Using 'learning to rank' with user specific features

[Nawab Zada Asad Iqbal <kh...@gmail.com>]

hi,

I am going through learning to rank examples in Solr7. In the examples, the
features are part of the searched document.  Can I use solr's learning to
rank system if my features are user specific? e.g., if searching for
products, i want to rank some products higher if they have been used by
current user's friends.

Initially, i was thinking of tracking a list of 'friend products' with each
user so that after the query, i re-rank the results if any of the resulting
item is also in 'friend products' list. This list is being generated
outside the solr server. Can I user Solr7's re-ranking functionality with
this list?

One alternative is to extract features (e.g., like category, price buckets
etc.) of the products and save them in the solr documents; and then also
deduce the features of user's 'friend products' instead of just keeping the
raw product list. However, in both cases the search user has its specific
feature values.



Thanks
Nawab

Re: Using 'learning to rank' with user specific features

["alessandro.benedetti" <a....@sease.io>]

Hi,
let me see if I got your problem :
 your "user specific" features are Query dependent features from Solr side.
The value of this feature depends on a query component ( the user Id) and a
document component( product Id)
You can definitely use them.
You can model this feature as a binary feature.
1 means the product was coming from friends
0 means the product was not.

At training time, you need to provide the value to each training row.
At query time you may need a custom feature type.
You can pass the user id as an EFI.
In that situation the custom feature will query the external server to get
the friend's products and then you can calculate it.
Of course you can implement the custom feature as you wish.
That will strictly depend on how you decide to implement the user-product
interactions tracking and retrieval system.




-----
---------------
Alessandro Benedetti
Search Consultant, R&D Software Engineer, Director
Sease Ltd. - www.sease.io
--
Sent from: http://lucene.472066.n3.nabble.com/Solr-User-f472068.html