获得了EMI Music Recommendation Hackathon冠军
来源:互联网 发布:算法那本书好 编辑:程序博客网 时间:2024/05/16 09:49
很高兴这次最终获得了Hackathon的冠军!我们音乐预测算法的精度达到了RMSE=13.24598
SVD++的implicit feedbacks这次并没有发挥很大的作用,相反,words里的86列feature有很大的帮助,用在了Logistic Regression中,另外,user的各种profile和item,artist的关系组合,也带来了很好的效果
比赛介绍如下:
COMPETITION GOAL
Can you predict if a listener will love a new song?
“Soulful” ... “Catchy” ... “Cool" ... "Cheesy" ... "Edgy”
How do people connect to and describe the music they have just heard?
EMI Insight performs extensive market research about their artists by interviewing thousands of people around the world. This research has produced EMI One Million Interview Dataset; one of the largest music preference datasets in the world today, that connects data about people--who they are, where they live, how they engage with music in their daily lives-- with their opinions about EMI’s artists.
This Data Science London hackathon will focus on one key subset of this data: understanding what it is about people and artists that predicts how much people are going to like a particular track. We have taken a sample of the data from the United Kingdom that provides a granular mixture of profile, word-association, and rating data.
The goal of this weekend hackathon is to design an algorithm that combines users’ (a) demographics, (b) artist and track ratings, (c) answers to questions about their preferences for music, and (d) words that they use to describe EMI artists in order to predict how much they like tracks they have just heard.
There is also a Visualization thread where you can submit your most amazing Music-Data Viz and view and vote on other contestants' entries. Go to 'Prospect' at the top of this page. Submissision will open at the same time as the competition.
(Data will be made available 24 hours prior to the start of the contest)
For more info http://musicdatascience.com/
hashtag #musicdata #ds_ldn #DSGhack
Proudly brought to you by
- 获得了EMI Music Recommendation Hackathon冠军
- EMI Music Data Science Hackathon冠军团队的技术报告
- Music recommendation algorithm
- Deep content-based music recommendation
- nips 2013笔记(1)-Deep content-based music recommendation
- EMI
- 很高兴获得了CIKM Competition数据挖掘竞赛的冠军
- Apple, EMI enter pact for DRM-less music——Apple和EMI公司联合制作DRM音乐
- Recommendation
- WCG2008世界总决赛Moon VS Grubby,太精彩了,恭喜Grubby第二次获得WCG世界总决赛冠军
- 韩国黑客获得国际黑客大赛冠军
- 如何在 ImageNet 比赛中获得冠军?
- FLYME HACKATHON
- Music
- music
- music
- music~~
- Music
- 获取硬盘的详细信息
- 新一代视频编码HEVC标准 简介
- android 点击notification只启动一个activity
- 关于加班这件事吐槽两句-加班的种类划分
- DBA_SEGMENTS 数据字典 块数量和发生变化情况
- 获得了EMI Music Recommendation Hackathon冠军
- javascript中window窗体对象open()和showModalDialog()用法
- USB系统设备模型建立流程
- Ubuntu下,分别用ibus和scim安装极点五笔
- hdu1385
- Unity3d_获取系统地址
- [转载]Oracle Decode函数详解
- 内存堆栈
- Selenium tips