James Lee

Marie Le Guilly

Phd. Student at INSA Lyon with LIRIS Lab

Engineer in Computer Science from INSA Lyon

Download CV

About Me

I'm Marie Le Guilly, a french PHD student in computer science. I work at the intersection between databases and machine learning, in order to provide new data exploration solution to users. I also teach programming at INSA Lyon.

About My PhD


Interactive query lanquages for data exploration using machine learning principles


This PhD aims at developing new approaches for interactive big data exploration by revisiting classical database approaches due to prohibitive running times, memory consumption, and volumes of the outputs. The key idea is to consider the data analyst as an essential link in the data exploration process, without making any hypothesis neither on the size of the data space nor on the size of the pattern space to be analyzed. We intend to guide and help the data analyst to both elicit zones of interest in the data space and to navigate in the pattern space, based on declarative approaches originating from database and artificial intelligence. We plan to propose high-level prototypes (e.g. from declarative languages or convenient user interfaces) to data analysts, hiding as much as possible the inherent complexity of big data analytics. An example of this is a SQL query completion prototype aiming at guiding databases exploration by suggesting possible completions for a given SQL query.

Professional Experience


Phd. Student - INSA-Lyon with LIRIS Lab
September 2017 - Present

Interactive query languages for data exploration using machine learning techniques


Teacher - INSA-Lyon
September 2017 - Present

Introduction to programmation, and java programming. Undergraduate students.


Research Intern - LIRIS Lab
January 2017 - June 2017

Research internship on data exploration using SQL query completion.


Research Intern - Dodin Campenon Bernard (VINCI) and LIRIS Lab
June 2016 - September 2016

Analysis of the data from a boring machine, prediction of soil compaction based on the machine’s parameters



Marie Le Guilly, Ihab F. Ilyas, Jean-Marc Petit & Vasile-Marian Scuturici (2018). « Partitioning queries for data exploration using query extension ». BDA 2018 34ème conférence sur la Gestion de Données — Principes, Technologies et Applications, October 2018, Bucarest (Romania).


Marie Le Guilly, Jean-Marc Petit & Vasile-Marian Scuturici (2017). « Retour d'expérience sur l'analyse des données d'un tunnelier ». BDA 2017 33ème conférence sur la Gestion de Données — Principes, Technologies et Applications, 14 novembre 2017, Nancy (France). Short Paper

Marie Le Guilly (2017). « Langages de requêtes interactifs pour l'exploration de données ». BDA, 14 novembre 2017, Nancy (France). PhD Workshop paper


May 2018 ISIP Workshop (Fukuoka, Japan)

Could Functional Dependencies Help to Identify Balanced Classification Datasets ?

September 2017 Decade Symposium (Lyon, France)

SQL query completion for data exploration

Technical Skills


Python, Java, C/C++


PL/SQL, MysQL, Oracle


Latex, Git, SVN