲JCU文凭学位证书
『澳洲文凭』买詹姆士库克大学毕业证书成绩单办理澳洲JCU文凭学位证书『澳洲文凭』买詹姆士库克大学毕业证书成绩单办理澳洲JCU文凭学位证书
『澳洲文凭』买詹姆士库克大学毕业证书成绩单办理澳洲JCU文凭学位证书
 

Flexible recommender systems based on graphs

  • 1. | kernixdigital factory + data lab Flexible recommender systems based on graphs
  • 2. | KERNIX 45 co-workers 500projects 2co-founders 3,5M€ revenue 15years experience 10books published Digital factory Data lab CO-FOUNDERS Fabrice Métayer and François-Xavier Bois, two EPITA engineers, gathered their complementary profiles to create Kernix in 2001. ABOUT KERNIX Kernix’s core business consists in a digital factory and a data lab. This double skill allows us to accompany our clients from upstream phases (consulting, study, POC) to downstream phases (industrialization by production teams).
  • 3. | 3 DATA LAB Clients Collaborations EXPERTISE Data Pipelines Cop21 TerraRush Predictive maintenance ERDF Data Vizualisation SolarImpulse Recommender systems PriceMinister WikiDistrict Clickalto HobbyStreet Marketing Automation Performics RadiumOne Open Data Accessible.net
  • 4. | • Graph database – data stored as nodes • label : “type” of data stored in the node • properties : collection of information describing the node – nodes are linked together by edges • type : describes the nature of the relation – query language : allows to perform graph traversals • Why graph-oriented recommender systems ? – gather heterogeneous data in the same structure – explicitly take advantage of relationships – "meaningful" for humans – easy implementation – fast execution (no training) GRAPH-ORIENTED RECOMMENDER SYSTEM
  • 5. | USE CASE 1 : HOBBYSTREET
  • 6. | Facilitate connections between craftsmen and private individuals • Craftsmen : propose workshops (different categories, dates, prices) • Individuals : follow workshops/categories, sign up at workshops • Hobbystreet : handle registrations, plannings, payments, propose customized suggestions CONTEXT
  • 7. | DATA STRUCTURE User name city Carftman name activity Workshop name description GPS coordinates Session date, time price status stock Category name activity follows proposes related to instance of participates
  • 8. | SUGGESTIONS : OVERALL STRATEGY Category User Workshop 1 Category 1 Category 2 Workshop 2 Workshop 3 Workshop 4 Similar descriptions User Workshop 1 Workshop 2 Workshop 3 Workshop 4 Workshop 5 Workshop 6 from LSA Similar users User 1 Workshop 1 Workshop 2 Workshop 3 User 2 User 3 Workshop 4 Workshop 5 Workshop 6 Usim
  • 9. | USE CASE 2 : KONBINI
  • 10. | Context “... multi format media company producing its own mix of culture, art and news content. It promotes online journalism, advocating an emphasis on pop culture and a commitment to develop local emerging talents.” “... became one of the first websites to put Social Media platforms at the heart of their strategy.”Issue: ~90% bounce rate (users going back after viewing a page) Solution: Recommend interesting articles on the visited pages will help user experience.
  • 11. | Entities French posts [693] Authors [56] Categories [534] Mexican posts [149] English posts [417] Examples of node properties blog_id: 9 post_id: 217628 post_date: 20151007 slug: rihanna-thinks-rachel... boost: 0 viewed_count: 0 facebook_count: 148 twitter_count: 0 Multiple web sites [US, England, Mexic, France] US posts [364]
  • 12. | Recommendations principles For each posts, we will recommend a list of other posts based on relations shared with the initial post: - semantic similarity of the contents [LSA] - number of common categories - number of common authors And also on their own properties: - the freshness - social counts - manual boost Once the graph constructed, these recommendations can be obtained thanks to a single Cypher query.
  • 14. | Stacks and Workflows Konbini web siteHobbystreet web site POST content GET recommendations POST content Daily cached recommendadions GET recommendations Live recommendation for dynamic interactions Cached recommendation for high availability needs
  • 15. | Improve semantic analysis: • exploit similarity of short descriptions (tweets, comments, …). PhD thesis on the subject. Assess recommendation quality: • A/B testing but Needs production deployment. • Offline testing ? No real assessment on the impact of the recommendations performed. • Rating of pool of testers ? Outlook
  • 16. THANK YOU ! Kernix Data Lab +33 (0)1 53 98 73 43 lab@kernix.com