Re: Large scale ranked recommendation

2016-01-07 Thread xenocyon
(following up a rather old thread:) Hi Christopher, I understand how you might use nearest neighbors for item-item recommendations, but how do you use it for top N items per user? Thanks! Apu -- View this message in context: http://apache-spark-user-list.1001560.n3.nabble.com/Large-scale

Re: Large scale ranked recommendation

2014-07-18 Thread Nick Pentreath
wrote: Yes, thats what prediction should be doing, taking dot products or sigmoid function for each user,item pair. For 1 million users and 10 K items data there are 10 billion pairs. -- View this message in context: http://apache-spark-user-list.1001560.n3.nabble.com/Large-scale-ranked

Re: Large scale ranked recommendation

2014-07-18 Thread Bertrand Dechoux
, taking dot products or sigmoid function for each user,item pair. For 1 million users and 10 K items data there are 10 billion pairs. -- View this message in context: http://apache-spark-user-list.1001560.n3.nabble.com/Large-scale-ranked-recommendation-tp10098p10107.html Sent from the Apache

Re: Large scale ranked recommendation

2014-07-18 Thread Xiangrui Meng
million users and 10 K items data there are 10 billion pairs. -- View this message in context: http://apache-spark-user-list.1001560.n3.nabble.com/Large-scale-ranked-recommendation-tp10098p10107.html Sent from the Apache Spark User List mailing list archive at Nabble.com.

Re: Large scale ranked recommendation

2014-07-18 Thread m3.sharma
these flops faster. -- View this message in context: http://apache-spark-user-list.1001560.n3.nabble.com/Large-scale-ranked-recommendation-tp10098p10183.html Sent from the Apache Spark User List mailing list archive at Nabble.com.

Re: Large scale ranked recommendation

2014-07-18 Thread Nick Pentreath
to leverage GPU capability of nodes for performing these flops faster. -- View this message in context: http://apache-spark-user-list.1001560.n3.nabble.com/Large-scale-ranked-recommendation-tp10098p10183.html Sent from the Apache Spark User List mailing list archive at Nabble.com.

Re: Large scale ranked recommendation

2014-07-18 Thread Christopher Johnson
. It will be great to have builtin GPU support in SPARK for faster computations to leverage GPU capability of nodes for performing these flops faster. -- View this message in context: http://apache-spark-user-list.1001560.n3.nabble.com/Large-scale-ranked-recommendation-tp10098p10183.html Sent from

Re: Large scale ranked recommendation

2014-07-18 Thread m3.sharma
if that don't work. I will look into annoy. Thanks. -- View this message in context: http://apache-spark-user-list.1001560.n3.nabble.com/Large-scale-ranked-recommendation-tp10098p10212.html Sent from the Apache Spark User List mailing list archive at Nabble.com.

Large scale ranked recommendation

2014-07-17 Thread m3.sharma
partitions before doing above steps, still it was of no help. I am using about 100 executor , 2 core, each executor with 2gb RAM. Are there any suggestions to make these predictions fast? -- View this message in context: http://apache-spark-user-list.1001560.n3.nabble.com/Large-scale-ranked

Re: Large scale ranked recommendation

2014-07-17 Thread m3.sharma
We are using RegressionModels that comes with *mllib* package in SPARK. -- View this message in context: http://apache-spark-user-list.1001560.n3.nabble.com/Large-scale-ranked-recommendation-tp10098p10103.html Sent from the Apache Spark User List mailing list archive at Nabble.com.

Re: Large scale ranked recommendation

2014-07-17 Thread Shuo Xiang
: http://apache-spark-user-list.1001560.n3.nabble.com/Large-scale-ranked-recommendation-tp10098p10103.html Sent from the Apache Spark User List mailing list archive at Nabble.com.

Re: Large scale ranked recommendation

2014-07-17 Thread m3.sharma
Yes, thats what prediction should be doing, taking dot products or sigmoid function for each user,item pair. For 1 million users and 10 K items data there are 10 billion pairs. -- View this message in context: http://apache-spark-user-list.1001560.n3.nabble.com/Large-scale-ranked