Data Science Liege MEETUP #10

Abstract

How we built a Job Recommender SaaS for VDAB with Deep Learning  – Clement NTWARI NSHUTI

In this talk, we’ll tell you about our experience building a job recommender software as a service for VDAB. Our deep neural net, called JobNet, “reads” job seeker résumés and job descriptions in multiple languages and learns to embed them in a common space. The resulting embeddings allow us to match job seekers and jobs in both directions. To deliver the best recommendations at the scale of VDAB, we built JobNet using a modern ML stack based on Dask, Sklearn, and TensorFlow. We’ll also talk about how we deployed the solution in the cloud using a modern Continuous Integration pipeline based on CircleCI, Terraform, Docker, and AWS ECS.

Driving behavior modeling using smart phone sensor data – Bertrand FONTAINE

Sentiance converts smartphone sensor data into driving and behavior intelligence for driver centric assistance, serves and usage-based insurance. I’ll start by introducing the use case of driving behaviour profiling for coaching and insurance. I’ll then present how we apply machine learning to implement that use case, i.e. to extract useful insights from low-level GPS, accelerometer, and gyroscope data streams. We’ll look into detecting transport mode, map-matching GPS-fixes to a plausible traveling route, and fusing that data to arrive at the driver/passenger classifier, openly discussing all ML architectures used, from random forests to CNN.

Comment un business peut-il surperformer grâce à l’intelligence artificielle ?  – Yves COLINET

Les nombreuses communications au sujet de l’intelligence artificielle rendent le sujet à la fois abstrait et confus. Il s’agit pourtant d’un levier pour les entreprises si elles s’appuient sur une combinaison des trois piliers qui sont l’organisation des données, la plateforme et les compétences. Au travers de deux cas, Yves Colinet (Micropole) expliquera comment un business peut surperformer grâce à l’intelligence artificielle.