{"id":28225843,"url":"https://github.com/krishnaura45/bracket-brain","last_synced_at":"2026-02-06T17:03:33.850Z","repository":{"id":288668131,"uuid":"968444560","full_name":"krishnaura45/bracket-brain","owner":"krishnaura45","description":"🏆Basketball Predictions 🧪 Ensemble and GOTO Techniques","archived":false,"fork":false,"pushed_at":"2025-06-06T14:29:59.000Z","size":3075,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-07-04T10:43:03.301Z","etag":null,"topics":["basketball","betting-odds","bracket","brier-scores","featured","kaggle-competition","march-madness","ml","sports"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"cc0-1.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/krishnaura45.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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,"zenodo":null}},"created_at":"2025-04-18T05:20:33.000Z","updated_at":"2025-06-06T14:30:01.000Z","dependencies_parsed_at":"2025-06-13T00:32:04.405Z","dependency_job_id":"6edf99f3-169f-47a3-b021-6d3988e9b1b4","html_url":"https://github.com/krishnaura45/bracket-brain","commit_stats":null,"previous_names":["krishnaura45/bracket-brain"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/krishnaura45/bracket-brain","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/krishnaura45%2Fbracket-brain","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/krishnaura45%2Fbracket-brain/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/krishnaura45%2Fbracket-brain/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/krishnaura45%2Fbracket-brain/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/krishnaura45","download_url":"https://codeload.github.com/krishnaura45/bracket-brain/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/krishnaura45%2Fbracket-brain/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29169384,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-06T16:33:35.550Z","status":"ssl_error","status_checked_at":"2026-02-06T16:33:30.716Z","response_time":59,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["basketball","betting-odds","bracket","brier-scores","featured","kaggle-competition","march-madness","ml","sports"],"created_at":"2025-05-18T11:09:42.925Z","updated_at":"2026-02-06T17:03:33.833Z","avatar_url":"https://github.com/krishnaura45.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🏀bracket-brain\nForecasting NCAA basketball tournament outcomes using machine learning models to support bracket predictions and sports analytics.\n\n![Python](https://img.shields.io/badge/Python-3776AB?style=for-the-badge\u0026logo=python\u0026logoColor=white)\n![Kaggle](https://img.shields.io/badge/Kaggle-20BEFF?style=for-the-badge\u0026logo=kaggle\u0026logoColor=white)\n![Scikit-Learn](https://img.shields.io/badge/Scikit--Learn-F7931E?style=for-the-badge\u0026logo=scikit-learn\u0026logoColor=white)\n![Brier Score Optimized](https://img.shields.io/badge/Optimized--for-Brier%20Score-yellowgreen?style=for-the-badge)\n![Metric Score](https://img.shields.io/badge/Best%20Score-0.10921-2ECC71?style=for-the-badge)\n![Rank](https://img.shields.io/badge/Rank-53%20of%201727-brightgreen?style=for-the-badge)\n![Solo](https://img.shields.io/badge/Submission-Solo-orange?style=for-the-badge)\n\n### **Project Duration**: Mar 17, 2025 - Apr 7, 2025\n\n---\n\n## 🧠 Problem Statement\n\nThe aim of this competition was to predict the outcomes of all potential matchups in the 2025 NCAA Division I men’s and women’s basketball tournaments. Each submission included predicted probabilities for every possible matchup that could occur in the tournament brackets. \n\nHosted on Kaggle as part of the annual **March Machine Learning Mania**, submissions were evaluated using the **Brier score**, which penalizes inaccurate probability predictions. Lower Brier scores indicate better predictions.\n\n---\n\n## 🧩 Approach\n\nYou can explore the complete methodology in this notebook: 🔗 [MMLM25 - EDA and Prediction](https://github.com/krishnaura45/bracket-brain/blob/main/mmlm25-eda-pred.ipynb)\n\nKey steps followed:\n\n- 📊 **Exploratory Data Analysis (EDA)**:\n  - Understood tournament structure, team seeding, and regional splits.\n  - Analyzed match histories and evaluated metrics such as `ScoreDiff`, `SeedDiff`, and team-level historical performance.\n  - Assessed other features such as win-loss records, and scoring statistics.\n\n- 🧠 **GOTO Model**:\n  - Utilized the goto_conversion method to convert betting odds into outcome probabilities.\n  - This method adjusts inverse odds by the same units of standard error, effectively addressing the favourite-longshot bias by considering the proportionately wider standard errors implied for inverses of longshot odds and vice versa.\n\n- 🧪 **Prediction \u0026 Submission**:\n  - Mapped test data using team identifiers from the sample submission file.\n  - Applied the converted probabilities to predict outcomes for every possible tournament matchup.\n  - Ensured that the predictions accounted for the inherent biases in betting markets, leading to more accurate forecasts.\n\n---\n\n## 🏆 Results / Outcomes\n\n- ✅ **Public Leaderboard Scores**:\n  - Achieved **0.12453** and **0.10921** Brier scores.\n\n- 🏁 **Private Leaderboard Score**:\n  - Final score: **0.10921** on hidden test data.\n\n- 🥇 **Rank Achieved**:\n  - Placed **53rd out of 1,986 participants** and **1,727 teams** as a **solo participant**.\n\n---\n\n## 🔗 References\n\n- 🏆 Kaggle Competition: [March Machine Learning Mania 2025](https://www.kaggle.com/competitions/march-machine-learning-mania-2025)\n- 📁 Dataset: [Competition Data](https://www.kaggle.com/competitions/march-machine-learning-mania-2025/data)\n- 🗒️ Helpful Notebooks:\n  - [MMLM - Starter by Paul](https://www.kaggle.com/code/paultimothymooney/simple-starter-notebook-for-march-mania-2025)\n  - [Vilnius NCAA by Raddar](https://www.kaggle.com/code/jocelyndumlao/march-ml-mania-2025-brier-score-prediction)\n- 📦 `goto_conversion` Package: [GitHub repo](https://github.com/gotoConversion/goto_conversion)\n\n---\n\n## 🛠️ Tech Stack\n\n- **Language**: Python 🐍\n- **Libraries**:\n  - `pandas`, `numpy` for data manipulation\n  - `matplotlib`, `seaborn` for visualization\n- **Tools**:\n  - Jupyter Notebook 📓 for development\n  - Kaggle Kernels / Google Colab for experimentation and submission\n\n---\n\n📌 *This project highlights the effectiveness of advanced odds conversion techniques, like goto_conversion, in improving the accuracy of probabilistic forecasts for sports tournaments.*\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkrishnaura45%2Fbracket-brain","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkrishnaura45%2Fbracket-brain","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkrishnaura45%2Fbracket-brain/lists"}