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 Manuel.Blechschmidt@gmx.de
 designates 213.165.64.23 as permitted sender)
Content-Type: text/plain; charset=us-ascii
Mime-Version: 1.0 (Apple Message framework v1084)
Subject: Re: Purchase prediction
From: Manuel Blechschmidt <Manuel.Blechschmidt@gmx.de>
In-Reply-To: 
 <OF537F4235.B31A00CB-ON8525797A.006D7403-8525797A.006DCB47@us.ibm.com>
Date: Tue, 3 Jan 2012 21:26:31 +0100
Content-Transfer-Encoding: quoted-printable
Message-Id: <D658539D-3199-4AC1-BE41-194231160ACA@gmx.de>
References: 
 <CAERhYFOpq=VbVBPniGyNBPqgvcN0Bt+bhE7WX1VpA5tTAcQofw@mail.gmail.com>
 <74911649-7CCF-4766-BFDC-6EFD4262EAD2@gmx.de>
 <OF537F4235.B31A00CB-ON8525797A.006D7403-8525797A.006DCB47@us.ibm.com>
To: user@mahout.apache.org

Hi Mike,
actually it is a very tough research task to make predictions in real =
time.

I would expect that you can tune hidden markov models to work in semi =
real time.

Further if you have a trained model you can use this model in real time. =
The big question is how often can and should you rebuild your model. =
Further the question is how much computation time do you want to spend =
for every customer?

Perhaps the KDD Cup from 2000 is valueable:
http://www.kdd.org/kddcup/index.php?section=3D2000&method=3Dresult

Tasks:
Given a set of page views, will the visitor view another page on the =
site or will the visitor leave?
Given a set of page views, which product brand will the visitor view in =
the remainder of the session?
...

Agrawal et al. described a method to semi real time recommendations for =
news stories:
Fast Online Learning through Offline Initialization for Time-sensitive =
Recommendation
=
http://users.cs.fiu.edu/~lzhen001/activities/KDD_USB_key_2010/docs/p703.pd=
f

Hope that helps. If you have any results I would be interested in them.

/Manuel


On 03.01.2012, at 20:59, Mike Spreitzer wrote:

> I suspect the original request was concerned with --- and I, on my =
own, am=20
> concerned with --- a scenario in which it is desired to be able to =
quickly=20
> make predictions based on very recent data.  Thus, approaches that=20
> occasionally take a lot of time to build a model are non-solutions.  =
Are=20
> there solutions for my scenario in what you mentioned, or elsewhere?
>=20
> Thanks,
> Mike
>=20
>=20
>=20
> From:   Manuel Blechschmidt <Manuel.Blechschmidt@gmx.de>
> To:     user@mahout.apache.org
> Date:   01/03/2012 02:40 PM
> Subject:        Re: Purchase prediction
>=20
>=20
>=20
> Hello Nishan,
> you can use the recommender approaches with the boolean reference =
model.
>=20
> You can use IRStatistics (Precision, Recall, F-Measure) to benchmark =
your=20
> results.
> =
https://cwiki.apache.org/confluence/display/MAHOUT/Recommender+Documentati=
on
>=20
>=20
> Further you could also use the hidden markov model to predict=20
> probabilities of next purchases.
> http://isabel-drost.de/hadoop/slides/HMM.pdf
> https://issues.apache.org/jira/browse/MAHOUT-396
>=20
> There are some papers describing how to combine some of these methods:
>=20
> Rendle. et. al presented a paper using a combination of both:
> Factorizing Personalized Markov Chains for Next-Basket Recommendation
> =
http://www.ismll.uni-hildesheim.de/pub/pdfs/RendleFreudenthaler2010-FPMC.p=
df
>=20
>=20
> In my opinion some seasonal models could also help to better predict =
next=20
> purchases.
>=20
> There is currently an resolved enhancement request for 0.6 making=20
> evaluation for a use case like yours better:
> https://issues.apache.org/jira/browse/MAHOUT-906
>=20
> If you have further questions feel free to ask.
>=20
> /Manuel
>=20
> On 03.01.2012, at 19:02, Nishant Chandra wrote:
>=20
>> Hi,
>>=20
>> I am trying to predict shopper purchase and non-purchase intention in
>> E-Commerce context. I am more interested in finding the later.
>> A near-real time approach will be great. So given a sequence of pages
>> a shopper views, I would like the algorithm to predict the intention.
>>=20
>> Any algorithms in Mahout or otherwise that can help?
>>=20
>> Thanks,
>> Nishant
>=20
> --=20
> Manuel Blechschmidt
> Dortustr. 57
> 14467 Potsdam
> Mobil: 0173/6322621
> Twitter: http://twitter.com/Manuel_B
>=20
>=20

--=20
Manuel Blechschmidt
Dortustr. 57
14467 Potsdam
Mobil: 0173/6322621
Twitter: http://twitter.com/Manuel_B