广东工业大学学报 ›› 2016, Vol. 33 ›› Issue (05): 28-33.doi: 10.3969/j.issn.1007-7162.2016.05.006

• 综合研究 • 上一篇    下一篇

基于Spark的线性模型在广告投放系统中的应用研究

林穗, 赵菲   

  1. 广东工业大学 计算机学院,广东 广州 510006
  • 收稿日期:2016-03-10 出版日期:2016-09-10 发布日期:2016-09-10
  • 通信作者: 赵菲(1989-),女,硕士研究生,主要研究方向为云计算.E-mail:zflb2008@126.com
  • 作者简介:林穗(1972-),女,副教授,主要研究方向为操作系统、云计算.E-mail:linsui@gdut.edu.cn
  • 基金资助:

    广东省科技计划项目(2014B090901053);广州市科技计划项目(2013Y2-00074)

An Application Research of Linear Model in the Advertising System Based on Spark

Lin Sui, Zhao Fei   

  1. School of Computers,Guangdong University of Technology, Guangzhou 510006, China
  • Received:2016-03-10 Online:2016-09-10 Published:2016-09-10

摘要:

针对在线广告投放中对实时性和高精确度的要求,对比了Hadoop和Spark两种主流平台在实现流程及效率方面的差异,提出了将线性模型结合Spark技术应用在广告投放系统中,并从数值特征、迭代和步长等方面对模型进行优化.经测试表明,调优后的精确度有5%至10%的提升.

关键词: Spark; 实时计算; 在线广告; 线性模型

Abstract:

The online advertisement is the most important model of Internet profit. It makes the computing advertising a hot point of current research. For the real-time requirement and the high accuracy requirement in the online advertising system, the difference between the implementation and efficiency is compared based on the two popular platforms of Hadoop and Spark. And then a linear model is proposed combined with the technology of Spark to be applied in the advertising system. Finally the linear model is optimized from the aspect of numerical characteristics, iteration and step size. The testing result shows that the accuracy has a 5% to 10% increase after the optimization.

Key words: Spark; real time computing; online advertisement; linear model

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!