SlideShare a Scribd company logo
1 of 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

More Related Content

What's hot

What's hot (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
 

Viewers also liked

Viewers also liked (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
 

Similar to Flexible recommender systems based on graphs

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
 
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
BookNet Canada
 

Similar to 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
 

More from recsysfr

More from 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
 

Recently uploaded

6.High Profile Call Girls In Punjab +919053900678 Punjab Call GirlHigh Profil...
6.High Profile Call Girls In Punjab +919053900678 Punjab Call GirlHigh Profil...6.High Profile Call Girls In Punjab +919053900678 Punjab Call GirlHigh Profil...
6.High Profile Call Girls In Punjab +919053900678 Punjab Call GirlHigh Profil...
@Chandigarh #call #Girls 9053900678 @Call #Girls in @Punjab 9053900678
 
( Pune ) VIP Baner Call Girls 🎗️ 9352988975 Sizzling | Escorts | Girls Are Re...
( Pune ) VIP Baner Call Girls 🎗️ 9352988975 Sizzling | Escorts | Girls Are Re...( Pune ) VIP Baner Call Girls 🎗️ 9352988975 Sizzling | Escorts | Girls Are Re...
( Pune ) VIP Baner Call Girls 🎗️ 9352988975 Sizzling | Escorts | Girls Are Re...
nilamkumrai
 
Lucknow ❤CALL GIRL 88759*99948 ❤CALL GIRLS IN Lucknow ESCORT SERVICE❤CALL GIRL
Lucknow ❤CALL GIRL 88759*99948 ❤CALL GIRLS IN Lucknow ESCORT SERVICE❤CALL GIRLLucknow ❤CALL GIRL 88759*99948 ❤CALL GIRLS IN Lucknow ESCORT SERVICE❤CALL GIRL
Lucknow ❤CALL GIRL 88759*99948 ❤CALL GIRLS IN Lucknow ESCORT SERVICE❤CALL GIRL
imonikaupta
 
VIP Call Girls Pollachi 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Pollachi 7001035870 Whatsapp Number, 24/07 BookingVIP Call Girls Pollachi 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Pollachi 7001035870 Whatsapp Number, 24/07 Booking
dharasingh5698
 

Recently uploaded (20)

6.High Profile Call Girls In Punjab +919053900678 Punjab Call GirlHigh Profil...
6.High Profile Call Girls In Punjab +919053900678 Punjab Call GirlHigh Profil...6.High Profile Call Girls In Punjab +919053900678 Punjab Call GirlHigh Profil...
6.High Profile Call Girls In Punjab +919053900678 Punjab Call GirlHigh Profil...
 
VIP Model Call Girls Hadapsar ( Pune ) Call ON 9905417584 Starting High Prof...
VIP Model Call Girls Hadapsar ( Pune ) Call ON 9905417584 Starting  High Prof...VIP Model Call Girls Hadapsar ( Pune ) Call ON 9905417584 Starting  High Prof...
VIP Model Call Girls Hadapsar ( Pune ) Call ON 9905417584 Starting High Prof...
 
Wagholi & High Class Call Girls Pune Neha 8005736733 | 100% Gennuine High Cla...
Wagholi & High Class Call Girls Pune Neha 8005736733 | 100% Gennuine High Cla...Wagholi & High Class Call Girls Pune Neha 8005736733 | 100% Gennuine High Cla...
Wagholi & High Class Call Girls Pune Neha 8005736733 | 100% Gennuine High Cla...
 
Yerawada ] Independent Escorts in Pune - Book 8005736733 Call Girls Available...
Yerawada ] Independent Escorts in Pune - Book 8005736733 Call Girls Available...Yerawada ] Independent Escorts in Pune - Book 8005736733 Call Girls Available...
Yerawada ] Independent Escorts in Pune - Book 8005736733 Call Girls Available...
 
Dubai Call Girls Milky O525547819 Call Girls Dubai Soft Dating
Dubai Call Girls Milky O525547819 Call Girls Dubai Soft DatingDubai Call Girls Milky O525547819 Call Girls Dubai Soft Dating
Dubai Call Girls Milky O525547819 Call Girls Dubai Soft Dating
 
Call Girls Sangvi Call Me 7737669865 Budget Friendly No Advance BookingCall G...
Call Girls Sangvi Call Me 7737669865 Budget Friendly No Advance BookingCall G...Call Girls Sangvi Call Me 7737669865 Budget Friendly No Advance BookingCall G...
Call Girls Sangvi Call Me 7737669865 Budget Friendly No Advance BookingCall G...
 
2nd Solid Symposium: Solid Pods vs Personal Knowledge Graphs
2nd Solid Symposium: Solid Pods vs Personal Knowledge Graphs2nd Solid Symposium: Solid Pods vs Personal Knowledge Graphs
2nd Solid Symposium: Solid Pods vs Personal Knowledge Graphs
 
Busty Desi⚡Call Girls in Vasundhara Ghaziabad >༒8448380779 Escort Service
Busty Desi⚡Call Girls in Vasundhara Ghaziabad >༒8448380779 Escort ServiceBusty Desi⚡Call Girls in Vasundhara Ghaziabad >༒8448380779 Escort Service
Busty Desi⚡Call Girls in Vasundhara Ghaziabad >༒8448380779 Escort Service
 
VVVIP Call Girls In Connaught Place ➡️ Delhi ➡️ 9999965857 🚀 No Advance 24HRS...
VVVIP Call Girls In Connaught Place ➡️ Delhi ➡️ 9999965857 🚀 No Advance 24HRS...VVVIP Call Girls In Connaught Place ➡️ Delhi ➡️ 9999965857 🚀 No Advance 24HRS...
VVVIP Call Girls In Connaught Place ➡️ Delhi ➡️ 9999965857 🚀 No Advance 24HRS...
 
WhatsApp 📞 8448380779 ✅Call Girls In Mamura Sector 66 ( Noida)
WhatsApp 📞 8448380779 ✅Call Girls In Mamura Sector 66 ( Noida)WhatsApp 📞 8448380779 ✅Call Girls In Mamura Sector 66 ( Noida)
WhatsApp 📞 8448380779 ✅Call Girls In Mamura Sector 66 ( Noida)
 
Hire↠Young Call Girls in Tilak nagar (Delhi) ☎️ 9205541914 ☎️ Independent Esc...
Hire↠Young Call Girls in Tilak nagar (Delhi) ☎️ 9205541914 ☎️ Independent Esc...Hire↠Young Call Girls in Tilak nagar (Delhi) ☎️ 9205541914 ☎️ Independent Esc...
Hire↠Young Call Girls in Tilak nagar (Delhi) ☎️ 9205541914 ☎️ Independent Esc...
 
Pune Airport ( Call Girls ) Pune 6297143586 Hot Model With Sexy Bhabi Ready...
Pune Airport ( Call Girls ) Pune  6297143586  Hot Model With Sexy Bhabi Ready...Pune Airport ( Call Girls ) Pune  6297143586  Hot Model With Sexy Bhabi Ready...
Pune Airport ( Call Girls ) Pune 6297143586 Hot Model With Sexy Bhabi Ready...
 
( Pune ) VIP Baner Call Girls 🎗️ 9352988975 Sizzling | Escorts | Girls Are Re...
( Pune ) VIP Baner Call Girls 🎗️ 9352988975 Sizzling | Escorts | Girls Are Re...( Pune ) VIP Baner Call Girls 🎗️ 9352988975 Sizzling | Escorts | Girls Are Re...
( Pune ) VIP Baner Call Girls 🎗️ 9352988975 Sizzling | Escorts | Girls Are Re...
 
Lucknow ❤CALL GIRL 88759*99948 ❤CALL GIRLS IN Lucknow ESCORT SERVICE❤CALL GIRL
Lucknow ❤CALL GIRL 88759*99948 ❤CALL GIRLS IN Lucknow ESCORT SERVICE❤CALL GIRLLucknow ❤CALL GIRL 88759*99948 ❤CALL GIRLS IN Lucknow ESCORT SERVICE❤CALL GIRL
Lucknow ❤CALL GIRL 88759*99948 ❤CALL GIRLS IN Lucknow ESCORT SERVICE❤CALL GIRL
 
Al Barsha Night Partner +0567686026 Call Girls Dubai
Al Barsha Night Partner +0567686026 Call Girls  DubaiAl Barsha Night Partner +0567686026 Call Girls  Dubai
Al Barsha Night Partner +0567686026 Call Girls Dubai
 
VIP Call Girls Pollachi 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Pollachi 7001035870 Whatsapp Number, 24/07 BookingVIP Call Girls Pollachi 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Pollachi 7001035870 Whatsapp Number, 24/07 Booking
 
Call Girls Ludhiana Just Call 98765-12871 Top Class Call Girl Service Available
Call Girls Ludhiana Just Call 98765-12871 Top Class Call Girl Service AvailableCall Girls Ludhiana Just Call 98765-12871 Top Class Call Girl Service Available
Call Girls Ludhiana Just Call 98765-12871 Top Class Call Girl Service Available
 
Shikrapur - Call Girls in Pune Neha 8005736733 | 100% Gennuine High Class Ind...
Shikrapur - Call Girls in Pune Neha 8005736733 | 100% Gennuine High Class Ind...Shikrapur - Call Girls in Pune Neha 8005736733 | 100% Gennuine High Class Ind...
Shikrapur - Call Girls in Pune Neha 8005736733 | 100% Gennuine High Class Ind...
 
Call Now ☎ 8264348440 !! Call Girls in Shahpur Jat Escort Service Delhi N.C.R.
Call Now ☎ 8264348440 !! Call Girls in Shahpur Jat Escort Service Delhi N.C.R.Call Now ☎ 8264348440 !! Call Girls in Shahpur Jat Escort Service Delhi N.C.R.
Call Now ☎ 8264348440 !! Call Girls in Shahpur Jat Escort Service Delhi N.C.R.
 
All Time Service Available Call Girls Mg Road 👌 ⏭️ 6378878445
All Time Service Available Call Girls Mg Road 👌 ⏭️ 6378878445All Time Service Available Call Girls Mg Road 👌 ⏭️ 6378878445
All Time Service Available Call Girls Mg Road 👌 ⏭️ 6378878445
 

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