{"id":17216929,"url":"https://github.com/lenguyenthedat/dextra-mindef-2015","last_synced_at":"2025-07-02T09:03:45.500Z","repository":{"id":36840331,"uuid":"41147250","full_name":"lenguyenthedat/dextra-mindef-2015","owner":"lenguyenthedat","description":"My solution for Dextra Data Science Challenge #44 (Singapore Ministry of Defense) https://challenges.dextra.sg/challenge/44","archived":false,"fork":false,"pushed_at":"2020-04-18T09:38:29.000Z","size":19439,"stargazers_count":8,"open_issues_count":0,"forks_count":3,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-06-08T17:40:31.913Z","etag":null,"topics":["classification","data-science","machine-learning","xgboost"],"latest_commit_sha":null,"homepage":null,"language":"Python","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/lenguyenthedat.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}},"created_at":"2015-08-21T09:20:43.000Z","updated_at":"2020-04-18T09:37:39.000Z","dependencies_parsed_at":"2022-08-24T21:11:03.423Z","dependency_job_id":null,"html_url":"https://github.com/lenguyenthedat/dextra-mindef-2015","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/lenguyenthedat/dextra-mindef-2015","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lenguyenthedat%2Fdextra-mindef-2015","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lenguyenthedat%2Fdextra-mindef-2015/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lenguyenthedat%2Fdextra-mindef-2015/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lenguyenthedat%2Fdextra-mindef-2015/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/lenguyenthedat","download_url":"https://codeload.github.com/lenguyenthedat/dextra-mindef-2015/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lenguyenthedat%2Fdextra-mindef-2015/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":263108752,"owners_count":23415001,"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":["classification","data-science","machine-learning","xgboost"],"created_at":"2024-10-15T03:42:46.349Z","updated_at":"2025-07-02T09:03:45.480Z","avatar_url":"https://github.com/lenguyenthedat.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"Ministry of Defence Data Analytics Challenge\n============================================\n![img](https://github.com/lenguyenthedat/dextra-mindef-2015/blob/master/data/Challenge%20Banner.png?raw=true)\n\n![img](https://github.com/lenguyenthedat/dextra-mindef-2015/blob/master/data/Winning%20Team.png?raw=true)\n\n**Note**: A few people asked me for the challenge's data source. Unfortunately, I am not authorized to publicly release it - if you need it, please do send the request to either Mindef or Dextra.sg instead of sending it to me.\n\nChallenge URL: http://www.dextra.sg/ministry-of-defence-data-analytics-challenge/\n\nQuick analysis with Tableau Public [Removed due to non-disclosure agreement] \n\nLibraries used: Scikit-Learn, Pandas, XGBoost, Mathplotlib\n\nScores:\n-------\n[Public Leader Board (5th/158 Participants)](https://challenges.dextra.sg/challenge/44)\n\n- 0.0169515: best Single XGBoost model\n- 0.0168939: blending multiple XGBoost models with different Features Set.\n\n[Private Leader Board (1st/158 Participants)](http://www.dextra.sg/mindef-challenge-results/)\n\n- 0.0141351 \n\nSubmission History (only the best one):\n---------------------------------------\nOnly Native XGBoost was recorded since it just dominated everything.\n\n1) Public Leader Board 0.0171364\n\n    $ python classify-xgb-native.py # 990r depth6\n    0.0155765992602\n    0.019516592639\n    0.00988590074655\n    0.0141124661651\n    0.014303086534\n    Mean: 0.014678929069 (Local Score)\n\n2) Public Leader Board 0.0172253\n\n    $ python classify-xgb-native.py # 180r\n    0.0157726389016\n    0.0201645979107\n    0.0095532522597\n    0.013888759618\n    0.0139117869773\n    Mean: 0.0146582071335 (Local Score)\n\n3) Public Leader Board 0.0171475\n\n    $ python classify-xgb-native.py #added age_gender, rm a bunch of features\n    0.015551655811\n    0.019148557532\n    0.00965389534226\n    0.0139233429833\n    0.0139280448029\n    Mean: 0.0144410992943 (Local Score)\n\n4) Public Leader Board 0.0171112\n\n    $ python classify-xgb-native.py # promo - gender\n    0.0155083548415\n    0.0189263516813\n    0.00951782504063\n    0.0140093232169\n    0.014178032663\n    Mean: 0.0144279774887 (Local Score)\n\n5) Public Leader Board 0.0170703\n\n    $ python classify-xgb-native.py # cap salary 101%\n    0.0153414063482\n    0.0189991328711\n    0.00959486331913\n    0.0139794582592\n    0.0140253377611\n    Mean: 0.0143880397117 (Local Score)\n\n6) Public Leader Board 0.0170369\n\n    $ python classify-xgb-native.py # INJURY TYPE as String\n    0.0153022751895\n    0.0189944794534\n    0.00957494483944\n    0.0139220394066\n    0.014069437855\n    Mean: 0.0143726353488 (Local Score)\n\n7) Public Leader Board 0.0169515\n\n    $ python classify-xgb-native.py # better minchildage # treat as str\n    0.0152455036731\n    0.0189285563506\n    0.00961418416464\n    0.0139189502782\n    0.0139664367926\n    Mean: 0.0143347262518 (Local Score)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flenguyenthedat%2Fdextra-mindef-2015","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flenguyenthedat%2Fdextra-mindef-2015","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flenguyenthedat%2Fdextra-mindef-2015/lists"}