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 goksron@gmail.com designates
 209.85.210.170 as permitted sender)
Received-SPF: pass (google.com: domain of goksron@gmail.com designates
 10.42.157.65 as permitted sender) client-ip=10.42.157.65;
MIME-Version: 1.0
In-Reply-To: <4F43E3E0.70007@xebia.com>
References: 
 <CAPDtdwDs4RtEShexcv6MBr0meYFdp-V-aJ-dgZGy-vF7Q0DfMg@mail.gmail.com>
	<A0A1769D-DBDA-45F9-93D0-DF7F052BDE5C@gmx.de>
	<CAPDtdwAKf9OgGim9Q0btmmu_Jx3KCU19emMiHLs-_MhafrCK+g@mail.gmail.com>
	<4F43DB7D.6070905@xebia.com>
	<CAPDtdwBJif_z-nbmyj8KdALgZ1D1=wUYJvp9GcG2ohifXZYBbg@mail.gmail.com>
	<CAPDtdwBVKvKW7F70tHPr-S3Y-PW-yDcG0vsPFfcNO9MBNK6Q0Q@mail.gmail.com>
	<4F43E3E0.70007@xebia.com>
Date: Tue, 21 Feb 2012 17:05:14 -0800
Message-ID: 
 <CAK9GPcRDfVM1q4RiSzyHzenYGEuvYG4OhK8RBhBZzk+7CX=TtQ@mail.gmail.com>
Subject: Re: Mahout Content based recommendation
From: Lance Norskog <goksron@gmail.com>
To: user@mahout.apache.org
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: quoted-printable

This sounds like two item-item matrices, one from preferences and one
from shared attributes.

You could combine these by adding the matrices, possibly with weights.
You could also multiply the matrices.

On Tue, Feb 21, 2012 at 10:35 AM, Paritosh Ranjan <pranjan@xebia.com> wrote=
:
> Maybe you will find this mail chain useful,
>
> http://lucene.472066.n3.nabble.com/Content-based-Recommender-Implementati=
on-td913981.html
>
>
> On 21-02-2012 23:48, VIGNESH PRAJAPATI wrote:
>>
>> can you suggest me another algorithm of mahout that can generate
>> content based recommendation .?
>>
>> On Tue, Feb 21, 2012 at 11:48 PM, VIGNESH PRAJAPATI
>> <vignesh2066@gmail.com>wrote:
>>
>>>
>>> On Tue, Feb 21, 2012 at 11:29 PM, Paritosh
>>> Ranjan<pranjan@xebia.com>wrote:
>>>
>>>> If you want to group similar objects ( in your case, content) together=
,
>>>> then clustering algorithms would help.
>>>>
>>>>
>>>> On 21-02-2012 23:26, VIGNESH PRAJAPATI wrote:
>>>>
>>>>> THanks =C2=A0Manuel Blechschmidt ,
>>>>>
>>>>> =C2=A0 =C2=A0 =C2=A0can you suggest me another algorithm of mahout th=
at can generate
>>>>> content based recommendation .?
>>>>>
>>>>> On Tue, Feb 21, 2012 at 10:55 PM, Manuel Blechschmidt<
>>>>> Manuel.Blechschmidt@gmx.de> =C2=A0 wrote:
>>>>>
>>>>> =C2=A0Hello Vignesh,
>>>>>>
>>>>>> content based recommendation is as far as I know not supported by
>>>>>> taste.
>>>>>> Taste uses collaborative filtering techniques.
>>>>>> If you want to use content based recommendation I would recommend to
>>>>>> use
>>>>>> simple SQL to query your database for products with same attributes.
>>>>>>
>>>>>> e.g. if you have a shirt then search the database for search
>>>>>> if you have a blue jacket search the database for other blue stuff
>>>>>>
>>>>>> You can also collect these attributes during the browsing behavior o=
f
>>>>>> the
>>>>>> customer and then combine then.
>>>>>>
>>>>>> Hope that helps
>>>>>> =C2=A0 =C2=A0Manuel
>>>>>>
>>>>>> On 21.02.2012, at 18:20, VIGNESH PRAJAPATI wrote:
>>>>>>
>>>>>> =C2=A0Hello folks,
>>>>>>>
>>>>>>> =C2=A0I am new to Apache mahout, have developed Simple Recommender =
for my
>>>>>>> online portal purchasing data based on Taste.Its *Collaborative
>>>>>>>
>>>>>> filtering*.but
>>>>>>
>>>>>>> i am not satisfied with the result of this recommender, cause
>>>>>>> sometimes
>>>>>>>
>>>>>> it
>>>>>>
>>>>>>> gives no recommendation for Userbased Recommender, Item Based
>>>>>>> Recommender
>>>>>>> and Slop One Recommender. So, I want to try Content Based
>>>>>>> Recommender.Any
>>>>>>> one have Idea on my Problem , how can i Solve this ?Or any
>>>>>>> alternative
>>>>>>>
>>>>>> for
>>>>>>
>>>>>>> this.....?
>>>>>>>
>>>>>>> Thanks
>>>>>>> --
>>>>>>>
>>>>>>> *Vignesh Prajapati*
>>>>>>> Tel: 9427415949 |
>>>>>>> vignesh2066@gmail.com | www.vipras.com.co.in
>>>>>>> MYTK [image:
>>>>>>> Facebook]<https://www.**facebook.com/vigs143<https://www.facebook.c=
om/vigs143>>
>>>>>>> =C2=A0[image:
>>>>>>>
>>>>>>> Twitter]<http://twitter.com/#%**21/vigs143<http://twitter.com/#%21/=
vigs143>>
>>>>>>> =C2=A0[image:
>>>>>>>
>>>>>>> LinkedIn]<http://www.linkedin.**com/pub/vignesh-prajapati/37/**756/=
46a<http://www.linkedin.com/pub/vignesh-prajapati/37/756/46a>
>>>>>>
>>>>>> [image:
>>>>>>
>>>>>>> about.me]<http://www.way4fun.**tk<http://www.way4fun.tk>><
>>>>>>>
>>>>>> http://r1.wisestamp.com/r/**landing?promo=3D7&dest=3Dhttp%3A%**
>>>>>> 2F%2Fwww.wisestamp.com%**2Femail-install%3Futm_source%**
>>>>>>
>>>>>> 3Dextension%26utm_medium%**3Demail%26utm_campaign%**3Dpromo_7<http:/=
/r1.wisestamp.com/r/landing?promo=3D7&dest=3Dhttp%3A%2F%2Fwww.wisestamp.com=
%2Femail-install%3Futm_source%3Dextension%26utm_medium%3Demail%26utm_campai=
gn%3Dpromo_7>
>>>>>> --
>>>>>> Manuel Blechschmidt
>>>>>> Dortustr. 57
>>>>>> 14467 Potsdam
>>>>>> Mobil: 0173/6322621
>>>>>> Twitter: http://twitter.com/Manuel_B
>>>>>>
>>>>>>
>>>>>>
>>>
>>> --
>>>
>>> *Vignesh Prajapati*
>>> Tel: 9427415949 |
>>> vignesh2066@gmail.com | www.vipras.com.co.in
>>> MYTK [image: Facebook]<https://www.facebook.com/vigs143> =C2=A0[image:
>>> Twitter]<http://twitter.com/#%21/vigs143> =C2=A0[image:
>>> LinkedIn]<http://www.linkedin.com/pub/vignesh-prajapati/37/756/46a>
>>> =C2=A0[image:
>>>
>>> about.me]<http://www.way4fun.tk><http://r1.wisestamp.com/r/landing?prom=
o=3D7&dest=3Dhttp%3A%2F%2Fwww.wisestamp.com%2Femail-install%3Futm_source%3D=
extension%26utm_medium%3Demail%26utm_campaign%3Dpromo_7>
>>>
>>
>>
>


--=20
Lance Norskog
goksron@gmail.com