{ "fetched_at": "2026-10-24T16:46:26Z", "source_url": "https://www.kaggle.com/competitions/final22202/data", "pages": [ { "name": "data-description", "content": "

File descriptions

\r\n\r\n

For detailed information on the semantics of the features, labels, and weights, see the technical documentation from the LAL website on the task.

\r\n

Some details to get started:

\r\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Description", "content": "

Overview

\r\n

Discovery of the long awaited Higgs Boson was announced July 4, 2012 and confirmed six months later. 2013 saw a number of prestigious awards, including a Nobel prize. But for physicists, the discovery of a new particle means the beginning of a long and difficult quest to measure its characteristics and determine if it fits the current model of nature.

\r\n

A key property of any particle is how often it decays into other particles. ATLAS is a particle physics experiment taking place at the Large Hadron Collider at CERN that searches for new particles and processes using head-on collisions of protons of extraordinarily high energy. The ATLAS experiment has recently observed a signal of the Higgs boson decaying into two tau particles, but this decay is a small signal buried in background noise.

\r\n

The goal of the Higgs Boson Machine Learning Challenge is to explore the potential of advanced machine learning methods to improve the discovery significance of the experiment. No knowledge of particle physics is required. Using simulated data with features characterizing events detected by ATLAS, your task is to classify events into \"tau tau decay of a Higgs boson\" versus \"background.\"

\r\n

The winning method may eventually be applied to real data and the winners may be invited to CERN to discuss their results with high energy physicists.

", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Evaluation", "content": "

The evaluation metric is the approximate median significance (AMS):

\r\n
AMS=2((s+b+br)log(1+sb+br)−s)−−−−−−−−−−−−−−−−−−−−−−−−−−−−−−√
\r\n

where

\r\n\r\n

More precisely, let (y1,…,yn)∈{b,s}nbe the vector of true test labels, let (y^1,…,y^n)∈{b,s}nbe the vector of predicted (submitted) test labels, and let (w1,…,wn)∈R+nbe the vector of weights. Then

\r\n
s=∑i=1nwi1{yi=s}1{y^i=s}
\r\n
\r\n

\r\n\r\n

\r\n

and

\r\n
b=∑i=1nwi1{yi=b}1{y^i=s},
\r\n
\r\n

\r\n\r\n

\r\n

where the indicator function 1{A} 1 if its argument A  \r\n\r\nis true and 0 otherwise.

\r\n

For more information on the statistical model and the derivation of the metric, see the technical documentation. We have provided python code for the metric is available from the Data page and a Python starting kit.

\r\n

Submission Instructions

\r\n

The submission file format is

\r\n
EventId,Class
1,b
2,s
3,b
4,b
5,s
\r\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "rules", "content": "\r\n

One account per participant

\r\n

You cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.

\r\n

No private sharing outside teams

\r\n

Privately sharing code or data outside of teams is not permitted. It's okay to share code if made available to all participants on the forums.

\r\n

Team Mergers

\r\n

Team mergers are not allowed in this competition.

\r\n

Team Limits

\r\n

There is no maximum team size.

\r\n

Submission Limits

\r\n

You may submit a maximum of 2 entries per day.

\r\n

You may select up to 2 final submissions for judging.

\r\n

Competition Timeline

\r\n

Start Date: TBA

\r\n

Merger Deadline: None

\r\n

Entry Deadline: None

\r\n

End Date: 2/1/2014 12:00 AM UTC

\r\n\r\n

The rules page is a bit special: it will auto-update the text based on the parameters of the competition. The rules you need to add here are any additional rules relating to dataset usage. You may also put grading information here.

", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }