You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "mob-ai (Jira)" <ji...@apache.org> on 2019/09/24 02:17:00 UTC
[jira] [Commented] (SPARK-29224) Implement Factorization Machines
as a ml-pipeline component
[ https://issues.apache.org/jira/browse/SPARK-29224?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16936308#comment-16936308 ]
mob-ai commented on SPARK-29224:
--------------------------------
This is my implementation of FactorizationMachines:
[https://github.com/mob-ai/spark/tree/2.4/fm]
> Implement Factorization Machines as a ml-pipeline component
> -----------------------------------------------------------
>
> Key: SPARK-29224
> URL: https://issues.apache.org/jira/browse/SPARK-29224
> Project: Spark
> Issue Type: New Feature
> Components: ML
> Affects Versions: 2.4.3
> Reporter: mob-ai
> Priority: Major
>
> Factorization Machines is widely used in advertising and recommendation system to estimate CTR(click-through rate).
> Advertising and recommendation system usually has a lot of data, so we need Spark to estimate the CTR, and Factorization Machines are common ml model to estimate CTR.
> Goal: Implement Factorization Machines as a ml-pipeline component
> Requirements:
> 1. loss function supports: logloss, mse
> 2. optimizer: mini batch SGD
> References:
> 1. S. Rendle, “Factorization machines,” in Proceedings of IEEE International Conference on Data Mining (ICDM), pp. 995–1000, 2010.
> https://www.csie.ntu.edu.tw/~b97053/paper/Rendle2010FM.pdf
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org