{"id":21955265,"url":"https://github.com/mindawei/alimusic-predict","last_synced_at":"2025-03-22T18:51:08.992Z","repository":{"id":215749582,"uuid":"95952288","full_name":"mindawei/alimusic-predict","owner":"mindawei","description":"阿里音乐流行趋势预测大赛代码（包括初赛、复赛）","archived":false,"fork":false,"pushed_at":"2018-01-28T08:22:15.000Z","size":149,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-01-27T23:15:32.885Z","etag":null,"topics":["data","java","predict","pyhton","tianchi"],"latest_commit_sha":null,"homepage":"","language":"Java","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/mindawei.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":"2017-07-01T08:34:56.000Z","updated_at":"2024-07-02T03:51:07.000Z","dependencies_parsed_at":null,"dependency_job_id":"c7e3871d-f611-46ce-a71b-c8bfe827710c","html_url":"https://github.com/mindawei/alimusic-predict","commit_stats":null,"previous_names":["mindawei/alimusic-predict"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mindawei%2Falimusic-predict","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mindawei%2Falimusic-predict/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mindawei%2Falimusic-predict/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mindawei%2Falimusic-predict/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mindawei","download_url":"https://codeload.github.com/mindawei/alimusic-predict/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245007170,"owners_count":20546143,"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","java","predict","pyhton","tianchi"],"created_at":"2024-11-29T07:30:44.508Z","updated_at":"2025-03-22T18:51:08.972Z","avatar_url":"https://github.com/mindawei.png","language":"Java","funding_links":[],"categories":[],"sub_categories":[],"readme":"# alimusic-predict\n[阿里音乐流行趋势预测大赛](https://tianchi.aliyun.com/competition/information.htm?spm=5176.100067.5678.2.4c5fd3bez7WUi\u0026raceId=231531)比赛要求参赛者利用阿里音乐用户前 6 个月的播放数据预测未来 2 个月的播放情况。本人在比赛中负责数据的清洗和平滑、规则的编写。初赛排名第216名（前500名进入复赛），复赛排名第 12（共 5476 队），获得极客奖。\n\n## alimusic-predict-1\u003cbr\u003e\n这是初赛代码（Python）,解题思路：进行数据分析，清理异常值，构造数据特征，调用一些模型（GBDT,随机深林）进行预测。\n\n## alimusic-predict-2\u003cbr\u003e\n这是复赛代码（Java）,解题思路：由于数据质量不高，均值预测效果较好。趋势的反映可以制定相关规则实现。\n\n## 总结\n* 基本概念一定要清晰：其他选手会将一些输入输出公式化；宏观问题不适合使用微观因素，因为缺少部分它们之间的相互关系。\n* 分类效率不高：我们使用一些规则、人工进行判断 \u003c-\u003e 对方 GBDT 进行分类\n* 预测模型：我们是直线 \u003c-\u003e 对方是V字型\n* 公式观察：没有观察 \u003c-\u003e 对方分析，公式来看偏小值进行预测比偏大值预测分数高\n* 提交问题：直观分析 \u003c-\u003e 记录每次提交的详细信息，并分析分数变动的原因；为了一些未知的部分，可以设定值去试\n* 其他：对手模型融合增加鲁棒性；分类部分GBDT基本默认参数；数据清洗；充分运用均值、中位数等\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmindawei%2Falimusic-predict","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmindawei%2Falimusic-predict","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmindawei%2Falimusic-predict/lists"}