![](\"https://storage.googleapis.com/kaggle-media/competitions/kaggle/4488/media/CERN_logo156.png\"){kind=logo}
You may submit a maximum of 10 entries per day.
\nStart Date: 6/22/2018
\nMerger Deadline: None
\nEntry Deadline: None
\n\n\nCompetitions are open to residents of the United States and worldwide, except if you are a resident of Crimea, Cuba, Iran, Syria, North Korea, Sudan, or are subject to U.S. export controls or sanctions, then you may not enter the Competition. Other local rules and regulations may apply to you, so please check your local laws to ensure that you are eligible to participate in skills-based competitions.
\nENTRY IN THIS COMPETITION CONSTITUTES YOUR ACCEPTANCE OF THESE OFFICIAL COMPETITION RULES.
\nThe Competition named above is a skills-based competition to promote and further the field of data science. You must register via the Competition Website to enter. Your competition submissions (“Submissions”) must conform to the requirements set forth on the Competition Website. The Competition Sponsor will score your Submissions based on the evaluation metric described on the Competition Website. Subject to compliance with the Competition Rules, Prizes described on the Competition Website, if any, will be awarded to participants with the highest scores, based on the merits of content submitted plus Kaggle's discretion. See below for the complete Competition Rules.
\nCOMPETITION TITLE (the 'Competition'): Flavours of Physics
\nCOMPETITION SPONSOR: Kaggle
\nCOMPETITION WEBSITE: https://www.kaggle.com/c/flavours-of-physics-kernels-only
\nPRIZES: Knowledge\n\n
In addition to the provisions of the General Competition Rules below, you understand and agree to these Specific Competition Rules required by the Competition Sponsor:
\n\nThe following provision supersedes General Rules Section 3 below: “The Competition is sponsored and hosted by Kaggle Inc. (“Kaggle”). As a Kaggle.com account holder and user of the Kaggle competition platform, remember you have accepted and are subject to the Kaggle Terms of Service at < www.kaggle.com/terms > in addition to these Rules.\"
\n\nThe following provision supersedes General Rules Section 7.B. below: “You may use data, other than the Competition Data, as allowed on the Competition Website to develop and test your models and Submissions; provided, you have the right and authority to use such external data for the purposes of the Competition, and to share such data with Sponsor and Kaggle as may be required.\"
\n\nThe following provision supersedes General Rules Sections 9, 10 and 11 below: \"The Competition does not count towards Kaggle ranking points or medals. No prizes will be awarded for winning submissions. Winners are not obligated to provide their solution to Kaggle, or license their solution in any form.\"
\n\n\nIn order to enter the Competition, you must agree to these Official Competition Rules, which incorporate by reference the provisions and content of the Competition Website and any Specific Competition Rules above (collectively, the “Rules”). Please read these Rules carefully prior to entry to ensure you understand and agree. You agree that submission of an entry in the Competition constitutes agreement to these Rules. You may not submit an entry to the Competition and are not eligible to receive the prizes described in these Rules unless you agree to these Rules. These Rules form a binding legal agreement between you and the Competition Sponsor with respect to the Competition.
\nA. To be eligible to enter the Competition, you must be:
\nIf you are entering as a representative of a company, educational institution or other legal entity, or on behalf of your employer, these rules are binding on you, individually, and/or the entity you represent or are an employee. If you are acting within the scope of your employment, as an employee, contractor, or agent of another party, you warrant that such party has full knowledge of your actions and has consented thereto, including your potential receipt of a prize. You further warrant that your actions do not violate your employer’s or entity’s policies and procedures.
\nThe Competition Sponsor reserves the right to verify eligibility and to adjudicate on any dispute at any time. If you provide any false information relating to the Competition concerning your identity, residency, mailing address, telephone number, email address, ownership of right, or information required for entering the Competition, you may be immediately disqualified from the Competition.
\nB. Unless otherwise set forth in the Specific Competition Rules above, employees, interns, contractors, officers and directors of the Competition Sponsor, Kaggle Inc., and their parent companies, subsidiaries, affiliates, and their respective directors, officers, employees, advertising and promotion agencies, representatives, and agents (“Competition Entities”) may enter and participate in the Competition, but are not eligible to win any Prizes.
\nThe Competition is sponsored by Competition Sponsor named above. The Competition is hosted on behalf of Competition Sponsor by Kaggle Inc. (“Kaggle”). Kaggle is an independent contractor of Competition Sponsor, is not a party to this or any agreement between you and Competition Sponsor. You understand that Kaggle has no responsibility with respect to selecting the potential Competition winner(s) or awarding any Prizes. Kaggle will perform certain administrative functions relating to hosting the Competition, and you agree to abide by the provisions relating to Kaggle under these Rules. As a Kaggle.com account holder and user of the Kaggle competition platform, remember you have accepted and are subject to the Kaggle Terms of Service at < www.kaggle.com/terms > in addition to these Rules.
\nThe Competition will run from the Start Date and time to the End Date and time, as set forth on the Competition Website. The Competition Period and Submission deadlines are subject to change, and Competition Sponsor may introduce additional hurdle deadlines during the Competition. Any updated or additional deadlines will be publicized on the Competition Website. It is your responsibility to check the Competition Website regularly to stay informed of any deadline changes. YOU ARE RESPONSIBLE FOR DETERMINING THE CORRESPONDING TIME ZONE IN YOUR LOCATION.
\nNO PURCHASE NECESSARY TO ENTER OR WIN. To enter the Competition, you must register on the Competition Website during the Competition Period, and follow the instructions for developing and entering your Submission through the Competition Website. Your Submissions must be made in the manner and format, and in compliance with all other requirements, set forth on the Competition Website (the “Requirements”). Submissions must be received prior to any Submission deadlines set forth on the Competition Website.
\nSubmissions may not use or incorporate information from hand labeling or human prediction of the validation dataset or test data records.
\nIf the Competition is a multi-stage competition with temporally separate training data and/or leaderboard data, one or more valid Submissions must be made and selected during each Competition stage in the manner described on the Competition Website in order for the Submissions to be Prize eligible.
\nSubmissions are void if they are in whole or part illegible, incomplete, damaged, altered, counterfeit, obtained through fraud, or late. Competition Sponsor reserves the right, in its sole discretion, to disqualify any entrant who makes a Submission that does not meet the Requirements.
\nA. Individual Account. You may make Submissions only under one, unique Kaggle.com account. You will be disqualified if you make Submissions through more than one Kaggle account, or attempt to falsify an account to act as your proxy. You may submit up to the maximum number of Submissions per day as specified on the Competition Website.
\nB. Teams. If permitted under the Competition Website guidelines, multiple individuals may collaborate as a team (a “Team”); however, you may join or form only one Team. Each Team member must be a single individual with a separate Kaggle account. You must register individually for the Competition before joining a Team. You must confirm your Team membership to make it official by responding to the Team notification message sent to your Kaggle account. Team membership may not exceed the Maximum Team Size set forth on the Competition Website.
\nC. Team Merger. Teams may request to merge by notifying Kaggle at least seven (7) days before any Submission deadline set forth on the Competition Website. Team mergers may be allowed provided that: (i) the combined Team does not exceed the Maximum Team Size; (ii) the number of Submissions made by the merging Teams does not exceed the number of Submissions permissible for one Team at the date of the merger request; and (iii) the proposed combined Team otherwise meets all the requirements of these Rules. A merger is not official until the requesting Teams are notified of the allowed merger by Kaggle sent to the Team member’s Kaggle accounts.
\n'Data' means the Data or Datasets linked from the Competition Website for the purpose of use by Participants in the Competition. For the avoidance of doubt, Data is deemed for the purpose of these Competition Rules to include any prototype or executable code provided to Participants by Kaggle or Competition Sponsor via the Website. Participants must use the Data only as permitted by these Competition Rules and any associated data use rules specified on the Competition Website.
\nUnless otherwise permitted by the terms of the Competition Website, Participants must use the Data solely for the purpose and duration of the Competition, including but not limited to reading and learning from the Data, analyzing the Data, modifying the Data and generally preparing your Submission and any underlying models and participating in forum discussions on the Website. Participants agree to use suitable measures to prevent persons who have not formally agreed to these Competition Rules from gaining access to the Data and agree not to transmit, duplicate, publish, redistribute or otherwise provide or make available the Data to any party not participating in the Competition. Participants agree to notify Kaggle immediately upon learning of any possible unauthorized transmission or unauthorized access of the Data and agree to work with Kaggle to rectify any unauthorized transmission. Participants agree that participation in the Competition shall not be construed as having or being granted a license (expressly, by implication, estoppel, or otherwise) under, or any right of ownership in, any of the Data.
\nA. Private Code Sharing. Unless otherwise specifically permitted under the Competition Website or Competition Specific Rules above, during the Competition, you are not allowed to privately share source or executable code developed in connection with or based upon the Competition Data. This prohibition includes code sharing between separate Teams, unless a Team merger occurs. Any such code sharing is a breach of these Competition Rules and may result in disqualification.
\nB. Public Code Sharing. You are permitted to publicly share source or executable code developed in connection with or based upon the Competition Data, or otherwise relevant to the Competition, provided that such public sharing does not violate the intellectual property rights of any third party. By so sharing, you are deemed to have licensed the shared code under any of the eligible Open Source licenses listed below.
\nC. Use of Open Source. Unless otherwise set forth in the Specific Competition Rules above, if Open Source code is used in the model to general the Submission, then you must only use Open Source code licensed under an Open Source Initiative-approved license (see www.opensource.org>) that in no event limits commercial use of such code or model containing or depending on such code.
\nEach Submission will be scored and ranked by the evaluation metric set forth on the Competition Website. During the Competition, the then current ranking will be visible on the Competition Website’s leaderboard. In this Playground Competition, winners will not be selected on the basis of their Submission scores. Instead, potential winners will be selected according the the criteria outlined on the Prizes page.
\nKaggle will notify the potential winner(s) by email. If a potential winner does not respond to the notification attempt within five (5) days from the first notification attempt, then such potential winner will be disqualified and an alternate potential winner will be selected from among all eligible entries received based on the judging criteria described herein.
\nThe winner’s list will be publicly displayed at Kaggle.com. Determinations of Competition Sponsor are final and binding.
\nAs a condition to being awarded a Prize, a Prize winner must fulfill the following obligations:
\n(a) grant to Competition Sponsor the license to the winning Submission as set forth in the Competition Specific Rules above, and represent that you have the unrestricted right to grant that license;
\n(b) sign and return all Prize acceptance documents as may be required by Competition Sponsor or Kaggle, including without limitation: (i) eligibility certifications; (ii) licenses, releases and other agreements required under the Rules; and (iii) U.S, tax forms (such as IRS Form W-9 if U.S. resident, IRS Form W-8BEN if foreign resident, or future equivalents).
\nPrize(s) are as described on the Competition Website. Odds of winning any prize depends on the number of eligible Submissions received during the Competition Period and the skill of the entrants.
\nAll Prizes are subject to Competition Sponsor’s review and verification of the entrant’s eligibility and compliance with these Rules, and the compliance of the winning Submissions with the Submissions Requirements. In the event that the Submission demonstrates non-compliance with these Competition Rules, Competition Sponsor may at its discretion take either of the following actions: (i) disqualify the Submission(s); or (ii) require the potential winner to remediate within one week after notice all issues identified in the Submission(s) (including, without limitation, the resolution of license conflicts, the fulfillment of all obligations required by software licenses, and the removal of any software that violates the software restrictions).
\nA potential winner may decline to be nominated as a Competition winner by notifying Kaggle directly within 1 week after the end of the Competition Period, in which case the potential winner forgoes any prize or other features associated with winning the Competition. Kaggle reserves the right to disqualify a Participant who so declines its winner status.
\nPotential winners must return all required documents within 15 days following notification, or such potential winner will be deemed to have forfeited the prize and another potential winner will be selected. Prize(s) will be awarded within approximately 30 days after receipt by Competition Sponsor of the required Prize acceptance documents. Transfer or assignment of a Prize is not allowed.
\nYou are not eligible to receive any Prize if you do not meet the Eligibility requirements in Section 2 above.
\nIf a Team wins a monetary Prize, the Prize money will be allocated in even shares between the eligible Team members, unless the Team unanimously opts for a different prize split and notifies Kaggle before prizes are issued.
\nALL TAXES IMPOSED ON PRIZES ARE THE SOLE RESPONSIBILITY OF THE WINNERS. Payments to potential winners are subject to the express requirement that they submit all documentation requested by Competition Sponsor or Kaggle for compliance with applicable state, federal, local and foreign (including provincial) tax reporting and withholding requirements. Prizes will be net of any taxes that Competition Sponsor is required by law to withhold. If a potential winner fails to provide any required documentation or comply with applicable laws, the Prize may be forfeited and Competition Sponsor may, in its sole discretion, select an alternative potential winner. Any winners who are U.S. residents will receive an IRS 1099 form in the amount of their Prize.
\nAll federal, state, provincial and local laws and regulations apply. Competition Sponsor reserves the right to disqualify any entrant from the Competition if, in Competition Sponsor’s sole discretion, it reasonably believes that the entrant has attempted to undermine the legitimate operation of the Competition by cheating, deception, or other unfair playing practices or abuses, threatens or harasses any other entrants, Competition Sponsor or Kaggle.
\nBy accepting a Prize, you agree that Competition Sponsor, Kaggle and its agencies may use of your name and/or likeness, for advertising and promotional purposes without additional compensation, unless prohibited by law.
\nYou acknowledge and agree that Competition Sponsor and Kaggle may collect, store, share and otherwise use personally identifiable information provided during the registration process and the Competition, including, but not limited to, name, mailing address, phone number, and email address. Kaggle will use this information in accordance with its Privacy Policy
You warrant that your Submission is your own original work and, as such, you are the sole and exclusive owner and rights holder of the Submission, and you have the right to make the Submission and grant all required licenses. You agree not to make any Submission that: (i) infringes any third party proprietary rights, intellectual property rights, industrial property rights, personal or moral rights or any other rights, including without limitation, copyright, trademark, patent, trade secret, privacy, publicity or confidentiality obligations; or (ii) otherwise violates any applicable state or federal law.
\nTo the maximum extent permitted by law, you indemnify and agree to keep indemnified Competition Entities at all times from and against any liability, claims, demands, losses, damages, costs and expenses resulting from any act, default or omission of the entrant and/or a breach of any warranty set forth herein. To the maximum extent permitted by law, you agree to defend, indemnify and hold harmless the Competition Entities from and against any and all claims, actions, suits or proceedings, as well as any and all losses, liabilities, damages, costs and expenses (including reasonable attorneys fees) arising out of or accruing from: (a) your Submission or other material uploaded or otherwise provided by you that infringes any copyright, trademark, trade secret, trade dress, patent or other intellectual property right of any person or entity, or defames any person or violates their rights of publicity or privacy; (b) any misrepresentation made by you in connection with the Competition; (c) any non-compliance by you with these Rules; (d) claims brought by persons or entities other than the parties to these Rules arising from or related to your involvement with the Competition; and (e) your acceptance, possession, misuse or use of any Prize, or your participation in the Competition and any Competition-related activity.
\nYou hereby release Competition Sponsor and Kaggle from any liability associated with: (a) any malfunction or other problem with the Competition Website; (b) any error in the collection, processing, or retention of any Submission; or (c) any typographical or other error in the printing, offering or announcement of any Prize or winners.
\nCompetition Entities are not responsible for any malfunction of the Competition Website or any late, lost, damaged, misdirected, incomplete, illegible, undeliverable, or destroyed Submissions or entry materials due to system errors, failed, incomplete or garbled computer or other telecommunication transmission malfunctions, hardware or software failures of any kind, lost or unavailable network connections, typographical or system/human errors and failures, technical malfunction(s) of any telephone network or lines, cable connections, satellite transmissions, servers or providers, or computer equipment, traffic congestion on the Internet or at the Competition Website, or any combination thereof, which may limit an entrant’s ability to participate.
\nIf for any reason the Competition is not capable of running as planned, including infection by computer virus, bugs, tampering, unauthorized intervention, fraud, technical failures, or any other causes which corrupt or affect the administration, security, fairness, integrity, or proper conduct of the Competition, Competition Sponsor reserves the right at its sole discretion to cancel, terminate, modify or suspend the Competition. Competition Sponsor further reserves the right to disqualify any entrant who tampers with the submission process or any other part of the Competition or Competition Website. Any attempt by an entrant to deliberately damage any web site, including the Competition Website, or undermine the legitimate operation of the Competition is a violation of criminal and civil laws and should such an attempt be made, Competition Sponsor and Kaggle each reserves the right to seek damages from any such entrant to the fullest extent of the applicable law.\n
\nUnless otherwise specifically provided under the Competition Website, under no circumstances shall the entry of a Submission, the awarding of a Prize, or anything in these Rules be construed as an offer or contract of employment with Competition Sponsor or any of the Competition Entities. You acknowledge that you have submitted your Submission voluntarily and not in confidence or in trust. You acknowledge that no confidential, fiduciary, agency or other relationship or implied-in-fact contract now exists between you and Competition Sponsor or any of the Competition Entities, and that no such relationship is established by your entry of your Submission.
\nUnless otherwise provided in the Competition Specific Rules above, all claims arising out of or relating to these Rules will be governed by California law, excluding its conflict of laws rules, and will be litigated exclusively in the Federal or State courts of Santa Clara County, California, USA. The parties consent to personal jurisdiction in those courts. If any provision of these Rules is held to be invalid or unenforceable, all remaining provisions of the Rules will remain in full force and effect.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "data-description", "content": "In this competition, you are given a list of collision events and their properties. You will then predict whether a τ → 3μ decay happened in this collision. This τ → 3μ is currently assumed by scientists not to happen, and the goal of this competition is to discover τ → 3μ happening more frequently than scientists currently can understand.
\nIt is challenging to design a machine learning problem for something you have never observed before. Scientists at CERN developed the following designs to achieve the goal.
\nThis is a labelled dataset (the label ‘signal’ being ‘1’ for signal events, ‘0’ for background events) to train the classifier. Signal events have been simulated, while background events are real data.
\nThis real data is collected by the LHCb detectors observing collisions of accelerated particles with a specific mass range in which τ → 3μ can’t happen. We call these events “background” and label them 0.
\nThe test dataset has all the columns that training.csv has, except mass, production, min_ANNmuon, and signal.
\nThe test dataset consists of a few parts:
\nreal data for the control channel (ignored for scoring, used by agreement test)
\nYou need to submit predictions for ALL the test entries. You will need to treat them all the same and predict as if they are all the same channel's collision events.
\nA submission is only scored after passing both the agreement test and the correlation test.
\nThis dataset contains simulated and real events from the Control channel Ds → φπ to evaluate your simulated-real data of submission agreement locally. It contains the same columns as test.csv and weight column. For more details see agreement test.
This dataset contains only real background events recorded at LHCb to evaluate your submission correlation with mass locally. It contains the same columns as test.csv and mass column to check correlation with. For more details see correlation test.
The European Organization for Nuclear Research is the world’s largest high energy physics laboratory.
\r\n![](\"https://storage.googleapis.com/kaggle-media/competitions/kaggle/4488/media/lhcb_logo150.png\"){kind=logo}
LHCb is an experiment set up to explore what happened after the Big Bang that allowed matter to survive and build the Universe we inhabit today.
\r\n![\"\"](\"https://storage.googleapis.com/kaggle-media/competitions/kaggle/4488/media/schoolofdata_logo.png\"){kind=logo}
The Yandex School of Data Analysis (YSDA) is a free Master’s-level program in Computer Science and Data Analysis, which is offered by Yandex since 2007. The aim of the School is to train specialists in data analysis and information retrieval to be able to solve cutting edge industry problems as well as fundamental research challenges. YSDA is associated member of LHCb since December 2014.
\r\n![\"\"](\"https://storage.googleapis.com/kaggle-media/competitions/kaggle/4488/media/datafactory_logo.png\"){kind=logo}
Yandex Data Factory are the Machine Learning and data analytics experts that use data science to improve business’ operations, revenues and profitability. By building upon the real-time personalisation and predictive analytics technology of parent company, Yandex, the fourth largest search engine in the world, Yandex Data Factory helps clients improve their business awareness through the exploitation of their own data.
\r\nYandex Data Factory’s proven data science and technology continually analyses, tests, refines and reapplies hundreds of hypotheses to the customers’ datasets to determine the best next course of action. It offers tailored, scalable, SaaS-driven Machine Learning services to a wide variety of data-reliant verticals, such as retail, financial services, travel and telecoms, who wish to use their data for purposes such as improving personalisation, segmentation, churn prevention or fraud detection.
\r\nYandex Data Factory was founded in 2014 by Yandex and is headquartered in Amsterdam, operating throughout Europe.
\r\n![\"\"](\"https://storage.googleapis.com/kaggle-media/competitions/kaggle/4488/media/intel_logo_crop.png\"){kind=logo}
Intel (NASDAQ: INTC) is a world leader in computing innovation. The company designs and builds the essential technologies that serve as the foundation for the world’s computing devices. As a leader in corporate responsibility and sustainability, Intel also manufactures the world’s first commercially available “conflict-free” microprocessors. Additional information about Intel is available at http://newsroom.intel.com and http://blogs.intel.com.
\r\n![\"\"](\"https://storage.googleapis.com/kaggle-media/competitions/kaggle/4488/media/zurich_logo.png\"){kind=logo}
The University of Zurich is one of the leading research universities in Europe and offers the widest range of degree programs in Switzerland. It was founded in 1833 and currently has seven faculties: Philosophy, Human Medicine, Economic Sciences, Law, Mathematics and Natural Sciences, Theology and Veterinary Medicine.
\r\n![\"\"](\"https://storage.googleapis.com/kaggle-media/competitions/kaggle/4488/media/univwarwick_logo.png\"){kind=logo}
Warwick is one of the UK's leading universities, with an acknowledged reputation for excellence in research and teaching, for innovation, and for links with business and industry.
\r\n![\"\"](\"https://storage.googleapis.com/kaggle-media/competitions/kaggle/4488/media/ifj_logo75.png\"){kind=logo}
Institute of Nuclear Physics, Polish Academy of Sciences. Founded in 1955 Institute of Nuclear Physics has become leading Particle Physics research institution and ranked as class A+ by Polish Ministry of Higher Education.
\r\n![\"\"](\"https://storage.googleapis.com/kaggle-media/competitions/kaggle/4488/media/higherschoolec_logo75.png\"){kind=logo}
Consistently ranked as one of Russia’s top universities, the Higher School of Economics is a leader in Russian education and one of the preeminent economics and social sciences universities in eastern Europe and Eurasia.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Agreement Test", "content": "Since the classifier is trained on a mix of simulated signal and real data background, it is possible to reach a high performance by picking features that are not perfectly modeled in the simulation. We require that the classifier not have a large discrepancy when applied to real and simulated data.
\r\nTo verify this, we use a control channel, Ds → φπ, that has a similar topology as the signal decay, τ → 3μ. Ds → φπ is a much more well-known, well-observed behavior, as it happens more frequently. We provide both data and simulation samples for this decay, to which the classifier is applied. A Kolmogorov–Smirnov (KS) test is used to evaluate the differences between the classifier distribution on each sample.
\r\nDs → φπ data is not included in the training set. This control channel data is used purely in the test set as \"ignored\" data, meaning that they don’t contribute to the final scoring. The control channel dataset is used purely in Kolmogorov–Smirnov test. We require the KS-value of the test to be smaller than 0.09. Only when a submission can pass the agreement test on these ignored data, we can then regard the predictions as valid, and score on the submission.
\r\nIn particle physics experiments, it is well-known how to split the signal/background by their “weights”. The method is called sPlot. This weight is a measurement derived from the likelihood/probability that the event is a Ds → φπ and the weights range from -∞ to ∞. Higher weight means likely this event is signal, lower weights means it’s likely to be background.
\r\nThe Control channel, Ds → φπ, is split into two main parts, real (data1) and simulated (data2):
\r\nweight from sPlot function and signal = 0weight = 1 and signal = 1We use K-S test to tell that classifier outputs for data1 and data2 are from the same distribution.
\r\nPlease check out the github repo to learn more about how the agreement test is implemented.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Correlation Test", "content": "Each particle has its own mass. In an ideal world, one would just the mass of a particle to tell which particle it is. However, in reality, mass is an estimation, and it isn't a feature that scientists trust when building a model. Correlations with mass can cause an artificial signal-like mass peak or lead to incorrect background estimations.
\r\nThe mass column is not included in the test dataset. However, we use the hidden mass information to perform a Cramer-von Mises (cvm) test. This test iteratively compares two distributions of a) predicted values from submission for entire dataset and b) predicted values within a certain mass region in rolling window fashion along the whole mass range. Then we get average value for those checks. Getting similar distributions for all mass sub-regions means that your classifier is not correlated with the mass. Your submission must give a cvm value less than 0.002 to pass the test.
\r\nBelow is an illustration of this correlation test. On the left shows no correlation between prediction and mass, while on the right there is correlation.
\r\n![\"\"](\"https://storage.googleapis.com/kaggle-media/competitions/kaggle/4488/media/corr_test.png\")
Please check out the github repo to learn more about how the correlation test is implemented.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Description", "content": "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\".
\nThe laws of nature ensure that some physical quantities, such as energy or momentum, are conserved. From Noether’s 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.
\nSymmetries are also crucial to the structure of the 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.
\n![](\"https://storage.googleapis.com/kaggle-media/competitions/kaggle/4488/media/standardmodel2.png\")
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.
\nYou will be working with real data from the LHCb experiment 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.
\nTo get started, review the Data Page, and be sure to download the Starter Kit. The Starter Kit will help you to get used to the unique submission procedure for this competition.
\nYou've got lots of questions. Researchers at CERN & LCHb have the answers.
\n- 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)
Flavour of Physics, Research Documentation
\nRoel Aaij et al., Search for the lepton flavour violating decay τ → µµµ, 2015, JHEP, 1502:121, 2015
\nNew approaches for boosting to uniformity
\nThis competition is brought to you by:
\n
Co-sponsored by:
\n![\"\"](\"https://storage.googleapis.com/kaggle-media/competitions/kaggle/4488/media/intel_logo.png\"){kind=logo}
Additional support from:
\n
The evaluation metric for this competition is Weighted Area Under the ROC Curve. The ROC curve is divided into sections based on the True Positive Rate (TPR). To calculate the total area, multiply the area with TPR in [0., 0.2] by weight 2.0, the area with TPR in [0.2, 0.4] by 1.5, the area with TPR [0.4, 0.6] with weight 1.0, and the area with TPR [0.6, 0.8] with weight 0.5. Anything above a TPR of 0.8 has weight 0.
\r\n![](\"https://storage.googleapis.com/kaggle-media/competitions/kaggle/4488/media/roc_optimistic.png\")
These weights were chosen to match the evaluation methodology used by CERN scientists. Note that the weighted AUC is calculated only for events (simulated signal events for tau->µµµ and real background events for tau->µµµ) with min_ANNmuon > 0.4 (see details in section 2.2 Physics background).
\r\nBefore your predictions are scored with weighted AUC, they also must pass two addition checks: first an agreement test and then the correlation test. Please refer to their respective pages to learn about these tests and what is needed to pass them.
\r\nFor every event in the dataset, submission files should contain two columns: id and prediction. The prediction should be a floating point value between 0 and 1.0, indicating the probability that this event is τ → 3μ decay.
The file should contain a header and have the following format:
\r\nid,prediction", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Starter Kit", "content": "
14711831,0.3
16316387,0.3
6771382,0.3
686045,0.3
8755882,0.3
10247299,0.3
etc.
There are several starter kits prepared for making submissions using different computing languages (Python, C++/ROOT).
\r\nAll the starter kits are available in the following GitHub repository:
https://github.com/yandexdataschool/flavours-of-physics-start
Also you can find implementations of the competition Agreement and Correlation checks there.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }