Recommender System Fragment 1
来源:互联网 发布:linux 制作iso 编辑:程序博客网 时间:2024/06/07 06:49
Procedure
- when a scenario(user) comes, fetch all the user’s properties and then pull candidates(items) from several queues depending on recall strategy(how? what model?). rank over all these candidate(~1000?) and push out the top ones.
Details
- each queue is updated dynamically.
- queue length? ~ 1000?
- always fetch from queue front? a bit slower and slower for bloom filter but acceptable cz queue not too long.
- ranking is a pre-trained stable model. just do ‘prediction’. parallel if needed.
- all queue and BF could be in memory.
Qs
- how to get user’s features? kv db and/or what? – kv db
- how to get doc features? are they stored in queue? – yes
- how and where to apply anti-spam & anti-cheating module?
0 0
- Recommender System Fragment 1
- Recommender System Fragment 2
- recommender system
- Recommender System
- about recommender system
- Modern Recommender System
- Introduction to Recommender System 之 Module 1 Introduction to Recommender Systems
- Recommender System ——charu C. Aggarwal学习笔记【1】
- anomaly detection ng recommender system
- [Mahout in action]--Recommender System
- Deep Learning based Recommender System: A Survey and New Perspectives (1)
- an excellent blog about recommender system
- 推荐系统(Recommender System)的技术基础
- 推荐系统(Recommender System)的技术基础
- 推荐系统(Recommender System)的技术基础
- Data Sciece from Scratch 之 Recommender System
- recosystem: Recommender System Using Parallel Matrix Factorization
- 论文推荐 推荐系统 Recommender System
- GDKOI 2016 魔卡少女
- gradle多渠道打包和同一App打包不同版本Api调用
- 创建Red Hat Enterprise Linux 6 64位虚拟机
- python中的sys模块函数
- stdlib.h
- Recommender System Fragment 1
- 区间选点问题---poj-1328
- maven常用命令集
- 金融IC卡降级交易常见问题解答
- MySQL使用存储过程循环插入数据
- 解决getView()方法反复执行
- Android面试汇总(百度+360+Tencent+淘宝+Qualcomm+HTC)
- CSS3背景渐变属性 linear-gradient(线性渐变)和radial-gradient(径向渐变)
- 你真的会写二分查找吗