Mailing-List: contact user-help@mahout.apache.org; run by ezmlm
Precedence: bulk
Reply-To: user@mahout.apache.org
Received-SPF: pass (athena.apache.org: domain of tevfik.aytekin@gmail.com
 designates 209.85.212.53 as permitted sender)
MIME-Version: 1.0
In-Reply-To: <F0157953-1514-4CD9-A758-B22D675FA31C@gmail.com>
References: <F0157953-1514-4CD9-A758-B22D675FA31C@gmail.com>
Date: Thu, 6 Feb 2014 14:41:50 +0200
Message-ID: 
 <CAH9ofMYXi0ZVgKHtqZOfiOOqLa-XvFQPy_oDDkqS15WBtUfWqw@mail.gmail.com>
Subject: Re: Popularity of recommender items
From: Tevfik Aytekin <tevfik.aytekin@gmail.com>
To: user@mahout.apache.org
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable

Well, I think what you are suggesting is to define popularity as being
similar to other items. So in this way most popular items will be
those which are most similar to all other items, like the centroids in
K-means.

I would first check the correlation between this definition and the
standard one (that is, the definition of popularity as having the
highest number of ratings). But my intuition is that they are
different things. For example. an item might lie at the center in the
similarity space but it might not be a popular item. However, there
might still be some correlation, it would be interesting to check it.

hope it helps


On Wed, Feb 5, 2014 at 3:27 AM, Pat Ferrel <pat@occamsmachete.com> wrote:
> Trying to come up with a relative measure of popularity for items in a re=
commender. Something that could be used to rank items.
>
> The user - item preference matrix would be the obvious thought. Just add =
the number of preferences per item. Maybe transpose the preference matrix (=
the temp DRM created by the recommender), then for each row vector (now tha=
t a row =3D item) grab the number of non zero preferences. This corresponds=
 to the number of preferences, and would give one measure of popularity. In=
 the case where the items are not boolean you'd sum the weights.
>
> However it might be a better idea to look at the item-item similarity mat=
rix. It doesn't need to be transposed and contains the "important" similari=
ties--as calculated by LLR for example. Here similarity means similarity in=
 which users preferred an item. So summing the non-zero weights would give =
perhaps an even better relative "popularity" measure. For the same reason c=
lustering the similarity matrix would yield "important" clusters.
>
> Anyone have intuition about this?
>
> I started to think about this because transposing the user-item matrix se=
ems to yield a fromat that cannot be sent directly into clustering.