{"id":16510399,"url":"https://github.com/romanlutz/nflplayprediction","last_synced_at":"2026-03-09T14:32:04.923Z","repository":{"id":88646079,"uuid":"44836517","full_name":"romanlutz/NFLPlayPrediction","owner":"romanlutz","description":"Based on NFL game data, we want to predict the success of a play. This can be used to insert different strategies before the play is called to determine the success probability.","archived":false,"fork":false,"pushed_at":"2016-12-21T06:12:02.000Z","size":8680,"stargazers_count":35,"open_issues_count":1,"forks_count":10,"subscribers_count":9,"default_branch":"master","last_synced_at":"2025-01-12T19:46:16.447Z","etag":null,"topics":["football","machine-learning","national-football-league","nfl","prediction","sports-science","sportsanalytics"],"latest_commit_sha":null,"homepage":null,"language":"OpenEdge ABL","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/romanlutz.png","metadata":{"files":{"readme":"README","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2015-10-23T20:22:20.000Z","updated_at":"2024-04-12T19:12:39.000Z","dependencies_parsed_at":null,"dependency_job_id":"9ea89379-416b-4df8-81e9-67590add457e","html_url":"https://github.com/romanlutz/NFLPlayPrediction","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/romanlutz%2FNFLPlayPrediction","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/romanlutz%2FNFLPlayPrediction/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/romanlutz%2FNFLPlayPrediction/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/romanlutz%2FNFLPlayPrediction/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/romanlutz","download_url":"https://codeload.github.com/romanlutz/NFLPlayPrediction/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":241474405,"owners_count":19968763,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["football","machine-learning","national-football-league","nfl","prediction","sports-science","sportsanalytics"],"created_at":"2024-10-11T15:55:00.372Z","updated_at":"2026-03-09T14:31:59.887Z","avatar_url":"https://github.com/romanlutz.png","language":"OpenEdge ABL","funding_links":[],"categories":[],"sub_categories":[],"readme":"Based on the statistics of all NFL seasons from 2009 to present, we'll try to predict the outcome of a play based on the situation and under the assumption of a certain play. This way, one could plug in every possible play and predict the best play to choose.\nPossible applications include participation in NFL call the play or even NFL Offensive Coordinators could use our prediction tool to find out what kind of play is the most promising.\n\nWe use the nflgame API that gets its data directly from NFL.com. The format is as follows:\n(DEN, DEN 22, Q4, 3 and 8) (4:42) (Shotgun) P.Manning pass short left to D.Thomas for 78 yards, TOUCHDOWN. Penalty on BAL-E.Dumervil, Defensive Offside, declined.\nHowever, there are lots of special cases and inconsistencies that we're removing or adjusting to get structured data.\n\nFeatures\n=========\n* Team\n* Opponent\n* Quarter\n* Time\n* Field position\n* Down\n* Yards to go\n* Shotgun formation (0/1)\n* Pass (0/1)\n* Side\n  -\u003e Pass: left / middle / right\n  -\u003e Run: left end / left tackle / left guard / middle / right guard / right tackle / right end\n* Pass length (short / deep)\n* QB Run (0/1)\n\nAfter filtering out irrelevant plays (special teams, \"No Play\"), we extracted information from the strings about the play. The labels show the success of the play, i.e. TD or not, how many yards, first down or not, possibly a combination of these (as a real value).\n\nOur Approach:\nFeature extraction: What features do we use? What plays are ignored?\nPrediction: Probability of success? What's a success? We use a variety of different measures for that.\n\nMachine Learning methods:\nClassification (Success / Fail): SVM, Nearest Neighbors, Decision Trees, Logistic Regression, Neural Nets\nRegression (Yards): SVR, Neural Nets, Linear Regression\nDimensionality reduction: PCA\nPrediction: Play with highest probability (or score?) of success\nEvaluation: k-fold cross validation\n\nInstallation:\nIn order to use our NFL Play Prediction, you will need to install the nflgame API with the following command:\nsudo pip install nflgame\nAnother requirement is the scikit-learn package for Machine Learning operations:\nsudo pip install scikit-learn\nIf you already have numpy and scipy installed, use the -U option in the previous command.\nIf you want to use the Neural Network prediction, you need to run this first:\neasy_install pybrain","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fromanlutz%2Fnflplayprediction","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fromanlutz%2Fnflplayprediction","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fromanlutz%2Fnflplayprediction/lists"}