kernixdigital factory + data lab
Flexible recommender systems
based on graphs
Digital factory Data lab
Fabrice Métayer and François-Xavier
Bois, two EPITA engineers, gathered
their complementary profiles to create
Kernix in 2001.
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).
• Graph database
– data stored as nodes
• label : “type” of data stored in the node
• properties : collection of information describing
– nodes are linked together by edges
• type : describes the nature of the relation
– query language : allows to perform graph traversals
• Why graph-oriented recommender
– 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
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
related to instance of
SUGGESTIONS : OVERALL STRATEGY
“... 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
“... 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
Solution: Recommend interesting articles on the visited
pages will help user experience.
French posts 
Categories  Mexican posts 
English posts 
Examples of node properties
Multiple web sites [US,
England, Mexic, France]
US posts 
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.
Stacks and Workflows
Konbini web siteHobbystreet web site
POST content GET recommendations POST content
Live recommendation for dynamic
Cached recommendation for high
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 ?
THANK YOU !
Kernix Data Lab
+33 (0)1 53 98 73 43