The aim of this playground challenge is to find a phenomenon that is not already known to exist – charged lepton flavour violation – thereby helping to establish "
[new physics](https://en.wikipedia.org/wiki/Physics_beyond_the_Standard_Model)
".
Flavours of Physics 101
The laws of nature ensure that some physical quantities, such as energy or momentum, are conserved. From
[Noether’s theorem](https://en.wikipedia.org/wiki/Noether%27s_theorem)
, we know that each conservation law is associated with a fundamental symmetry. For example, conservation of energy is due to the time-invariance (the outcome of an experiment would be the same today or tomorrow) of physical systems. The fact that physical systems behave the same, regardless of where they are located or how they are oriented, gives rise to the conservation of linear and angular momentum.
Symmetries are also crucial to the structure of the
[Standard Model](https://en.wikipedia.org/wiki/Standard_Model)
of particle physics, our present theory of interactions at microscopic scales. Some are built into the model, while others appear accidentally from it. In the Standard Model, lepton flavour, the number of electrons and electron-neutrinos, muons and muon-neutrinos, and tau and tau-neutrinos, is one such conserved quantity.
[](https://en.wikipedia.org/wiki/Standard_Model)
Interestingly, in many proposed extensions to the Standard Model, this symmetry doesn’t exist, implying decays that do not conserve lepton flavour are possible. One decay searched for at the LHC is
τ
-
→ μ
+
μ
-
μ
-
(or τ → 3μ). Observation of this decay would be a clear indication of the violation of lepton flavour and a sign of long-sought new physics.
Competition Design
You will be working with real data from the
[LHCb experiment](http://lhcb-public.web.cern.ch/lhcb-public/)
at the LHC, mixed with simulated datasets of the decay. The metric used in this challenge includes checks that physicists do in their analysis to make sure the results are unbiased. These checks have been built into the competition design to help ensure that the results will be useful for physicists in future studies.
To get started, review the
[Data Page](https://www.kaggle.com/c/flavours-of-physics-kernels-only/data)
, and be sure to download the
[Starter Kit](https://www.kaggle.com/c/flavours-of-physics-kernels-only/details/starter-kit)
. The Starter Kit will help you to get used to the unique submission procedure for this competition.
Competition Video Tutorial
You've got lots of questions. Researchers at CERN & LCHb have the answers.
- What is the goal of this competition? (1:56)
- Why is finding τ → μμμ exciting? (2:18)
- What are flavours? (4:10)
- Why use machine learning to find τ → μμμ? (4:57)
- How did you decide on the size of the dataset? (5:31)
- Why is weighted AUC the evaluation metric? (6:09)
- Why use Ds → φπ data for the Agreement Test? (7:53)
- Why do we need a Correlation Check? (8:44)
- How will the competition results impact what you do? (11:38)
- How will the competition results be used at CERN? (12:17)
Resources
[Flavour of Physics, Research Documentation](https://storage.googleapis.com/kaggle-media/competitions/kaggle/4488/media/lhcb_description_official.pdf)
[Roel Aaij et al., Search for the lepton flavour violating decay τ → µµµ, 2015, JHEP, 1502:121, 2015](http://arxiv.org/pdf/1409.8548.pdf)
[New approaches for boosting to uniformity](http://iopscience.iop.org/1748-0221/10/03/T03002/pdf/1748-0221_10_03_T03002.pdf)
Acknowledgements
This competition is brought to you by:
[](http://home.web.cern.ch/)
[](http://lhcb-public.web.cern.ch/lhcb-public/)
[](https://yandexdataschool.com/)
[](https://yandexdatafactory.com)
Co-sponsored by:
![](https://storage.googleapis.com/kaggle-media/competitions/kaggle/4488/media/intel_logo.png)
Additional support from:
[](https://www.uzh.ch/index_en.html)
[](http://www2.warwick.ac.uk/)
[](http://www.ifj.edu.pl/)
[](http://www.hse.ru/en/)
![](//mc.yandex.ru/watch/31554783)