The ATLAS Higgs machine learning challenge

High Energy Physics has been using Machine Learning techniques (commonly known as Multivariate Analysis) since the 90's with Artificial Neural Net for example, more recently with Boosted Decision Trees, Random Forest etc... Meanwhile, Machine Learning has become a full blown field of computer science. With the emergence of Big Data, Data Scientists are developing new Machine Learning algorithms to extract sense from large heterogeneous data. HEP has exciting and difficult problems like the extraction of the Higgs boson signal, data scientists have advanced algorithms: the goal of the HiggsML project is to bring the two together by a “challenge”: participants from all over the world and any scientific background can compete online ( https://www.kaggle.com/c/higgs-boson ) to obtain the best Higgs to tau tau signal significance on a set of ATLAS full simulated Monte Carlo signal and background. Winners with the best scores will receive money prizes ; authors of the best method (most usable) will be invited to CERN by ATLAS. Instead of HEP physicists browsing through machine learning papers and trying to infer which new algorithms might be useful for HEP, then coding and tuning them, the challenge will bring realistic HEP data to the data scientists, which will themselves try out their best algorithms. The challenge is organized by the ATLAS collaboration associated to data scientists, in partnership with Paris Saclay Center for Data Science, CERN and Google. It is running since 12th may 2014 and will end 15th september 2014. The poster describes the challenge, in particular the challenge within the challenge which is to make a full blown Higgs search analysis simple for non physicists, but not too simple so that the problem remains ... challenging.