{ "fetched_at": "2026-10-24T02:33:30Z", "source_url": "https://www.kaggle.com/competitions/google-cloud-ncaa-march-madness-2020-division-1-mens-tournament/data", "pages": [ { "name": "rules", "content": "### **Updated March 13, 2020**: The following supersedes the respective terms outlined below. As a result of COVID-19, this competition will be cancelled with no Kaggle points, Kaggle medals, or monetary prizes. The end date has been updated from April 7, 2020 at 11:59pm UTC to March 19, 2020 at 3:00 am UTC. Please see this [announcement post](https://www.kaggle.com/c/google-cloud-ncaa-march-madness-2020-division-1-mens-tournament/discussion/135404) for more details.\n\n### One account per participant\n\nYou cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.\n\n### Use of Automated Machine Learning Tools (AMLT)\n\nAs further described in the Rules, this Competition permits the use of automated machine learning tool(s) (“AMLT”) in the creation of Submissions. AMLT Teams (as defined in the Rules) are not eligible to win any prizes. \n\n### No private sharing outside teams\n\nPrivately 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.\n\n### Team Mergers\n\nTeam mergers are allowed and can be performed by the team leader. In order to merge, the combined team must have a total submission count less than or equal to the maximum allowed as of the merge date. The maximum allowed is the number of submissions per day multiplied by the number of days the competition has been running. AMLT Teams are not permitted to enter into a Team merger. \n\n### Team Limits\n\nThe maximum team size is 5.\n\n### Submission Limits\n\nYou may submit a maximum of 50 entries per day.\n\nYou may select up to 2 final submissions for judging.\n\n### Competition Timeline\n\nStart Date: February 14, 2020\n\nMerger Deadline: March 19, 2020, 3:00 PM UTC\n\nEntry Deadline: March 19, 2020, 3:00 PM UTC\n\nEnd Date: **April 7, 2020, 11:59 PM EST**\n\n### COMPETITION-SPECIFIC TERMS\n\n**COMPETITION TITLE** (the 'Competition'): Google Cloud & NCAA® ML Competition 2020-NCAAM\n\n**COMPETITION SPONSOR**: Google Cloud\n\n**COMPETITION SPONSOR ADDRESS**: 1600 Amphitheatre Parkway, Mountain View, CA 94043\n\n**COMPETITION WEBSITE**: https://www.kaggle.com/c/google-cloud-ncaa-march-madness-2020-division-1-mens-tournament\n\n**PRIZES: $25,000**\n\nFirst Prize: $10,000\n\nSecond Prize: $7,000\n\nThird Prize: $5,000\n\nFourth Prize: $2,000\n\nFifth Prize: $1,000\n\n**WINNER LICENSE TYPE**: Open Source\n\n**DATA ACCESS AND USE**: Competition-Use Only\n\nCompetitions are open to residents of the United States and worldwide, except that if you are a resident of Crimea, Cuba, Iran, Syria, North Korea, Sudan, or are subject to U.S. export controls or sanctions, 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. The Competition Sponsor reserves the right to award alternative Prizes where needed to comply with local laws.\n\n**ENTRY IN THIS COMPETITION CONSTITUTES YOUR ACCEPTANCE OF THESE OFFICIAL COMPETITION RULES.**\n\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 stated on the Competition Website. Your Submissions will be scored based on the evaluation metric described on the Competition Website. Subject to compliance with the Competition Rules, Prizes, if any, will be awarded to participants with the best scores, based on the merits of the data science models submitted. See below for the complete Competition Rules.\n\n### A. COMPETITION-SPECIFIC RULES\n\nIn 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\n#### **1.\tWINNER LICENSE**\n\nOpen Source: You will license your winning Submission and the source code used to generate the Submission under an [Open Source Initiative-approved license][1] that in no event limits commercial use of such code or model containing or depending on such code.\n\n#### **2.\tSPECIAL RULES**\n\nA. *NCAA® Data Use*. \n\nYou agree that use of, and access to, the NCAA® data provided for this Competition (the “NCAA® Data”) is provided for the limited purpose of, and in connection with, your participation in the Competition.\n\nYou will not: (a) use or access the NCAA® Data for any commercial, gambling, or illegal purpose; (b) copy, modify, reproduce, license, sublicense, distribute, transmit, republish, exhibit, or display the NCAA® Data (except to the extent copying, modifying, reproducing or displaying is necessary and directly related to your participation in the Competition; (c) remove, obscure, or modify any copyright notices or other notices, designations, or attributions within the NCAA® Data; or (d) use any NCAA® Marks or any copyright or other proprietary rights associated with the NCAA® Data for any purpose without the express written consent of NCAA®. “NCAA® Marks” means all names, trademarks, logos, symbols, designations, emblems, designs, and trade dress of the NCAA®, together with all identifications, labels, insignia or indicia thereof.\n\nYou agree that the NCAA® is the owner of all right, title and interest in and to the NCAA® Data and the NCAA® Marks throughout the world, and that your use of the NCAA® Data does not change this ownership. \n\nYou will not use NCAA® Data in any production or manner that (a) causes actual or perceived harm to the health, safety, or welfare of NCAA® student-athletes; (b) brings discredit to the purpose, values or principles of the NCAA® or its member institutions; or (c) negatively impacts the best interests of intercollegiate athletics or higher education.\n\nYou will not use NCAA® Data with any other material or content that contains or displays adult content, promotes gambling, involves the sale of tobacco or alcohol, or other illicit substances, including NCAA®-banned substances (e.g., stimulants, anabolic steroids, testosterone products, marijuana), or impermissible nutritional supplements that NCAA® member institutions may not provide to student-athletes (e.g., creatine, amino acids, ginseng, energy drinks) (the list of NCAA®-banned drug classes is available at [www.ncaa.org/drugtesting][2]).\n\nYou will not use NCAA® Data in any product or service that includes the name, image, or likeness of a currently eligible NCAA® student-athlete.\n\nYou will not use NCAA® Data in any product or service that, in the NCAA®’s opinion, is misleading, unfair, defamatory, infringing, libelous, disparaging, obscene, violent, profane, vulgar, offensive, disrespectful or otherwise objectionable to the NCAA®. \n\nYou will not use NCAA® Data in any manner that violates any law or regulation. \n\nYou will not incorporate NCAA® Data into the brand or name of any product or service.\n\nYou will not use NCAA® Data in any produce or service that are promoted, marketed, or branded with marks, logos, slogans, or designs that are confusingly similar to those of the NCAA® or associated with the NCAA®’s use of the NCAA® Data.\n\nNCAA, Final Four, March Madness and Selection Sunday are trademarks of the National Collegiate Athletic Association. \n\nB. *Competition Submission Special Rules*. \n\nYou may determine game probability predictions as part of a submission by any method you like, including guessing.\n \nYou may not use the test data to cheat on the first stage of the competition. Your approach should only utilize past data when making a prediction.\n\nC. *Eligibility*. The following supersedes section 2.B below - Unless otherwise stated in the Specific Competition Rules above or prohibited by internal policies of the Competition Entities, employees, interns, contractors, officers and directors of Competition Entities may enter and participate in the Competition, but are not eligible to win any Prizes. \"Competition Entities\" means the Competition Sponsor, Kaggle Inc., National Collegiate Athletic Association, CBS Broadcasting, Inc., Turner Broadcasting Systems, Inc., and each of their respective parent companies, subsidiaries and affiliates. If you are such a participant from a Competition Entity, you are subject to all applicable internal policies of your employer with respect to your participation.\n\n#### **3. AUTOMATED MACHINE LEARNING TOOLS (AMLT).** \n\nThis competition permits the use of automated machine learning tool(s) (“AMLT”) in the creation of Submissions. Except as described in this section, AMLT are not permitted to be used in the creation of a Submission.\n \n**A. Submission as an AMLT**\n \nAn individual or team may make a Submission as an AMLT (each individual or team making a submission as an AMLT, a “AMLT Team”). The AMLT Team must be authorized to make such Submission by the owner(s) of the AMLT (including all rights in the AMLT). AMLT Teams must declare themselves as such by submitting the following form prior to making a Submission: https://www.kaggle.com/amlt-registration. Submissions made by an AMLT Team will be marked as benchmarks (highlighted and named to match the AMLT Team name) on the Competition’s public leaderboard and, like all Submissions, cannot be removed or revoked once submitted.\n \nThe following provision is added to the end of Section 2 of the General Competition Rules below: “AMLT Teams may enter and participate in the Competition, but are not eligible to win any Prizes.”\n\nThe following provision is added to the end of Section 6 of the General Competition Rules below: “D. AMLT Teams. If you submit a Submission to this Competition as an AMLT Team, you cannot also submit as an individual user or as a team. Violation may result in your disqualification from the Competition and removal from the Competition leaderboard, at Kaggle's sole discretion. AMLT Teams are not permitted to enter into a Team merger.”\n\n**B. Using an AMLT to create a submission**\n \nIndividual participants and Teams may also use an AMLT to create a Submission, provided that the participant ensures that they have an appropriate license to the AMLT and are able to comply with the Rules. An individual participant’s or Team’s use of an AMLT to create a Submission does not require that individual or team declare itself as an AMLT Team as described in Subsection A (Submission as an AMLT Team) above. \n \nThe following provision is added to the end of Section 11 of the General Competition Rules below: “Individual participants and Teams who have not declared themselves as an AMLT Team, but who create a Submission using an AMLT may win a Prize. However, for clarity, the potential winner’s Submission must still meet the requirements of these Rules, including but not limited to Section A.1 (Winners License), Section B.11 (Winners Obligations), and Section B.17 (Warranty, Indemnity, and Release). Additionally, as this Competition requires [an open source] license, a participant may only use AMLTs in the creation of their Submission if they have the unrestricted right to grant the open source license to source code used to generate the Submission, including the AMLT code. Associated disqualification and other consequences as specified in these Rules will apply if this requirement is not met.”\n\n#### **4. AGGREGATION OF COMPETITION ENTRIES**\n\nYou acknowledge and agree that any Competition entry you submit may be aggregated with other entries and the resulting aggregate may be used in marketing activities, such as averaging participant predictions or promoting a competition-wide community prediction.\"\n\n\n### B. GENERAL COMPETITION RULES\n#### **1.\tBINDING AGREEMENT.** \n\nTo 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 before entry to ensure you understand and agree. You further 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 associated with this Competition (“Prizes”) unless you agree to these Rules. These Rules form a binding legal agreement between you and the Competition Sponsor with respect to the Competition.\n\n#### **2.\tELIGIBILITY.** \n\nA. To be eligible to enter the Competition, you must be:\n\t(i) a registered account holder at Kaggle.com; \n\t(ii) the older of 18 years old or the age of majority in your jurisdiction of residence (unless otherwise agreed to by Competition Sponsor and appropriate parental/guardian consents have been obtained by Competition Sponsor); \n\t(iii) not a resident of Crimea, Cuba, Iran, Syria, North Korea, or Sudan; and\n\t(iv) not a person or representative of an entity under U.S. export controls or sanctions (see [https://www.treasury.gov/resource-center/sanctions/Programs/Pages/Programs.aspx][1]).\n\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 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. \n\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.\n\nB. Unless otherwise stated in the Specific Competition Rules above or prohibited by internal policies of the Competition Entities, employees, interns, contractors, officers and directors of Competition Entities may enter and participate in the Competition, but are not eligible to win any Prizes. \"Competition Entities\" means the Competition Sponsor, Kaggle Inc., and their respective parent companies, subsidiaries and affiliates. If you are such a participant from a Competition Entity, you are subject to all applicable internal policies of your employer with respect to your participation.\n\n#### **3.\tSPONSOR AND HOSTING PLATFORM.** \n\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, and 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][2] in addition to these Rules.\n\n#### **4.\tCOMPETITION PERIOD.** \n\nFor the purposes of Prizes, the Competition will run from the Start Date and time to the End Date and time (such duration the “Competition Period”). The Competition Timeline is subject to change, and Competition Sponsor may introduce additional hurdle deadlines during the Competition Period. 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.* \n\n#### **5.\tCOMPETITION ENTRY.** \n\nNO PURCHASE NECESSARY TO ENTER OR WIN. To enter the Competition, you must register on the Competition Website prior to the Entry Deadline, 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, stated on the Competition Website (the \"Requirements\"). Submissions must be received before any Submission deadlines stated on the Competition Website. Submissions not received by the stated deadlines will not be eligible to receive a Prize.\n\nSubmissions may not use or incorporate information from hand labeling or human prediction of the validation dataset or test data records.\n\nIf the Competition is a multi-stage competition with temporally separate training and/or test data, one or more valid Submissions may be required during each Competition stage in the manner described on the Competition Website in order for the Submissions to be Prize eligible.\n\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 to disqualify any entrant who does not follow these Rules, including making a Submission that does not meet the Requirements. \n\n#### **6.\tINDIVIDUALS AND TEAMS.** \n\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. \n\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 stated on the Competition Website.\n\nC. *Team Merger*. Teams may request to merge via 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; (iii) the merger is completed before the earlier of: any merger deadline or the Competition deadline; and (iv) the proposed combined Team otherwise meets all the requirements of these Rules. \n\n#### **7.\tCOMPETITION DATA.** \n\n\"Competition Data\" means the data or datasets available from the Competition Website for the purpose of use in the Competition, including any prototype or executable code provided on the Competition Website. The Competition Data will contain private and public test sets. Which data belongs to which set will not be made available to participants. \n\nA. *Data Access and Use*. You may access and use the Competition Data only for participating in the Competition and on Kaggle.com forums. The Competition Sponsor reserves the right to disqualify any participant who uses the Competition Data other than as permitted by the Competition Website and these Rules.\n\nB. *Data Security*. You agree to use reasonable and suitable measures to prevent persons who have not formally agreed to these Rules from gaining access to the Competition Data. You agree not to transmit, duplicate, publish, redistribute or otherwise provide or make available the Competition Data to any party not participating in the Competition. You agree to notify Kaggle immediately upon learning of any possible unauthorized transmission of or unauthorized access to the Competition Data and agree to work with Kaggle to rectify any unauthorized transmission or access.\n\nC. *External Data*. You may use data other than the Competition Data (“External Data”) to develop and test your models and Submissions. However, you will (i) ensure the External Data is available to use by all participants of the competition for purposes of the competition at no cost to the other participants and (ii) post such access to the External Data for the participants to the official competition forum prior to the Entry Deadline.\n\n#### **8.\tSUBMISSION CODE REQUIREMENTS.**\n\nA. *Private Code Sharing*. Unless otherwise specifically permitted under the Competition Website or Competition Specific Rules above, during the Competition Period, you are not allowed to privately share source or executable code developed in connection with or based upon the Competition Data or other source or executable code relevant to the Competition (“Competition Code”). This prohibition includes sharing Competition Code between separate Teams, unless a Team merger occurs. Any such sharing of Competition Code is a breach of these Competition Rules and may result in disqualification.\n\nB. *Public Code Sharing*. You are permitted to publicly share Competition Code, provided that such public sharing does not violate the intellectual property rights of any third party. If you do choose to share Competition Code or other such code, you are required to share it on Kaggle.com on the discussion forum or kernels associated specifically with the Competition for the benefit of all competitors. By so sharing, you are deemed to have licensed the shared code under an Open Source Initiative-approved license (see [www.opensource.org][3]) that in no event limits commercial use of such Competition Code or model containing or depending on such Competition Code.\n\nC. *Use of Open Source*. Unless otherwise stated in the Specific Competition Rules above, if open source code is used in the model to generate the Submission, then you must only use open source code licensed under an Open Source Initiative-approved license (see [www.opensource.org][4]) that in no event limits commercial use of such code or model containing or depending on such code.\n\n#### **9.\tDETERMINING WINNERS.** \n\nEach Submission will be scored and ranked by the evaluation metric stated on the Competition Website. During the Competition Period, the current ranking will be visible on the Competition Website's public leaderboard. The potential winner(s) are determined solely by the leaderboard ranking on the private leaderboard, subject to compliance with these Rules. The public leaderboard will be based on the public test set and the private leaderboard will be based on the private test set.\n\nIn the event of a tie, the Submission that was entered first to the Competition will be the winner. In the event a potential winner is disqualified for any reason, the Submission that received the next highest score rank will be chosen as the potential winner.\n\n#### **10.\tNOTIFICATION OF WINNERS & DISQUALIFICATION.**\n\nThe potential winner(s) will be notified by email. \n \nIf a potential winner (i) does not respond to the notification attempt within one (1) week from the first notification attempt or (ii) notifies Kaggle within one week after the End Date that the potential winner does not want to be nominated as a winner or does not want to receive a Prize, then, in each case (i) and (ii) such potential winner will not receive any Prize, and an alternate potential winner will be selected from among all eligible entries received based on the Competition’s judging criteria.\n \nIn case (i) and (ii) above Kaggle may disqualify the participant. However, in case (ii) above, if requested by Kaggle, such potential winner may provide code and documentation to verify the participant’s compliance with these Rules. If the potential winner provides code and documentation to the satisfaction of Kaggle, the participant will not be disqualified pursuant to this paragraph.\n \nCompetition Sponsor reserves the right to disqualify any participant from the Competition if the Competition Sponsor reasonably believes that the participant 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 participants, Competition Sponsor or Kaggle.\n \nA disqualified participant may be removed from the Competition leaderboard, at Kaggle's sole discretion. If a Participant is removed from the Competition Leaderboard, additional winning features associated with the Kaggle competition platform, for example Kaggle points or medals, may also not be awarded.\n \nThe final leaderboard list will be publicly displayed at Kaggle.com. Determinations of Competition Sponsor are final and binding.\n\n#### **11.\tWINNERS OBLIGATIONS.**\n\nAs a condition to being awarded a Prize, a Prize winner must fulfill the following obligations:\n\n(a) deliver to the Competition Sponsor the final model's software code as used to generate the winning Submission and associated documentation. The delivered software code should follow [these documentation guidelines][5], must be capable of generating the winning Submission, and contain a description of resources required to build and/or run the executable code successfully. If the final model’s software code includes generally commercially available software that is not owned by you, but that can be procured by the Competition Sponsor without undue expense, then instead of delivering the code for that software to the Competition Sponsor, you must identify that software, method for procuring it, and any parameters or other information necessary to replicate the winning Submission;\n\n(b) grant to the Competition Sponsor the license to the winning Submission stated in the Competition Specific Rules above, and represent that you have the unrestricted right to grant that license; \n\n(c) 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).\n\n#### **12.\tPRIZES.** \n\nPrize(s) are as described on the Competition Website and are only available for winning during the time period described on the Competition Website. The odds of winning any Prize depends on the number of eligible Submissions received during the Competition Period and the skill of the participants. \n\nAll Prizes are subject to Competition Sponsor's review and verification of the participant’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).\n\nA potential winner may decline to be nominated as a Competition winner in accordance with Section 10.\n\nPotential winners must return all required Prize acceptance documents within two (2) weeks following notification of such required documents, 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 or Kaggle of the required Prize acceptance documents. Transfer or assignment of a Prize is not allowed. \n\nYou are not eligible to receive any Prize if you do not meet the Eligibility requirements in Section 2 above.\n\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.\n\n#### **13.\tTAXES.** \n\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 select an alternative potential winner. Any winners who are U.S. residents will receive an IRS Form-1099 in the amount of their Prize.\n\n#### **14.\tGENERAL CONDITIONS.**  \n\nAll federal, state, provincial and local laws and regulations apply. \n\n#### **15.\tPUBLICITY.**\n\nYou agree that Competition Sponsor, Kaggle and its affiliates may use your name and likeness for advertising and promotional purposes without additional compensation, unless prohibited by law.\n\n#### **16.\tPRIVACY.**\n\nYou acknowledge and agree that Competition Sponsor and Kaggle may collect, store, share and otherwise use personally identifiable information provided by you during the Kaggle account registration process and the Competition, including but not limited to, name, mailing address, phone number, and email address (“Personal Information”). Kaggle acts as an independent controller with regard to its collection, storage, sharing, and other use of this Personal Information, and will use this Personal Information in accordance with its Privacy Policy <[www.kaggle.com/privacy][6]>, including for administering the Competition. As a Kaggle.com account holder, you have the right to request access to, review, rectification, portability or deletion of any personal data held by Kaggle about you by logging into your account and/or contacting Kaggle Support at <[www.kaggle.com/contact][7]>.\n\n As part of Competition Sponsor performing this contract between you and the Competition Sponsor, Kaggle will transfer your Personal Information to Competition Sponsor, which acts as an independent controller with regard to this Personal Information. As a controller of such Personal Information, Competition Sponsor agrees to comply with all U.S. and foreign data protection obligations with regard to your Personal Information. Kaggle will transfer your Personal Information to Competition Sponsor in the country specified in the Competition Sponsor Address listed above, which may be a country outside the country of your residence. Such country may not have privacy laws and regulations similar to those of the country of your residence.\n\n#### **17.\tWARRANTY, INDEMNITY AND RELEASE.** \n\nYou 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 defames any person; or (ii) otherwise violates any applicable U.S. or foreign state or federal law.\n\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 of your acts, defaults or omissions 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 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 defames any person; (b) any misrepresentation made by you in connection with the Competition; (c) any non-compliance by you with these Rules or any applicable U.S. or foreign state or federal law; (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.\n\nYou hereby release Competition Entities 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.\n\n#### **18.\tINTERNET.** \n\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 a participant’s ability to participate.\n\n#### **19.\tRIGHT TO CANCEL, MODIFY OR DISQUALIFY.**\n\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 to cancel, terminate, modify or suspend the Competition. Competition Sponsor further reserves the right to disqualify any participant who tampers with the submission process or any other part of the Competition or Competition Website. Any attempt by a participant to deliberately damage any website, including the Competition Website, or undermine the legitimate operation of the Competition is a violation of criminal and civil laws. Should such an attempt be made, Competition Sponsor and Kaggle each reserves the right to seek damages from any such participant to the fullest extent of the applicable law.\n\n#### **20.\tNOT AN OFFER OR CONTRACT OF EMPLOYMENT.**\n\nUnder no circumstances will 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, employment or other similar relationship is created between you and Competition Sponsor or any of the Competition Entities by your acceptance of these Rules or your entry of your Submission.\n\n#### **21.\tGOVERNING LAW.** \n\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.\n\n\n [1]: https://www.treasury.gov/resource-center/sanctions/Programs/Pages/Programs.aspx\n [2]: http://www.kaggle.com/terms\n [3]: http://www.opensource.org\n [4]: http://www.opensource.org\n [5]: https://www.kaggle.com/WinningModelDocumentationGuidelines\n [6]: http://www.kaggle.com/privacy\n [7]: http://www.kaggle.com/contact", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "data-description", "content": "# Data Description:\n\n

Each season there are thousands of NCAA basketball games played between Division I men's teams, culminating in March Madness®, the 68-team national championship that starts in the middle of March. We have provided a large amount of historical data about college basketball games and teams, going back many years. Armed with this historical data, you can explore it and develop your own distinctive ways of predicting March Madness® game outcomes. You can even evaluate and compare different approaches by seeing which of them would have done best at predicting tournament games from the past.

\n

If you are unfamiliar with the format and intricacies of the NCAA® tournament, we encourage reading the wikipedia page before diving into the data. The data description and schema may seem daunting at first, but is not as complicated as it appears.

\n

As a reminder, you are encouraged to incorporate your own sources of data. We have provided extensive historical data to jump-start the modeling process, and this data is self-consistent (for instance, dates and team ID's are always treated the same way). Nevertheless, you may also be able to make productive use of external data. If you head down this path, please be forewarned that many sources have their own distinctive way of identifying the names of teams, and this can make it challenging to link up with our data. The MTeamSpellings file, which is listed in the bottom section below, may help you map external team references into our own Team ID structure. You will probably also need to understand exactly how dates work in our data. Remember as well that you are required to disclose your external sources of data prior to the start of the tournament

\n

Please also note that we have standardized the spelling of column names and filenames, so if you are re-using code from previous instances of this contest, you may need to adjust for this. All of the files that are specific to the men’s contest now have a filename prefix of M, so for instance this year the teams file is named MTeams rather than just Teams.

\n

We extend our gratitude to Kenneth Massey for providing much of the historical data.

\n

Special Acknowledgment to Jeff Sonas of Sonas Consulting for his support in assembling the dataset for this competition.

\n

What to predict

\n

Stage 1 - You should submit predicted probabilities for every possible matchup in the past 5 NCAA® tournaments (seasons 2015-2019).

\n

Stage 2 - You should submit predicted probabilities for every possible matchup before the 2020 tournament begins.

\n

Refer to the Timeline page for specific dates. In both stages, the sample submission will tell you which games to predict.

\n

File descriptions

\n

Below we describe the format and fields of the contest data files. The data will likely be refreshed once in early March while Stage 1 of the competition is running. Many of the files are only complete through the end of last season. At the start of Stage 2, we will provide updates to these files to incorporate data from the current season. Right now the MSeasons and MTeamConferences files are the only two files that reference the 2020 season, since those are the only files where the final 2020 data is already finalized; the other files will be updated later on when we provide preliminary data (in early March) and final Stage 2 data (after Selection Sunday) for the current season.

\n
\n

Data Section 1 - The Basics

\n

This section provides everything you need to build a simple prediction model and submit predictions.

\n\n

Special note about \"Season\" numbers: the college basketball season lasts from early November until the national championship tournament that starts in the middle of March. For instance, this year the first men’s Division I games were played on November 5th, 2019 and the men’s national championship game will be played on April 6th, 2020. Because a basketball season spans two calendar years like this, it can be confusing to refer to the year of the season. By convention, when we identify a particular season, we will reference the year that the season ends in, not the year that it starts in. So for instance, the current season will be identified in our data as the 2020 season, not the 2019 season or the 2019-20 season or the 2019-2020 season, though you may see any of these in everyday use outside of our data.

\n
\n

Data Section 1 file: MTeams.csv

\n

This file identifies the different college teams present in the dataset. Each school is uniquely identified by a 4 digit id number. You will not see games present for all teams in all seasons, because the games listing is only for matchups where both teams are Division-I teams. There are 353 teams currently in Division-I, and an overall total of 367 teams in our team listing. Each year, some teams might start being Division-I programs, and others might stop being Division-I programs, and in fact this year is no exception. Savannah State (TeamID=1366) is no longer part of Division I and so their data in our dataset stops after the 2019 season, and they are no longer part of the Mid-Eastern Athletic Conference. To balance this out, Merrimack (TeamID=1467) has just moved to Division I this year, so they show up as a new team in the data and they are now part of the America East Conference. Other than the teams file and team conferences file, you won't see any data for Merrimack until preliminary 2020 season data starts coming in, as we approach Stage 2 of the contest.

\n\n
\n

Data Section 1 file: MSeasons.csv

\n

This file identifies the different seasons included in the historical data, along with certain season-level properties.

\n\n
\n

Data Section 1 file: MNCAATourneySeeds.csv

\n

This file identifies the seeds for all teams in each NCAA® tournament, for all seasons of historical data. Thus, there are between 64-68 rows for each year, depending on whether there were any play-in games and how many there were. In recent years the structure has settled at 68 total teams, with four \"play-in\" games leading to the final field of 64 teams entering Round 1 on Thursday of the first week (by definition, that is DayNum=136 each season). We will not know the seeds of the respective tournament teams, or even exactly which 68 teams it will be, until Selection Sunday on March 15, 2020 (DayNum=132).

\n\n
\n

Data Section 1 file: MRegularSeasonCompactResults.csv

\n

This file identifies the game-by-game results for many seasons of historical data, starting with the 1985 season (the first year the NCAA® had a 64-team tournament). For each season, the file includes all games played from DayNum 0 through 132. It is important to realize that the \"Regular Season\" games are simply defined to be all games played on DayNum=132 or earlier (DayNum=132 is Selection Sunday, and there are always a few conference tournament finals actually played early in the day on Selection Sunday itself). Thus a game played on or before Selection Sunday will show up here whether it was a pre-season tournament, a non-conference game, a regular conference game, a conference tournament game, or whatever.

\n\n
\n

Data Section 1 file: MNCAATourneyCompactResults.csv

\n

This file identifies the game-by-game NCAA® tournament results for all seasons of historical data. The data is formatted exactly like the MRegularSeasonCompactResults data. All games will show up as neutral site (so WLoc is always N). Note that this tournament game data also includes the play-in games (which always occurred on day 134/135) for those years that had play-in games. Thus each season you will see between 63 and 67 games listed, depending on how many play-in games there were.

\n

Because of the consistent structure of the NCAA® tournament schedule, you can actually tell what round a game was, depending on the exact DayNum. Thus:

\n\n

Special note: Each year, there are also going to be other games that happened after Selection Sunday, which are not part of the NCAA® Tournament. This includes tournaments like the postseason NIT, the CBI, the CIT, and the Vegas 16. Such games are not listed in the Regular Season or the NCAA® Tourney files; they can be found in the \"Secondary Tourney\" data files within Data Section 6. Although they would not be games you would ever be predicting directly for the NCAA® tournament, and they would not be games you would have data from at the time of predicting NCAA® tournament outcomes, you may nevertheless wish to make use of these games for model optimization, depending on your methodology. The more games that you can test your predictions against, the better your optimized model might eventually become, depending on how applicable all those games are. A similar argument might be advanced in favor of optimizing your predictions against conference tournament games, which might be viewed as reasonable proxies for NCAA® tournament games.

\n\n
\n

Data Section 1 file: MSampleSubmissionStage1.csv

\n

This file illustrates the submission file format for Stage 1. It is the simplest possible submission: a 50% winning percentage is predicted for each possible matchup.

\n

A submission file lists every possible matchup between tournament teams for one or more years. During Stage 1, you are asked to make predictions for all possible matchups from the past five NCAA® tournaments (seasons 2015, 2016, 2017, 2018, 2019). In Stage 2, you will be asked to make predictions for all possible matchups from the current NCAA® tournament (season 2020).

\n

When there are 68 teams in the tournament, there are 68*67/2=2,278 predictions to make for that year, so a Stage 1 submission file will have 2,278*5=11,390 data rows.

\n\n

Example #1: You want to make a prediction for Duke (TeamID=1181) against Arizona (TeamID=1112) in the 2017 tournament, with Duke given a 53% chance to win and Arizona given a 47% chance to win. In this case, Arizona has the lower numerical ID so they would be listed first, and the winning percentage would be expressed from Arizona's perspective (47%):

\n

2017_1112_1181,0.47

\n

Example #2: You want to make a prediction for Duke (TeamID=1181) against North Carolina (TeamID=1314) in the 2018 tournament, with Duke given a 51.6% chance to win and North Carolina given a 48.4% chance to win. In this case, Duke has the lower numerical ID so they would be listed first, and the winning percentage would be expressed from Duke's perspective (51.6%):

\n

2018_1181_1314,0.516

\n

Also note that a single prediction row serves as a prediction for each of the two teams' winning chances. So for instance, in Example #1, the submission row of \"2017_1112_1181,0.47\" specifically gives a 47% chance for Arizona to win, and doesn't explicitly mention Duke's 53% chance to win. However, our evaluation utility will automatically infer the winning percentage in the other direction, so a 47% prediction for Arizona to win also means a 53% prediction for Duke to win. And similarly, because the submission row in Example #2 gives Duke a 51.6% chance to beat North Carolina, we will automatically figure out that this also means North Carolina has a 48.4% chance to beat Duke.

\n
\n

Data Section 2 - Team Box Scores

\n

This section provides game-by-game stats at a team level (free throws attempted, defensive rebounds, turnovers, etc.) for all regular season, conference tournament, and NCAA® tournament games since the 2002-03 season.

\n

Team Box Scores are provided in \"Detailed Results\" files rather than \"Compact Results\" files. However, the two files are strongly related. \n

In a Detailed Results file, the first eight columns (Season, DayNum, WTeamID, WScore, LTeamID, LScore, WLoc, and NumOT) are exactly the same as a Compact Results file. However, in a Detailed Results file, there are many additional columns. The column names should be self-explanatory to basketball fans (as above, \"W\" or \"L\" refers to the winning or losing team):

\n\n

(and then the same set of stats from the perspective of the losing team: LFGM is the number of field goals made by the losing team, and so on up to LPF).

\n

Note: by convention, \"field goals made\" (either WFGM or LFGM) refers to the total number of fields goals made by a team, a combination of both two-point field goals and three-point field goals. And \"three point field goals made\" (either WFGM3 or LFGM3) is just the three-point fields goals made, of course. So if you want to know specifically about two-point field goals, you have to subtract one from the other (e.g., WFGM - WFGM3). And the total number of points scored is most simply expressed as 2*FGM + FGM3 + FTM.

\n
\n

Data Section 2 file: MRegularSeasonDetailedResults.csv

\n

This file provides team-level box scores for many regular seasons of historical data, starting with the 2003 season. All games listed in the MRegularSeasonCompactResults file since the 2003 season should exactly be present in the MRegularSeasonDetailedResults file.

\n
\n

Data Section 2 file: MNCAATourneyDetailedResults.csv

\n

This file provides team-level box scores for many NCAA® tournaments, starting with the 2003 season. All games listed in the MNCAATourneyCompactResults file since the 2003 season should exactly be present in the MNCAATourneyDetailedResults file.

\n
\n

Data Section 3 - Geography

\n

This section provides city locations of all regular season, conference tournament, and NCAA® tournament games since the 2009-10 season

\n
\n

Data Section 3 file: Cities.csv

\n

This file provides a master list of cities that have been locations for games played. Please notice that the Cities and Conferences files are the only two that don't start with an M; this is because the data files are identical between men's and women's data, so you don't need to maintain separate listings of cities or conferences across the two contests. Also note that if you created any supplemental data last year on cities (latitude/longitude, altitude, etc.), the CityID's match between last year and this year, so you should be able to re-use that information.

\n\n
\n

Data Section 3 file: MGameCities.csv

\n

This file identifies all games, starting with the 2010 season, along with the city that the game was played in. Games from the regular season, the NCAA® tourney, and other post-season tournaments, are all listed together. There should be no games since the 2010 season where the CityID is not known. Games from the 2009 season and before are not listed in this file.

\n\n
\n

Data Section 4 - Public Rankings

\n

This section provides weekly team rankings for dozens of top rating systems - Pomeroy, Sagarin, RPI, ESPN, etc., since the 2002-2003 season

\n
\n

Data Section 4 file: MMasseyOrdinals.csv

\n

This file lists out rankings (e.g. #1, #2, #3, ..., #N) of teams going back to the 2002-2003 season, under a large number of different ranking system methodologies. The information was gathered by Kenneth Massey and provided on his College Basketball Ranking Composite page.

\n

Note that a rating system is more precise than a ranking system, because a rating system can provide insight about the strength gap between two adjacently-ranked teams. A ranking system will just tell you who is #1 or who is #2, but a rating system might tell you whether the gap between #1 and #2 is large or small. Nevertheless, it can be hard to compare two different rating systems that are expressed in different scales, so it can be very useful to express all the systems in terms of their ordinal ranking (1, 2, 3, ..., N) of teams.

\n\n

Disclaimer: you ought to be careful about your methodology when using or evaluating these ranking systems. They are presented on a weekly basis, and given a consistent date on the Massey Composite page that typically is a Sunday; that is how the ranking systems can be compared against each other on this page. However, these systems each follow their own timeline and some systems may be released on a Sunday and others on a Saturday or Monday or even Tuesday. You should remember that if a ranking is released on a Tuesday, and was calculated based on games played through Monday, it will make the system look unusually good at predicting if you use that system to forecast the very games played on Monday that already inform the rankings. To avoid this methodological trap, we have typically used a conservative RankingDayNum of Wednesday to represent the rankings that were released at approximately the end of the weekend, a few days before, even though those rankings are represented on the composite page as being on a Sunday. For some of the older years, a more precise timestamp was known for each ranking system that allowed a more precise assignment of a RankingDayNum. By convention, the final pre-tournament rankings are always expressed as RankingDayNum=133, even though sometimes the rankings for individual systems are not released until Tuesday (DayNum=134) or even Wednesday or Thursday. If you decide to use some rankings from these Massey Ordinals to inform your predictions, be forewarned that we have no control over when they are released, and not all systems may turn out to be available in time to make pre-tournament predictions by our submission deadline. In such a situation, you may wish to use the rankings from DayNum=128 or you may need to dig into the details of the actual source of the rankings, by following the respective links on the Massey Composite Page. We may also be able to provide partial releases of the final pre-tournament Massey Ordinals on the forums, so that as systems come in on Monday or Tuesday you can use them right away.

\n
\n

Data Section 5 - Play-by-play

\n

This section provides play-by-play event logs for more than 99.5% of each year's regular season, NCAA® tournament, and secondary tournament games since the 2014-15 season - including plays by individual players.

\n
\n

This year we are transitioning to a different play-by-play source, which includes data since the 2014-2015 season rather than since the 2009-2010 season (that's what we had previously for men's data). However, we are now able to provide play-by-play for both men's and women's data, and there is locational play-by-play detail starting with games from the 2018-2019 season. This includes an X/Y location (ranging from 0 to 100 in each dimension) on the court for each shot attempt, turnover, and foul for many games, as well as an overall categorization of the area on the court that the shot or turnover or foul occurred in (inside left wing, outside right wing, under the basket, etc.) Some games in these recent seasons still lack the locational detail. The data from last year (2019 season) matches what you can expect for the current year (2020 season) as we approach the postseason. Despite the 99.5% coverage, there are still a few games missing annually, and we will try to bring those in as well, if possible.

\n
\n

Data Section 5 file: MEvents2015.csv, MEvents2016.csv, MEvent2017.csv, MEvents2018.csv, MEvents2019.csv

\n

Each MEvents file lists the play-by-play event logs for more than 99.5% of games from that season. Each event is assigned to either a team or a single one of the team's players. Thus if a basket is made by one player and an assist is credited to a second player, that would show up as two separate records. The players are listed by PlayerID within the MPlayers.csv file.

\n\n

Event Types and Subtypes:

\n\n
  • X, Y - for games where it is available, this describes an X/Y position on the court where the lower-left corner of the full court is (0,0), the upper-right corner of the full court is (100,100), the exact middle of the full court (where the initial jump ball happens) is (50,50), and so on. The X/Y position is provided for fouls, turnovers, and field-goal attempts (either 2-point or 3-point).
    • \n\n

    This is the diagram provided by the play-by-play source:

    \n\n\n
  • Area - for events where an X/Y position is provided, this position is more generally categorized into one of 13 \"areas\" of the court, as follows: \n1=under basket; \n2=in the paint; \n3=inside right wing; \n4=inside right; \n5=inside center; \n6=inside left; \n7=inside left wing; \n8=outside right wing; \n9=outside right; \n10=outside center; \n11=outside left; \n12=outside left wing; \n13=backcourt
    • \n
    \n

    Here is a diagram of these regions on a typical court:

    \n\n\n

    And you may also have noticed that the three-point-arc is different this year in college basketball. The width of the court is still 15.2 m (50 ft) and the length of the court is still 28.7 m (94 feet), but the distance to the arc has changed from 6.32 m (20 feet 9 inches) to 6.75 m (22.15 feet).

    \n\n

    Here is a diagram of the old court, which would apply for play-by-play in seasons 2019 and before:

    \n\n\n

    And here is a diagram of the new court, which only applies for season 2020:

    \n\n\n
    \n

    Data Section 5 file: MPlayers.csv

    \n\n\n

    Note: there are data collection errors within the events, in that they don't necessarily add up to the final stats for the game. In addition, the player name spellings may vary over the course of a season or career for the same player, which would lead to the same player showing up with different PlayerID values. Nevertheless, this was the highest quality data we could manage for play-by-play with the near-complete set of games.

    \n
    \n

    Data Section 6 - Supplements

    \n

    This section contains additional supporting information, including coaches, conference affiliations, alternative team name spellings, bracket structure, and game results for NIT and other postseason tournaments.

    \n
    \n

    Data Section 6 file: MTeamCoaches.csv

    \n

    This file indicates the head coach for each team in each season, including a start/finish range of DayNum's to indicate a mid-season coaching change. For scenarios where a team had the same head coach the entire season, they will be listed with a DayNum range of 0 to 154 for that season. For head coaches whose term lasted many seasons, there will be many rows listed, most of which have a DayNum range of 0 to 154 for the corresponding season.

    \n\n
    \n

    Data Section 6 file: Conferences.csv

    \n

    This file indicates the Division I conferences that have existed over the years since 1985. Each conference is listed with an abbreviation and a longer name. There has been no attempt to link up conferences who merged with other conferences, or whose names changed over time. Thus you will see, for instance, a \"Pacific-10\" conference up through the 2011 season, and then a \"Pacific-12\" conference starting in the 2012 season, and these look like different conferences in the data, even though it was still mostly the same teams. Please notice that the Cities and Conferences files are the only two that don't start with an M; this is because the data files are identical between men's and women's data, so you don't need to maintain separate listings of cities or conferences across the two contests. However, the Team Conferences data differs slightly between men's and women's, so those files do have the prefixes.

    \n
    \n

    Data Section 6 file: MTeamConferences.csv

    \n

    This file indicates the conference affiliations for each team during each season. Some conferences have changed their names from year to year, and/or changed which teams are part of the conference. This file tracks this information historically.

    \n
    \n

    Data Section 6 file: MConferenceTourneyGames.csv

    \n

    This file indicates which games were part of each year's post-season conference tournaments (all of which finished on Selection Sunday or earlier), starting from the 2001 season. Many of these conference tournament games are held on neutral sites, and many of the games are played by tournament-caliber teams just a few days before the NCAA® tournament. Thus these games could be considered as very similar to NCAA® tournament games, and (depending on your methodology) may be of use in optimizing your predictions. However, this is NOT a new listing of games; these games are already present within the MRegularSeasonCompactResults and MRegularSeasonDetailedResults files. So this file simply helps you to identify which of the \"regular season\" games since the 2001 season were actually conference tournament games, in case that is useful information.

    \n
    \n

    Data Section 6 file: MSecondaryTourneyTeams.csv

    \n

    This file identifies the teams that participated in post-season tournaments other than the NCAA® Tournament (such events would run in parallel with the NCAA® Tournament). These are teams that were not invited to the NCAA® Tournament and instead were invited to some other tournament, of which the NIT is the most prominent tournament, but there have also been the CBI, CIT, and Vegas 16 (V16) at various points in recent years. Depending on your methodology, you might find it useful to have these additional game results, above and beyond what is available from the NCAA® Tournament results. Many of these teams, especially in the NIT, were \"bubble\" teams of comparable strength to several NCAA® Tournament invitees, and so these games may be of use in model optimization for predicting NCAA® Tournament results. Also note that this information could be determined just from inspecting the MSecondaryTourneyCompactResults file, but is presented in this file as well, for your convenience.

    \n
    \n

    Data Section 6 file: MSecondaryTourneyCompactResults.csv

    \n

    This file indicates the final scores for the tournament games of \"secondary\" post-season tournaments: the NIT, CBI, CIT, and Vegas 16. The detailed results (team box scores) have not been assembled for these games. For the most part, this file is exactly like other Compact Results listings, although it also has a column for Secondary Tourney. Also note that because these games are played after DayNum=132, they are NOT listed in the MRegularSeasonCompactResults file.

    \n
    \n

    Data Section 6 file: MTeamSpellings.csv

    \n

    This file indicates alternative spellings of many team names. It is intended for use in associating external spellings against our own TeamID numbers, thereby helping to relate the external data properly with our datasets. Over the years we have identified various external spellings of different team names (as an example, for Ball State we have seen \"ball st\", and \"ball st.\", and \"ball state\", and \"ball-st\", and \"ball-state\"). Other teams have had more significant changes to their names over the years; for example, \"Texas Pan-American\" and \"Texas-Rio Grande Valley\" are actually the same school. The current list is obviously not exhaustive, and we encourage participants to identify additional mappings and upload extended versions of this file to the forums.

    \n
    \n

    Data Section 6 file: MNCAATourneySlots

    \n

    This file identifies the mechanism by which teams are paired against each other, depending upon their seeds, as the tournament proceeds through its rounds. It can be of use in identifying, for a given historical game, what round it occurred in, and what the seeds/slots were for the two teams (the meaning of \"slots\" is described below). Because of the existence of play-in games for particular seed numbers, the pairings have small differences from year to year. You may need to know these specifics if you are trying to represent/simulate the exact workings of the tournament bracket.

    \n
    \n

    Data Section 6 file: MNCAATourneySeedRoundSlots.csv

    \n

    This file helps to represent the bracket structure in any given year. No matter where the play-in seeds are located, we can always know, for a given tournament seed, exactly what bracket slot they would be playing in, on each possible game round, and what the possible DayNum values would be for that round. Thus, if we know when a historical game was played, and what the team's seed was, we can identify the slot for that game. This can be useful in representing or simulating the tournament bracket structure.

    \n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Description", "content": "## Update: this competition has been cancelled on account of the COVID-19 pandemic.\n\n

    As a result of the continued collaboration between Google Cloud and the NCAA®, the seventh annual Kaggle-backed March Madness® competition is underway! Another year, another chance to anticipate the upsets, call the probabilities, and put your bracketology skills to the leaderboard test. Kagglers will join the millions of fans who attempt to forecast the outcomes of March Madness during this year's NCAA Division I Men’s and Women’s Basketball Championships. But unlike most fans, you will pick your bracket using a combination of NCAA’s historical data and your computing power, while the ground truth unfolds on national television.\n\n

    \n

    \"March

    \n\n

    In the first stage of the competition, Kagglers will rely on results of past tournaments to build and test models. We encourage you to post any useful external data as a dataset.

    \n\n

    In the second stage, competitors will forecast outcomes of all possible matchups in the 2020 NCAA Division I Men’s and Women’s Basketball Championships. You don't need to participate in the first stage to enter the second. The first stage exists to incentivize model building and provide a means to score predictions. The real competition is forecasting the 2020 results.

    \n\n

    As the official public cloud provider of the NCAA, Google is proud to provide a competition to help participants strengthen their knowledge of basketball, statistics, data modeling, and cloud technology. As part of its journey to the cloud, the NCAA has migrated 80+ years of historical and play-by-play data, from 90 championships and 24 sports, to Google Cloud Platform (GCP). The NCAA has tapped into decades of historical basketball data using BigQuery, Cloud Spanner, Datalab, Cloud Machine Learning and Cloud Dataflow, to power the analysis of team and player performance. The mission of the NCAA has long been about serving the needs of schools, their teams and students. Google Cloud is proud to support that mission by helping the NCAA use data and machine learning to better engage with its millions of fans, 500,000 student-athletes, and more than 19,000 teams. Game on!

    \n\n

    This page is for the NCAA Division I Men's tournament. Check out the NCAA Division I Women's tournament here. If you want to extend your analysis then try out our Analytics Competition here

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

    Submissions are scored on the log loss:

    \n

    $$
    \\textrm{LogLoss} = - \\frac{1}{n} \\sum_{i=1}^n \\left[ y_i \\log(\\hat{y}_i) + (1 - y_i) \\log(1 - \\hat{y}_i)\\right],
    $$

    \n

    where

    \n\n

    The use of the logarithm provides extreme punishments for being both confident and wrong. In the worst possible case, a prediction that something is true when it is actually false will add an infinite amount to your error score. In order to prevent this, predictions are bounded away from the extremes by a small value.

    \n

    Submission File

    \n

    The file you submit will depend on whether the competition is in stage 1 (historical model building) or stage 2 (the 2020 tournament). Sample submission files will be provided for both stages. The format is a list of every possible matchup between the tournament teams. Since team1 vs. team2 is the same as team2 vs. team1, we only include the game pairs where team1 has the lower team id. For example, in a tournament of 68 teams (64 + 4 play-in teams), you will predict (68*67)/2 = 2,278 matchups.

    \n

    Each game has a unique id created by concatenating the season in which the game was played, the team1 id, and the team2 id. For example, \"2015_1107_1112\" indicates team 1107 potentially played team 1112 in the year 2015. You must predict the probability that the team with the lower id beats the team with the higher id.

    \n

    The resulting submission format looks like the following, where \"pred\" represents the predicted probability that the first team will win:

    \n
    id,pred
    2015_1107_1112,0.5
    2015_1107_1116,0.5
    2015_1107_1124,0.5
    ...
    ", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Timeline", "content": "**Updated March 13, 2020**: The following supersedes the respective terms outlined below. As a result of COVID-19, this competition will be cancelled with no Kaggle points, Kaggle medals, or monetary prizes. The end date has been updated from April 7, 2020 at 11:59pm UTC to March 19, 2020 at 3:00 am UTC. Please see this [announcement post](https://www.kaggle.com/c/google-cloud-ncaa-march-madness-2020-division-1-mens-tournament/discussion/135404) for more details.\n------\n

    Stage 1 - Model Building

    \n\n

    Stage 2 - Championship

    \n\n

    All deadlines are at 11:59 PM UTC on the corresponding day unless otherwise noted. The organizers reserve the right to update the contest timeline if they deem it necessary.

    ", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Prizes", "content": "### **Updated March 13, 2020**: The following supersedes the respective terms outlined below. As a result of COVID-19, this competition will be cancelled with no Kaggle points, Kaggle medals, or monetary prizes. The end date has been updated from April 7, 2020 at 11:59pm UTC to March 19, 2020 at 3:00 am UTC. Please see this [announcement post](https://www.kaggle.com/c/google-cloud-ncaa-march-madness-2020-division-1-mens-tournament/discussion/135404) for more details.\n\n* 1st Place - $10,000\n* 2nd Place - $7,000\n* 3rd Place - $5,000\n* 4th Place - $2,000\n* 5th Place - $1,000\n\n

    Stage 1 will not count towards Kaggle rankings/points.

    \n

    Stage 2 will count toward Kaggle rankings/points.

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

    Is one tournament enough to decide the best basketball algorithm?
    It's better to be lucky than good! Besides, when was the last time your office held a cross validation pool?

    \n

    Can I update my predictions after the tournament starts?
    No changes are permitted once the tournament begins.

    \n

    How is the leaderboard going to work when the event being scored hasn't yet happened?
    You won't submit after the tournament starts. We'll update the solution file as the games occur, which will cause the ranks on the leaderboard to change.

    \n

    Why do we have to predict every match up? Why 68 teams and not 64?
    This was done for timing purposes. Predicting every possible matchup for the 68 teams announced on Selection Sunday gives participants the most time to get their current year predictions ready in time. There is a small \"play-in\" round, sometimes called the first round, where the 68 are narrowed to 64. While you are asked to predict these games (and you may be predicting them after they occur), we will not be scoring them.

    \n

    Why don't predictions in later rounds count for more?
    While it is possible to weight the later games, we chose to keep scoring simple and count all games equally. Any weights we pick would be mostly arbitrary (how many first-round games is a championship game worth?). Also, weighting any game increases the role that luck plays in determining a winner. We've also structured the competition so that people can still be in the running even if there are early-round upsets.

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