CLEAR: Compilation of Intermediate Languages into Efficient Big Data Runtimes.

CLEAR is a research project funded by ANR, which started in January 2017 for 48 months.

Project Overview

This project addresses one fundamental challenge of our time: the construction of effective programming models and compilation techniques for the correct and efficient exploitation of big and linked data. We study high-level specifications of pipelines of data transformations and extraction for producing valuable knowledge from rich and heterogeneous data. We investigate how to synthesize code which is correct and optimized for execution on distributed infrastructures, with concrete applications in smart cities, finance and healthcare.

Zoom on a recent result

Our work has a new application in healthcare: we analyze very large amounts of electronic health records to generate accurate machine learning models that predict important clinical outcomes. See more in our article published in the March 2018's issue of the Big Data Research journal:

Scalable Machine Learning for Predicting At-Risk Profiles Upon Hospital Admission. Pierre Genevès, Thomas Calmant, Nabil Layaïda, Marion Lepelley, Svetlana Artemova, Jean-Luc Bosson. Big Data Research, Elsevier, 2018, 12, pp.23-34. <10.1016j.bdr.2018.02.004>

See more publications and recent events.