Elastic Paris Meetup #24 - Behavioural Analytics


Apr 18, 2017, 5:00 – 8:00 PM


About this event

Please make sure your first and last name is updated in your profile.

Talk 1 by ContentSquare:

Bien connu pour ses performances en tant que moteur de recherche, Elasticsearch offre également des fonctionnalités analytiques puissantes. Pendant ce talk, nous vous présenterons un cas d'utilisation d'Elasticsearch en analyse comportementale des internautes, un domaine dans lequel ContentSquare est spécialisé.

Chez ContentSquare, nous récoltons les données de navigation des utilisateurs pour améliorer leur expérience. ElasticSearch nous permet de produire à la volée des statistiques fines sur des segments de population et des comportements complexes. Modèle de données et requêtes à l'appui, nous vous présenterons la solution que nous avons conçue pour répondre à ce besoin avancé.

Yanxiu LI

Yanxiu LI, diplômée de Telecom ParisTech en 2014, elle travaille en tant que data scientist chez ContentSquare. En plus des projets data sciences, elle travaille étroitement avec les data engineers pour la reconstitution des données dans le produit ContentSquare

Talk 2: Machine Learning for Behavioural Analytics by Steve Dodson.

As volumes of data increase, manually searching and visualising consumer or user behaviours becomes more and more difficult. An alternative approach is to use machine learning to automatically build behavioural models of these behaviours. These models enable users to gain deep insights into behavioural characteristics that are beyond the capabilities of classical search techniques.

Typical use cases include, automatically understanding users that are behaving unusually and understanding the typical behaviour of the population.

This talk will present real examples of machine learning techniques applied to real-time behavioural data, and describe the methodology behind these methods along with an overview of the machine learning space.

Stephen Dodson, PhD, Tech Lead, Machine Learning at Elastic

Steve was formerly founder and CTO of Prelert, a London based software company that developed novel unsupervised machine learning technologies to identify anomalies in IT Ops and IT Security data. Prelert was acquired by Elastic in September 2016, and Steve continues to grow and lead the machinelearning group at Elastic. 

Prior to Prelert, Steve was a founding member of Riversoft (IPO'ed and acquired by Micromuse) and Njini (acquired by Riverbed). At Riversoft, he led the design of the topology driven root-cause analysis technology used today within IBM Tivoli Netcool, HP OpenView, and Cisco management tools.

Prior to software development, Steve worked in the Computational Mechanics group at Imperial College, London where he delivered key contributions to the field, resolving scalability issues using a novel approach to solving Maxwell's equations which allowed it to become a practical technique used today by major companies. Steve holds MEng in Mechanical Engineering and a PhD in Computational Methods from Imperial College, London alongside a CES from École Centrale de Lyon.



Tuesday, April 18, 2017
5:00 PM – 8:00 PM UTC


  • David Pilato


    Developer | Evangelist

Contact Us