{"id":15158038,"url":"https://github.com/estaheri7/dotawinpredictor","last_synced_at":"2026-03-09T05:32:13.609Z","repository":{"id":254087184,"uuid":"844175079","full_name":"Estaheri7/DotaWinPredictor","owner":"Estaheri7","description":"This project aims to predict the outcome of Dota 2 matches based on the heroes picked by both the Radiant and Dire teams","archived":false,"fork":false,"pushed_at":"2024-08-21T09:17:36.000Z","size":385,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-01-31T02:15:59.394Z","etag":null,"topics":["data-science","dota2","machine-learning","numpy","pandas","python","random-forest","sklearn","support-vector-machines"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/Estaheri7.png","metadata":{"files":{"readme":"README.md","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":"2024-08-18T15:56:53.000Z","updated_at":"2024-08-21T09:17:39.000Z","dependencies_parsed_at":"2024-08-21T10:43:32.655Z","dependency_job_id":"9c5a3840-c040-4fa3-bd3a-88b578bd22d6","html_url":"https://github.com/Estaheri7/DotaWinPredictor","commit_stats":null,"previous_names":["estaheri7/dotawinpredictor"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Estaheri7%2FDotaWinPredictor","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Estaheri7%2FDotaWinPredictor/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Estaheri7%2FDotaWinPredictor/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Estaheri7%2FDotaWinPredictor/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Estaheri7","download_url":"https://codeload.github.com/Estaheri7/DotaWinPredictor/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":237982421,"owners_count":19397254,"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":["data-science","dota2","machine-learning","numpy","pandas","python","random-forest","sklearn","support-vector-machines"],"created_at":"2024-09-26T20:22:03.353Z","updated_at":"2025-10-24T14:31:28.412Z","avatar_url":"https://github.com/Estaheri7.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Dota 2 Match Outcome Prediction\n\n## Overview\n\nThis project aims to predict the outcome of [Dota 2](https://www.dota2.com/home) matches based on the heroes picked by both the Radiant and Dire teams. Using machine learning techniques, we train a model to determine the likelihood of either team winning given the heroes selected during the drafting phase.\n\n## Project Structure\n\n- **Data Collection**: We collect match data, including the heroes picked by both teams and the match outcome, using the [OpenDota API](https://docs.opendota.com).\n- **Data Preprocessing**: The hero IDs for both teams are encoded using one-hot encoding to create a feature set for machine learning models.\n- **Model Training**: A machine learning model is trained on the preprocessed data to predict the match outcome.\n- **Prediction**: The trained model is used to predict the outcome of new matches based on the heroes picked.\n\n## Data Directory\n  \n- **data/**\n  - `matches.csv`: Collected match data including match IDs, hero picks, and match outcomes.\n  - `heroes.csv`: List of Dota 2 heroes with their corresponding IDs.\n\n## Notes\n\n- The OpenDota API may return the same match details if queried too frequently. It is recommended to space out API requests to avoid collecting duplicate data.\n- The model's performance may vary depending on the amount and quality of data collected. Experimenting with different machine learning algorithms and hyperparameters is encouraged.\n\n## Future Work\n\n- **Feature Engineering**: Explore additional features such as player rankings, hero synergy, and counter-picks to improve model accuracy.\n- **Model Optimization**: Experiment with different machine learning algorithms and techniques like cross-validation, hyperparameter tuning, and ensemble methods.\n- **Real-time Prediction**: Integrate the model with live match data to provide real-time win probability predictions during ongoing matches.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Festaheri7%2Fdotawinpredictor","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Festaheri7%2Fdotawinpredictor","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Festaheri7%2Fdotawinpredictor/lists"}