基于随机森林和极限学习机算法融合的动漫用户性别识别
首发时间:2017-12-06
摘要:近年来动漫业务快速发展,动漫用户逐渐增加。对于动漫平台,针对不同性别用户在动漫客户端观看习惯上的差异,有必要根据性别为用户提供更准确的推荐产品和更个性化的服务。但由于绝大多数用户在客户端注册时所填写性别信息不准确或者信息缺失,因此研究基于用户行为记录进行用户性别的判断具有重要意义。针对此问题,本文提出了一种基于随机森林和极限学习机融合的算法模型,用于解决动漫用户性别识别的问题。
关键词: 性别识别 随机森林 极限学习机 数据挖掘
For information in English, please click here
Gender identification of animation users based on the fusion of random forest and extreme learning machine
Abstract:In recent years, with the rapid development of animation business, animation users gradually increased. As users with different gender have different habits when watching animation using mobile client, it is necessary to recommend products more accurately and provide more personalized service according to gender. But the filled gender infomation is inaccurate or missed for the vast majority of users when registering on the client. Therefore, it is of great significance to study the identification of users\' gender based on their behavior. To solve this problem, this paper presents an algorithm model based on the fusion of random forest and extreme learning machine, which is used to solve the problem of gender identification of animation users.
Keywords: gender identification random forest extreme learning machine data mining
基金:
引用
No.****
同行评议
勘误表
基于随机森林和极限学习机算法融合的动漫用户性别识别
评论
全部评论0/1000