├── contributing.md └── README.md /contributing.md: -------------------------------------------------------------------------------- 1 | #### Since there isn't a lot for me to manage, you can simply open an issue with a request label. 2 | example. https://github.com/AtomScott/awesome-sports-analytics/issues/1 3 | 4 |
5 | 6 | # Contribution Guidelines 7 | 8 | **Your pull request should have a useful title. Please carefully read everything in [Adding to this list](#adding-to-this-list).** 9 | 10 | ## Table of Contents 11 | 12 | - [Adding to this list](#adding-to-this-list) 13 | - [Creating your own awesome list](#creating-your-own-awesome-list) 14 | - [Adding something to an awesome list](#adding-something-to-an-awesome-list) 15 | - [Updating your Pull Request](#updating-your-pull-request) 16 | 17 | ## Adding to this list 18 | 19 | Please ensure your pull request adheres to the following guidelines: 20 | 21 | - Search previous suggestions before making a new one, as yours may be a duplicate. 22 | - Make sure the item you are adding is useful (and, you know, awesome) before submitting. 23 | - Make an individual pull request for each suggestion. 24 | - Use [title-casing](http://titlecapitalization.com) (AP style). 25 | - Use the following format: `[Item Name](link)` 26 | - Link additions should be added to the bottom of the relevant category. 27 | - New categories or improvements to the existing categorization are welcome. 28 | - Check your spelling and grammar. 29 | - Make sure your text editor is set to remove trailing whitespace. 30 | - The pull request and commit should have a useful title. 31 | - The body of your commit message should contain a link to the repository. 32 | 33 | Thank you for your suggestions! 34 | 35 | ## Adding something to an awesome list 36 | 37 | If you have something awesome to contribute to an awesome list, this is how you do it. 38 | 39 | You'll need a [GitHub account](https://github.com/join)! 40 | 41 | 1. Access the awesome list's GitHub page. For example: https://github.com/sindresorhus/awesome 42 | 2. Click on the `readme.md` file: ![Step 2 Click on Readme.md](https://cloud.githubusercontent.com/assets/170270/9402920/53a7e3ea-480c-11e5-9d81-aecf64be55eb.png) 43 | 3. Now click on the edit icon. ![Step 3 - Click on Edit](https://cloud.githubusercontent.com/assets/170270/9402927/6506af22-480c-11e5-8c18-7ea823530099.png) 44 | 4. You can start editing the text of the file in the in-browser editor. Make sure you follow guidelines above. You can use [GitHub Flavored Markdown](https://help.github.com/articles/github-flavored-markdown/). ![Step 4 - Edit the file](https://cloud.githubusercontent.com/assets/170270/9402932/7301c3a0-480c-11e5-81f5-7e343b71674f.png) 45 | 5. Say why you're proposing the changes, and then click on "Propose file change". ![Step 5 - Propose Changes](https://cloud.githubusercontent.com/assets/170270/9402937/7dd0652a-480c-11e5-9138-bd14244593d5.png) 46 | 6. Submit the [pull request](https://help.github.com/articles/using-pull-requests/)! 47 | 48 | ## Updating your Pull Request 49 | 50 | Sometimes, a maintainer of this list will ask you to edit your Pull Request before it is included. This is normally due to spelling errors or because your PR didn't match the awesome-* list guidelines. [Here is a write up on how to change a Pull Request](https://github.com/RichardLitt/docs/blob/master/amending-a-commit-guide.md), and the different ways you can do that. 51 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Awesome Sports Analytics: [![Awesome](https://awesome.re/badge.svg)](https://awesome.re) 2 | 3 | A curated list of awesome machine learning applications in the sports domain. 4 | An up to date version of this awesome list can be found [here](https://atomscott.me/Awesome-Sports-Analytics-a1a6595efc6e498b8a827dc72179239e) 5 | (I'll be writing in this notion page for the time being). 6 | 7 | [![HitCount](http://hits.dwyl.com/AtomScott/awesome-sports-analytics.svg)](http://hits.dwyl.com/AtomScott/awesome-sports-analytics) 8 | 9 | ## Contributing 10 | 11 | Check the [contribution guidelines](https://github.com/AtomScott/awesome-sports-analytics/blob/master/contributing.md). 12 | Or DM me on [twitter](https://twitter.com/AtomJamesScott) for a ~~fast~~ response. 13 | 14 | ## Table of Contents 15 | 16 | - [People](https://www.notion.so/atomscott/Awesome-S-8e673396ce474d059b5f5d4558d153ea#People) 17 | - [Books](https://www.notion.so/atomscott/Awesome-S-8e673396ce474d059b5f5d4558d153ea#books) 18 | - [Papers](https://www.notion.so/atomscott/Awesome-S-8e673396ce474d059b5f5d4558d153ea#papers) 19 | - [Software](https://www.notion.so/atomscott/Awesome-S-8e673396ce474d059b5f5d4558d153ea#software) 20 | - [Datasets](https://www.notion.so/atomscott/Awesome-S-8e673396ce474d059b5f5d4558d153ea#datasets) 21 | - [Tutorials and Talks](https://www.notion.so/atomscott/Awesome-S-8e673396ce474d059b5f5d4558d153ea#tutorials-and-talks) 22 | - [Resources for students](https://www.notion.so/atomscott/Awesome-S-8e673396ce474d059b5f5d4558d153ea#resources-for-students) 23 | - [Blogs](https://www.notion.so/atomscott/Awesome-S-8e673396ce474d059b5f5d4558d153ea#blogs) 24 | - [Links](https://www.notion.so/atomscott/Awesome-S-8e673396ce474d059b5f5d4558d153ea#links) 25 | 26 | ## People 27 | 28 | - Kyle Boddy - sabermetrics 29 | - Patrick Lucey - Chief Scientist at Stats Perform 30 | - David Sumpter - Soccermatics Author 31 | - William Spearman - Liverpool Analytics 32 | - Javier Fernandez - Barcalona Analytics 33 | - Luke Bornn - Sim Fraser University 34 | - Keita Watanabe - Japanese Volley Ball 35 | - Tom Decroos - Soccer data analytics researcher 36 | 37 | ## Books 38 | 39 | - Handbook of Statistical Methods and Analyses in Sports (Chapman & Hall/CRC Handbooks of Modern Statistical Methods) 1st Edition 40 | 41 | ## Papers 42 | 43 | ### Player Evaluation 44 | 45 | - Actions Speak Louder than Goals: Valuing Player Actions in Soccer (KDD 2019) 46 | **Best Paper**, Applied Data Science Track 47 | - Player Vectors: Characterizing Soccer Players’ Playing Style from Match Event Streams (ECML PKDD 2019) 48 | 49 | ### Team Evaluation 50 | 51 | - Automatic Discovery of Tactics in Spatio-Temporal Soccer Match Data 52 | - Spatio-temporal Analysis of Tennis Matches 53 | 54 | ### Result Prediction 55 | 56 | ### Player/Ball Tracking 57 | 58 | - DeepBall: Deep Neural-Network Ball Detector (VISIGRAPP 2019) 59 | - Towards Real-Time Detection and Tracking of Basketball Players using Deep Neural Networks (NIPS 2017) 60 | 61 | ### Action / Event Detection 62 | 63 | - Predicting soccer highlights from spatio-temporal match event streams (AAAI 2017) [link] 64 | - A Context-Aware Loss Function for Action Spotting in Soccer Videos (CVPR 2020) [[link](https://arxiv.org/pdf/1704.02581.pdf)] 65 | 66 | ### Future Trajectory 67 | 68 | - Predicting Wide Receiver Trajectories in American Football (IEEE WACV 2016) 69 | - Coordinated Multi-Agent Imitation Learning (ICML 2017) 70 | - Neural Relational Inference for Interacting Systems (ICML 2018) 71 | - Long Range Sequence Generation via Multiresolution Adversarial Training (NIPS 2018) 72 | - Where Will They Go? Predicting Fine-Grained Adversarial Multi-Agent Motion using Conditional Variational Autoencoders (ECCV 2018) 73 | - Generating Defensive Plays in Basketball Games (ACM MM 2018) 74 | - Generating Multi-Agent Trajectories using Programmatic Weak Supervision (ICLR 2019) 75 | - Stochastic Prediction of Multi-Agent Interactions from Partial Observations (ICLR 2019) 76 | - Diverse Generation for Multi-agent Sports Games (CVPR 2019) 77 | - DAG-Net: Double Attentive Graph Neural Network for Trajectory Forecasting (2020) 78 | - VAIN: Attentional Multi-agent Predictive Modeling (NIPS 2020) 79 | 80 | ### Other 81 | 82 | - Winning a Tournament by Any Means Necessary (IJCAI 2018) [[link](https://www.researchgate.net/profile/Sanjukta_Roy2/publication/326205400_Winning_a_Tournament_by_Any_Means_Necessary/links/5c3e7b18458515a4c7294f83/Winning-a-Tournament-by-Any-Means-Necessary.pdf)] 83 | 84 | ## Software 85 | 86 | - Python - High-level programming language. Norm for ML/DL research 87 | - R - Language for statistical computing and graphics 88 | - D3.js - Javascript library (nearly a language of its own) for cool vizualizations 89 | - Tableau - Data analysis software 90 | - Excel - Spreadsheet software from microsoft 91 | - 92 | 93 | ## Datasets 94 | 95 | **Soccer** 96 | 97 | - StatsBomb Open Data [[link](https://github.com/statsbomb/open-data)] 98 | - football.db [[link](https://openfootball.github.io/)] 99 | - FIFA 19 complete player dataset [[link](https://www.kaggle.com/karangadiya/fifa19)] 100 | - Fifa 18 More Complete Player Dataset [[link](https://www.kaggle.com/kevinmh/fifa-18-more-complete-player-dataset)] 101 | - FIFA World Cup [[link](https://www.kaggle.com/abecklas/fifa-world-cup)] 102 | - International football results from 1872 to 2020 [[link](https://www.kaggle.com/martj42/international-football-results-from-1872-to-2017)] 103 | - Wyscout (paid) 104 | 105 | **Basketball** 106 | 107 | - NBA shot logs [[link](https://www.kaggle.com/dansbecker/nba-shot-logs)] 108 | - NBA player of the week [[link](https://www.kaggle.com/jacobbaruch/nba-player-of-the-week)] 109 | - Daily Fantasy Basketball - DraftKings NBA [[link](https://www.kaggle.com/alandu20/daily-fantasy-basketball-draftkings)] 110 | - NCAA Basketball [[link](https://www.kaggle.com/ncaa/ncaa-basketball)] 111 | 112 | **American Football** 113 | 114 | - Detailed NFL Play-by-Play Data 2009-2018 [[link](https://www.kaggle.com/maxhorowitz/nflplaybyplay2009to2016)] 115 | - [NFLsavant.com](http://nflsavant.com) [[link](http://nflsavant.com/about.php)] 116 | 117 | **Baseball** 118 | 119 | - Lahman’s Baseball Database [[link](http://www.seanlahman.com/baseball-archive/statistics/)] 120 | 121 | **Hockey** 122 | 123 | - NHL Game Data [[link](https://www.kaggle.com/martinellis/nhl-game-data)] 124 | 125 | **Other** 126 | 127 | - FiveThirtyEight [[link](https://github.com/fivethirtyeight/data)] 128 | - Sports-1M [[link](https://cs.stanford.edu/people/karpathy/deepvideo/index.html)] 129 | - 120 years of Olympic history: athletes and results [[link](120 years of Olympic history: athletes and results)] 130 | 131 | ## Tutorials and Talks 132 | 133 | - International Workshop on Computer Vision in Sports at CVPR [[2013]](https://vap.aau.dk/cvsports/1st-ieee-internation-workshop-on-computer-vision-in-sports-at-cvpr-2013/) [[2015]](https://vap.aau.dk/cvsports/2nd/) [[2017]](https://vap.aau.dk/cvsports/3rd-ieee-international-workshop-in-computer-vision-in-sports-at-cvpr-2017/) [[2018](https://vap.aau.dk/cvsports/4th-ieee-international-workshop-on-computer-vision-in-sports-at-cvpr-2018/)] [[2019]](https://vap.aau.dk/cvsports/5th-ieee-international-workshop-on-computer-vision-in-sports-at-cvpr-2019/) 134 | - AAAI Workshop on AI in Team Sports [[2020](https://ai-teamsports.weebly.com/schedule.html)] 135 | - MIT Sloan Sports Analytics Conference [[2020](http://www.sloansportsconference.com/2020-conference/2020-research-paper-finalists-posters/)] 136 | SSAC don't seem to archive past conferences so search Google Scholar with `source:MIT Sloan Sports Analytics Conference` like [th](source:MIT Sloan Sports Analytics Conference)[i](https://scholar.google.com/scholar?q=source%3AMIT+Sloan+Sports+Analytics+Conference&hl=en&as_sdt=0%2C5&as_ylo=2011&as_yhi=2012)[s](source:MIT Sloan Sports Analytics Conference) and you should get around a hundred results. 137 | - Workshop on Machine Learning and Data Mining for Sports Analytics [[2019](https://dtai.cs.kuleuven.be/events/MLSA19/submission.php)] [[2018](https://dtai.cs.kuleuven.be/events/MLSA18/)] 138 | - Workshop on Large-Scale Sports Analytics [[2016](https://www.euro-online.org/websites/orinsports/event/kdd-2016-workshop-on-large-scale-sports-analytics/)] 139 | 140 | ## Resources for students 141 | 142 | ## Webstites/Blogs/Youtube 143 | 144 | ## Other 145 | 146 | ## ※ Notes 147 | 148 | Leave out stuff like, 149 | 150 | - Robo-Sports: So many papers, especially RoboCup, not sure which are important. 151 | - Coaching/Physiology/Medicine: Fast twitch, ATP, periodization, creatine etc. New methods + lots of data might provide insight but it's too broad. 152 | - Pose estimation/Object Detection: Too general. There are awesome lists specifically for those areas already. 153 | - Low impact research: I can't include everything! 154 | --------------------------------------------------------------------------------