Hr analytics and graphs : job recommendations

Post on 28-Nov-2014

458 views 0 download

description

Human resources : How to use graphs and Neo4j to make job recommendations.

Transcript of Hr analytics and graphs : job recommendations

SAS founded in 2013 in Paris | http://linkurio.us | @linkurious

HR analytics and graphs : job recommendations.

Introduction.

CMO

>5 years in consulting

MSc Political sciences and Competitive

Intelligence

JeanVilledieu

SébastienHeymann

RomainYon

CEO

Gephi Founder

Phd in Computer Science and Complex

Systems

CTO

Engineer (Microsoft, Spotify)

Machine Learning at Georgia Tech

Linkurious is a French startup founded in 2013.

Father Of

Father Of

Siblings

What is a graph ?

This is a graph.

Father Of

Father Of

Siblings

This is a node

This is a relationship

What is a graph ? / Nodes & relationshipsWhat is a graph : nodes and relationships.

A graph is a set of nodes linked by relationships.

Human resources and recruitment.

How can HR departments match jobs and candidates?

Making the right recommendation.

Making a good recommendation is hard.

Why some companies do it better than others?

Graphs can help.

Graphs are great for recommendations.

The graph of human resources.

Python Programming(Competency)

Financial Management(Competency)

James(Person)

Paul(Person)

HAS_COMPETENCY

WORKS_FOR WORKED_FORAcme(Company)

General Management(Competency)

HAS_COMPETENCY

HAS_COMPETENCY HAS_COMPETENCY

FRIEND_OF

People, skills, companies.

Graph databases are great to store this information.

Let’s try to play matchmaker with Neo4j!

Download the Neo4j dataset used for this presentation.

Find top 5 competencies at “Siliconfind”.

Step 1 : What are the competencies in my company?

//What kinds of competencies are in my company

match (n:Person)-[:HAS_COMPETENCY]->(co:Competency), (n)–>(cp:Company

{name:’Siliconfind’})

return co.name as competencies, count(n) as number_of_experts

order by count(n) desc

limit 5

This query is written with Cypher the Neo4j query language. It returns us 25 results.

A data problem.

The top 5 competencies at “Siliconfind”.

competencies number of experts

People Management 13

General Management 9

Carpenter 8

Java Programming 7

Scala Programming 6

Let’s look within the network of our employees for a recruit.

Step 1 : What are the competencies in my company?

//Find friends of our employees that have a skill in java and python programming

match (c:Company {name:’Siliconfind’})<-[WORKS_FOR]-(p1:Person)-[:

FRIEND_OF]-(p2:Person) with p2 match (p2)-[:HAS_COMPETENCY]->(c2:

Competency {name:”Java Programming”}), (p2)-[:HAS_COMPETENCY]->(c3:

Competency {name:”Python Programming”})

return distinct p2.first_name as first_name, p2.last_name as last_name

We are looking for friends of Siliconfind’s employees who know Java and Python.

A data problem.

Potential matches within our company’s social network.

first_name last_name

Damon Cruz

Gina Jenkins

Rick Carpenter

Whitney Ryan

//Find a perfect candidate for our software engineer position

match (o:Job {name:’Software Engineer’})-[:IS_REQUIRED]->req<-[:

HAS_COMPETENCY]-p

with o, p, count(req) as c

where length(o-[:IS_REQUIRED]-()) = c

return p, c

We are looking for someone who matches the competencies required by the job ad.

Matching a job ad and people.

Step 1 : What are the competencies in my company?

A data problem.

We have 3 perfect matches.

p c

(18:Person {first_name:"Alberto", gender:"Male", id:19, last_name:"Boone"}) 3

(98:Person {first_name:"Tommie", gender:"Male", id:99, last_name:"Holland"}) 3

(53:Person {first_name:"Jaime", gender:"Male", id:54, last_name:"Rogers"}) 3

Some of the domains in which our customers use graphs.

People, objects, movies, restaurants, music…

Suggest new contacts, help discover new music

Antennas, servers, phones, people…

Diminish network outages

Supplier, roads, warehouses, products…

Diminish transportation cost, optimize delivery

Supply chains Social networks Communications

Differents domains where graphs are important.

You can do it too!

Try Linkurious.

Contact us to discuss your projects at contact@linkurio.us

Conclusion