The data sample comes from OPERA (http://operaweb.lngs.infn.it) experiment that is well-known to find neutrinos using photo emulsion technique. Neutrinos themselves are invisible in the detector, but a very small fraction of them will interact with material in the detector and produce an electromagnetic shower in case of a scattered electron and also a hadronic shower in case of a scattered nucleus. The goal of the machine learning competition is to find traces of electromagnetic showers within a very dense background sample (see figure). Atomic electrons can also be scattered by light dark matter which is searched for by other experiments, including those at CERN, for example at SHiP (http://ship.web.cern.ch), which is going to use very similar neutrino detection techniques as the OPERA experiment.
![Background (blue) and electromagnetic shower (red) traces inside a detector module.](https://storage.googleapis.com/kaggle-media/competitions/inclass/6986/media/hep_ann_signal.png)
Prize
We believe that the motivation is very important in such competitions, however being pure research-motivated project, we cannot offer much more than pure joy of giving a whirl to uncharted area of dark matter searches. Also we believe that sharing joy is really important, so winner of this competition will be invited to give a talk at the 12th SHiP collaboration meeting this year at CERN.
Acknowledgements
We would like to thank OPERA collaboration and Prof. Giovanni De Lellis, spokesperson of the collaboration, for sharing the data sample and supporting this challenge.