You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@mahout.apache.org by "Sebastian Schelter (JIRA)" <ji...@apache.org> on 2010/12/05 10:40:10 UTC
[jira] Created: (MAHOUT-558) Extend ItembasedRecommender to offer
different "exclusion modes" when computing most similar items to a
collection of input items
Extend ItembasedRecommender to offer different "exclusion modes" when computing most similar items to a collection of input items
---------------------------------------------------------------------------------------------------------------------------------
Key: MAHOUT-558
URL: https://issues.apache.org/jira/browse/MAHOUT-558
Project: Mahout
Issue Type: New Feature
Components: Collaborative Filtering
Affects Versions: 0.5
Reporter: Sebastian Schelter
GenericItembased Recommender currently excludes all items that are not similar at least one of the input items when computing the most similar items to a collection of items. We should introduce a way to have the user decide whether he/she wants this behavior or he/she wants to have all items included that are similar to at least one of the input items, which is more useful in practice in my experience.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
Re: [jira] Commented: (MAHOUT-558) Extend ItembasedRecommender to
offer different "exclusion modes" when computing most similar items to a
collection of input items
Posted by Sean Owen <sr...@gmail.com>.
Oh OK thought you were referring to an implementation in the library.
As far as I personally am concerned, you're still honoring the contract of
"estimate preference". You could change the implementation to record and
return actual preferences, yes, regardless of what the implementation
otherwise does. This would make it more consistent with other
implementations. Maybe that's good. But maybe it costs a lot of resources in
practice. So I support your tradeoff. There's loads of this in the library,
for better or worse. I think it still hangs together well.
On Mon, Dec 6, 2010 at 11:09 PM, Lance Norskog <go...@gmail.com> wrote:
> I'm working on User-Item and Item-Item Recommenders based on Semantic
> Vectors:
>
> http://ultrawhizbang.blogspot.com/2010/11/semantic-vectors-part-1.html
>
> http://ultrawhizbang.blogspot.com/2010/11/semantic-vectors-for-recommenders-with.html
>
> (Please comment on errors and lack of clarity.)
>
> The SemanticVectorDataModel only saves the projected vectors, not the
> original recommender input. It cannot return the original prefs, only
> its own prefs (N-dimensional vector distances).
>
> On Mon, Dec 6, 2010 at 1:53 AM, Sean Owen (JIRA) <ji...@apache.org> wrote:
> >
> > [
> https://issues.apache.org/jira/browse/MAHOUT-558?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12967140#action_12967140]
> >
> > Sean Owen commented on MAHOUT-558:
> > ----------------------------------
> >
> > There's a tension between the need to fit several algorithms into one
> common API, and the fact that they do have different characteristics. Making
> them all work exactly the same would mean jumping through a few hoops and
> also cutting off access to shortcuts that improve performance.
> >
> > One big example to me is fudging what a preference estimate means when
> the data model has no preference values. estimatePreference() should
> unusefully return 1.0 all the time, really but it doesn't, in order to be
> more useful in practice.
> >
> > That said, at the level of your example we ought to have consistent
> behavior. Which recommender doesn't return the known pref value? That sounds
> like an unintentional behavior.
> >
> > However I would point out that the contract is to "estimate" a preference
> -- nobody said what the estimate has to be!
> >
> >> Extend ItembasedRecommender to offer different "exclusion modes" when
> computing most similar items to a collection of input items
> >>
> ---------------------------------------------------------------------------------------------------------------------------------
> >>
> >> Key: MAHOUT-558
> >> URL: https://issues.apache.org/jira/browse/MAHOUT-558
> >> Project: Mahout
> >> Issue Type: New Feature
> >> Components: Collaborative Filtering
> >> Affects Versions: 0.5
> >> Reporter: Sebastian Schelter
> >> Attachments: MAHOUT-558-2.patch, MAHOUT-558.patch
> >>
> >>
> >> GenericItembased Recommender currently excludes all items that are not
> similar at least one of the input items when computing the most similar
> items to a collection of items. We should introduce a way to have the user
> decide whether he/she wants this behavior or he/she wants to have all items
> included that are similar to at least one of the input items, which is more
> useful in practice in my experience.
> >
> > --
> > This message is automatically generated by JIRA.
> > -
> > You can reply to this email to add a comment to the issue online.
> >
> >
>
>
>
> --
> Lance Norskog
> goksron@gmail.com
>
Re: [jira] Commented: (MAHOUT-558) Extend ItembasedRecommender to
offer different "exclusion modes" when computing most similar items to a
collection of input items
Posted by Lance Norskog <go...@gmail.com>.
I'm working on User-Item and Item-Item Recommenders based on Semantic Vectors:
http://ultrawhizbang.blogspot.com/2010/11/semantic-vectors-part-1.html
http://ultrawhizbang.blogspot.com/2010/11/semantic-vectors-for-recommenders-with.html
(Please comment on errors and lack of clarity.)
The SemanticVectorDataModel only saves the projected vectors, not the
original recommender input. It cannot return the original prefs, only
its own prefs (N-dimensional vector distances).
On Mon, Dec 6, 2010 at 1:53 AM, Sean Owen (JIRA) <ji...@apache.org> wrote:
>
> [ https://issues.apache.org/jira/browse/MAHOUT-558?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12967140#action_12967140 ]
>
> Sean Owen commented on MAHOUT-558:
> ----------------------------------
>
> There's a tension between the need to fit several algorithms into one common API, and the fact that they do have different characteristics. Making them all work exactly the same would mean jumping through a few hoops and also cutting off access to shortcuts that improve performance.
>
> One big example to me is fudging what a preference estimate means when the data model has no preference values. estimatePreference() should unusefully return 1.0 all the time, really but it doesn't, in order to be more useful in practice.
>
> That said, at the level of your example we ought to have consistent behavior. Which recommender doesn't return the known pref value? That sounds like an unintentional behavior.
>
> However I would point out that the contract is to "estimate" a preference -- nobody said what the estimate has to be!
>
>> Extend ItembasedRecommender to offer different "exclusion modes" when computing most similar items to a collection of input items
>> ---------------------------------------------------------------------------------------------------------------------------------
>>
>> Key: MAHOUT-558
>> URL: https://issues.apache.org/jira/browse/MAHOUT-558
>> Project: Mahout
>> Issue Type: New Feature
>> Components: Collaborative Filtering
>> Affects Versions: 0.5
>> Reporter: Sebastian Schelter
>> Attachments: MAHOUT-558-2.patch, MAHOUT-558.patch
>>
>>
>> GenericItembased Recommender currently excludes all items that are not similar at least one of the input items when computing the most similar items to a collection of items. We should introduce a way to have the user decide whether he/she wants this behavior or he/she wants to have all items included that are similar to at least one of the input items, which is more useful in practice in my experience.
>
> --
> This message is automatically generated by JIRA.
> -
> You can reply to this email to add a comment to the issue online.
>
>
--
Lance Norskog
goksron@gmail.com
[jira] Commented: (MAHOUT-558) Extend ItembasedRecommender to offer
different "exclusion modes" when computing most similar items to a
collection of input items
Posted by "Hudson (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/MAHOUT-558?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12967044#action_12967044 ]
Hudson commented on MAHOUT-558:
-------------------------------
Integrated in Mahout-Quality #495 (See [https://hudson.apache.org/hudson/job/Mahout-Quality/495/])
> Extend ItembasedRecommender to offer different "exclusion modes" when computing most similar items to a collection of input items
> ---------------------------------------------------------------------------------------------------------------------------------
>
> Key: MAHOUT-558
> URL: https://issues.apache.org/jira/browse/MAHOUT-558
> Project: Mahout
> Issue Type: New Feature
> Components: Collaborative Filtering
> Affects Versions: 0.5
> Reporter: Sebastian Schelter
> Attachments: MAHOUT-558-2.patch, MAHOUT-558.patch
>
>
> GenericItembased Recommender currently excludes all items that are not similar at least one of the input items when computing the most similar items to a collection of items. We should introduce a way to have the user decide whether he/she wants this behavior or he/she wants to have all items included that are similar to at least one of the input items, which is more useful in practice in my experience.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Commented: (MAHOUT-558) Extend ItembasedRecommender to offer
different "exclusion modes" when computing most similar items to a
collection of input items
Posted by "Sean Owen (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/MAHOUT-558?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12967140#action_12967140 ]
Sean Owen commented on MAHOUT-558:
----------------------------------
There's a tension between the need to fit several algorithms into one common API, and the fact that they do have different characteristics. Making them all work exactly the same would mean jumping through a few hoops and also cutting off access to shortcuts that improve performance.
One big example to me is fudging what a preference estimate means when the data model has no preference values. estimatePreference() should unusefully return 1.0 all the time, really but it doesn't, in order to be more useful in practice.
That said, at the level of your example we ought to have consistent behavior. Which recommender doesn't return the known pref value? That sounds like an unintentional behavior.
However I would point out that the contract is to "estimate" a preference -- nobody said what the estimate has to be!
> Extend ItembasedRecommender to offer different "exclusion modes" when computing most similar items to a collection of input items
> ---------------------------------------------------------------------------------------------------------------------------------
>
> Key: MAHOUT-558
> URL: https://issues.apache.org/jira/browse/MAHOUT-558
> Project: Mahout
> Issue Type: New Feature
> Components: Collaborative Filtering
> Affects Versions: 0.5
> Reporter: Sebastian Schelter
> Attachments: MAHOUT-558-2.patch, MAHOUT-558.patch
>
>
> GenericItembased Recommender currently excludes all items that are not similar at least one of the input items when computing the most similar items to a collection of items. We should introduce a way to have the user decide whether he/she wants this behavior or he/she wants to have all items included that are similar to at least one of the input items, which is more useful in practice in my experience.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Commented: (MAHOUT-558) Extend ItembasedRecommender to offer
different "exclusion modes" when computing most similar items to a
collection of input items
Posted by "Sebastian Schelter (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/MAHOUT-558?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12967009#action_12967009 ]
Sebastian Schelter commented on MAHOUT-558:
-------------------------------------------
committed the first patch.
> Extend ItembasedRecommender to offer different "exclusion modes" when computing most similar items to a collection of input items
> ---------------------------------------------------------------------------------------------------------------------------------
>
> Key: MAHOUT-558
> URL: https://issues.apache.org/jira/browse/MAHOUT-558
> Project: Mahout
> Issue Type: New Feature
> Components: Collaborative Filtering
> Affects Versions: 0.5
> Reporter: Sebastian Schelter
> Attachments: MAHOUT-558-2.patch, MAHOUT-558.patch
>
>
> GenericItembased Recommender currently excludes all items that are not similar at least one of the input items when computing the most similar items to a collection of items. We should introduce a way to have the user decide whether he/she wants this behavior or he/she wants to have all items included that are similar to at least one of the input items, which is more useful in practice in my experience.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Updated: (MAHOUT-558) Extend ItembasedRecommender to offer
different "exclusion modes" when computing most similar items to a
collection of input items
Posted by "Sebastian Schelter (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/MAHOUT-558?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Sebastian Schelter updated MAHOUT-558:
--------------------------------------
Attachment: MAHOUT-558.patch
> Extend ItembasedRecommender to offer different "exclusion modes" when computing most similar items to a collection of input items
> ---------------------------------------------------------------------------------------------------------------------------------
>
> Key: MAHOUT-558
> URL: https://issues.apache.org/jira/browse/MAHOUT-558
> Project: Mahout
> Issue Type: New Feature
> Components: Collaborative Filtering
> Affects Versions: 0.5
> Reporter: Sebastian Schelter
> Attachments: MAHOUT-558.patch
>
>
> GenericItembased Recommender currently excludes all items that are not similar at least one of the input items when computing the most similar items to a collection of items. We should introduce a way to have the user decide whether he/she wants this behavior or he/she wants to have all items included that are similar to at least one of the input items, which is more useful in practice in my experience.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Updated: (MAHOUT-558) Extend ItembasedRecommender to offer
different "exclusion modes" when computing most similar items to a
collection of input items
Posted by "Sebastian Schelter (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/MAHOUT-558?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Sebastian Schelter updated MAHOUT-558:
--------------------------------------
Attachment: MAHOUT-558-2.patch
changed average computation to not favor obscure items
> Extend ItembasedRecommender to offer different "exclusion modes" when computing most similar items to a collection of input items
> ---------------------------------------------------------------------------------------------------------------------------------
>
> Key: MAHOUT-558
> URL: https://issues.apache.org/jira/browse/MAHOUT-558
> Project: Mahout
> Issue Type: New Feature
> Components: Collaborative Filtering
> Affects Versions: 0.5
> Reporter: Sebastian Schelter
> Attachments: MAHOUT-558-2.patch, MAHOUT-558.patch
>
>
> GenericItembased Recommender currently excludes all items that are not similar at least one of the input items when computing the most similar items to a collection of items. We should introduce a way to have the user decide whether he/she wants this behavior or he/she wants to have all items included that are similar to at least one of the input items, which is more useful in practice in my experience.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Commented: (MAHOUT-558) Extend ItembasedRecommender to offer
different "exclusion modes" when computing most similar items to a
collection of input items
Posted by "Sebastian Schelter (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/MAHOUT-558?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12966968#action_12966968 ]
Sebastian Schelter commented on MAHOUT-558:
-------------------------------------------
I think we misunderstand each other. When we compute similar items to A,B,C with the current trunk code than any X that is not similar to *each* of the input items will be excluded. Say X is similar to A and B but not to C than the last summand will be NaN and thus the estimate for X will be NaN, which means not similar and X will therefore be excluded.
With the patched version only the similarities of X to A and B would be considered. I agree that this favors obscure items. I initially proposed to interpret a "missing" similarity as 0 in this case, so that the average result would be lowered for items that have a smaller number of similarities. Should I better include this in the patch?
The practical use for me would be in this scenario: If you only work with a small number of precomputed similarities per item in memory and use the current version without the patch, mostSimilarItems(...) will give you empty results for a collection of input items in most cases (from my experiences). I've seen this behavior very often with larger shopping carts for example, and that's why I proposed to lower the conditions for items to be included in the result.
I don't see how this change would affect MostSimilarEstimator.
> Extend ItembasedRecommender to offer different "exclusion modes" when computing most similar items to a collection of input items
> ---------------------------------------------------------------------------------------------------------------------------------
>
> Key: MAHOUT-558
> URL: https://issues.apache.org/jira/browse/MAHOUT-558
> Project: Mahout
> Issue Type: New Feature
> Components: Collaborative Filtering
> Affects Versions: 0.5
> Reporter: Sebastian Schelter
> Attachments: MAHOUT-558.patch
>
>
> GenericItembased Recommender currently excludes all items that are not similar at least one of the input items when computing the most similar items to a collection of items. We should introduce a way to have the user decide whether he/she wants this behavior or he/she wants to have all items included that are similar to at least one of the input items, which is more useful in practice in my experience.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Commented: (MAHOUT-558) Extend ItembasedRecommender to offer
different "exclusion modes" when computing most similar items to a
collection of input items
Posted by "Sean Owen (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/MAHOUT-558?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12966931#action_12966931 ]
Sean Owen commented on MAHOUT-558:
----------------------------------
One initial comment is, shouldn't this change affect not just MultiMostSimilarEstimator, but MostSimilarEstimator? I think it would have an analogous change in the user-based recommender too for consistency.
Let me present a small example to make sure I understand. The estimated preference for some new thing X is based on the user's existing preferences for A, B and C. Right now, if X has no defined similarity (not 0, but uncomputable or undefined) to A, B or C, then X cannot be recommended -- there's simply no estimate.
Right now, if X has a defined simiarity to *any* of A, B or C then some estimate can be made. The undefined relations are ignored. This is, I think, a decent intepretation of the stock item-based recommender approach; it does "unfairly" favor obscurer items.
If I read this change right, it would need for X to have a resemblance to *all* of A, B and C to produce any estimate. That sounds like quite a strict rule in practice -- would it not fail to produce recommendations in many cases? Is that the intent and if so what's the real-world use case for this.
> Extend ItembasedRecommender to offer different "exclusion modes" when computing most similar items to a collection of input items
> ---------------------------------------------------------------------------------------------------------------------------------
>
> Key: MAHOUT-558
> URL: https://issues.apache.org/jira/browse/MAHOUT-558
> Project: Mahout
> Issue Type: New Feature
> Components: Collaborative Filtering
> Affects Versions: 0.5
> Reporter: Sebastian Schelter
> Attachments: MAHOUT-558.patch
>
>
> GenericItembased Recommender currently excludes all items that are not similar at least one of the input items when computing the most similar items to a collection of items. We should introduce a way to have the user decide whether he/she wants this behavior or he/she wants to have all items included that are similar to at least one of the input items, which is more useful in practice in my experience.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Commented: (MAHOUT-558) Extend ItembasedRecommender to offer
different "exclusion modes" when computing most similar items to a
collection of input items
Posted by "Lance Norskog (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/MAHOUT-558?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12967059#action_12967059 ]
Lance Norskog commented on MAHOUT-558:
--------------------------------------
It would be good to have a common contract that all of the Recommenders either honor or throw UnsupportedOperationException. Having a zillion recommenders with their own quirks and slightly different behaviors and interpretations makes the software base unusable.
For example, my bete noir: most of the user-based recommenders return the user's own pref for an item, rather than the recommender's calculated pref. Some recommenders cannot do this because they compute internal numbers based on the prefs and then toss the prefs. I am writing such a recommender and I cannot duplicate this behavior.
> Extend ItembasedRecommender to offer different "exclusion modes" when computing most similar items to a collection of input items
> ---------------------------------------------------------------------------------------------------------------------------------
>
> Key: MAHOUT-558
> URL: https://issues.apache.org/jira/browse/MAHOUT-558
> Project: Mahout
> Issue Type: New Feature
> Components: Collaborative Filtering
> Affects Versions: 0.5
> Reporter: Sebastian Schelter
> Attachments: MAHOUT-558-2.patch, MAHOUT-558.patch
>
>
> GenericItembased Recommender currently excludes all items that are not similar at least one of the input items when computing the most similar items to a collection of items. We should introduce a way to have the user decide whether he/she wants this behavior or he/she wants to have all items included that are similar to at least one of the input items, which is more useful in practice in my experience.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Updated: (MAHOUT-558) Extend ItembasedRecommender to offer
different "exclusion modes" when computing most similar items to a
collection of input items
Posted by "Sebastian Schelter (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/MAHOUT-558?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Sebastian Schelter updated MAHOUT-558:
--------------------------------------
Status: Patch Available (was: Open)
> Extend ItembasedRecommender to offer different "exclusion modes" when computing most similar items to a collection of input items
> ---------------------------------------------------------------------------------------------------------------------------------
>
> Key: MAHOUT-558
> URL: https://issues.apache.org/jira/browse/MAHOUT-558
> Project: Mahout
> Issue Type: New Feature
> Components: Collaborative Filtering
> Affects Versions: 0.5
> Reporter: Sebastian Schelter
> Attachments: MAHOUT-558.patch
>
>
> GenericItembased Recommender currently excludes all items that are not similar at least one of the input items when computing the most similar items to a collection of items. We should introduce a way to have the user decide whether he/she wants this behavior or he/she wants to have all items included that are similar to at least one of the input items, which is more useful in practice in my experience.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Commented: (MAHOUT-558) Extend ItembasedRecommender to offer
different "exclusion modes" when computing most similar items to a
collection of input items
Posted by "Lance Norskog (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/MAHOUT-558?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12968640#action_12968640 ]
Lance Norskog commented on MAHOUT-558:
--------------------------------------
bq. Which recommender doesn't return the known pref value? That sounds like an unintentional behavior.
This is an algorithm I'm writing, not one of the existing recommenders. The original data goes through a processing stage, and the datamodel only saves the output. It does not even know which users proffered a rating.
> Extend ItembasedRecommender to offer different "exclusion modes" when computing most similar items to a collection of input items
> ---------------------------------------------------------------------------------------------------------------------------------
>
> Key: MAHOUT-558
> URL: https://issues.apache.org/jira/browse/MAHOUT-558
> Project: Mahout
> Issue Type: New Feature
> Components: Collaborative Filtering
> Affects Versions: 0.5
> Reporter: Sebastian Schelter
> Attachments: MAHOUT-558-2.patch, MAHOUT-558.patch
>
>
> GenericItembased Recommender currently excludes all items that are not similar at least one of the input items when computing the most similar items to a collection of items. We should introduce a way to have the user decide whether he/she wants this behavior or he/she wants to have all items included that are similar to at least one of the input items, which is more useful in practice in my experience.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] [Assigned] (MAHOUT-558) Extend ItembasedRecommender to offer
different "exclusion modes" when computing most similar items to a
collection of input items
Posted by "Sebastian Schelter (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/MAHOUT-558?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Sebastian Schelter reassigned MAHOUT-558:
-----------------------------------------
Assignee: Sebastian Schelter
> Extend ItembasedRecommender to offer different "exclusion modes" when computing most similar items to a collection of input items
> ---------------------------------------------------------------------------------------------------------------------------------
>
> Key: MAHOUT-558
> URL: https://issues.apache.org/jira/browse/MAHOUT-558
> Project: Mahout
> Issue Type: New Feature
> Components: Collaborative Filtering
> Affects Versions: 0.5
> Reporter: Sebastian Schelter
> Assignee: Sebastian Schelter
> Fix For: 0.5
>
> Attachments: MAHOUT-558-2.patch, MAHOUT-558.patch
>
>
> GenericItembased Recommender currently excludes all items that are not similar at least one of the input items when computing the most similar items to a collection of items. We should introduce a way to have the user decide whether he/she wants this behavior or he/she wants to have all items included that are similar to at least one of the input items, which is more useful in practice in my experience.
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] Updated: (MAHOUT-558) Extend ItembasedRecommender to offer
different "exclusion modes" when computing most similar items to a
collection of input items
Posted by "Sebastian Schelter (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/MAHOUT-558?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Sebastian Schelter updated MAHOUT-558:
--------------------------------------
Resolution: Fixed
Fix Version/s: 0.5
Status: Resolved (was: Patch Available)
> Extend ItembasedRecommender to offer different "exclusion modes" when computing most similar items to a collection of input items
> ---------------------------------------------------------------------------------------------------------------------------------
>
> Key: MAHOUT-558
> URL: https://issues.apache.org/jira/browse/MAHOUT-558
> Project: Mahout
> Issue Type: New Feature
> Components: Collaborative Filtering
> Affects Versions: 0.5
> Reporter: Sebastian Schelter
> Fix For: 0.5
>
> Attachments: MAHOUT-558-2.patch, MAHOUT-558.patch
>
>
> GenericItembased Recommender currently excludes all items that are not similar at least one of the input items when computing the most similar items to a collection of items. We should introduce a way to have the user decide whether he/she wants this behavior or he/she wants to have all items included that are similar to at least one of the input items, which is more useful in practice in my experience.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Commented: (MAHOUT-558) Extend ItembasedRecommender to offer
different "exclusion modes" when computing most similar items to a
collection of input items
Posted by "Sean Owen (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/MAHOUT-558?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12966988#action_12966988 ]
Sean Owen commented on MAHOUT-558:
----------------------------------
I think I misread the patch since I assumed that MultiMostSImilarEstimator already has the behavior you are trying to implement. What you propose matches what MostSimilarEstimator does already. In that sense it's really a fix and I support it: ignore NaN. If that is indeed what the original patch does, I support it.
While the 'bias' here is an issue I think it is a larger task to change it across the code base. No I am not sure these should be interpreted as 0 as it makes the behavior a little 'stranger' to me and less defensible theoretically. Therefore I like the original patch, I think.
> Extend ItembasedRecommender to offer different "exclusion modes" when computing most similar items to a collection of input items
> ---------------------------------------------------------------------------------------------------------------------------------
>
> Key: MAHOUT-558
> URL: https://issues.apache.org/jira/browse/MAHOUT-558
> Project: Mahout
> Issue Type: New Feature
> Components: Collaborative Filtering
> Affects Versions: 0.5
> Reporter: Sebastian Schelter
> Attachments: MAHOUT-558-2.patch, MAHOUT-558.patch
>
>
> GenericItembased Recommender currently excludes all items that are not similar at least one of the input items when computing the most similar items to a collection of items. We should introduce a way to have the user decide whether he/she wants this behavior or he/she wants to have all items included that are similar to at least one of the input items, which is more useful in practice in my experience.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.