Hi Nirmal,
For Multi-Class Multi-Label Classification Could you please refer this[1]
The problem is to find the behavioural patterns between consumers. ( It's
not market basket analysis)
Example :
transaction ID 1: SalaryUSD 15K - Have2Childeren - MemberCardGold -
BuyedProductAnchor
transaction ID 2: SalaryUSD 15K - Have2Childeren - MemberCardGold -
BuyedProductTea
transaction ID 3: SalaryUSD 15K - Have2Childeren - MemberCardGold -
BuyedProductChickenMalto
if new customer comes with SalaryUSD 15K - Have2Childeren - MemberCardGold
- catagories I need to suggest {BuyedProductAnchor , BuyedProductTea,
BuyedProductChickenMalto }
Hope you get my problem.
[1] http://scikit-learn.org/stable/modules/multiclass.html
Regards.
*M. Nifras Ismail*
[image: LinkedIn] <http://lk.linkedin.com/pub/nifras-ismail/54/343/94b>
On Sun, Dec 13, 2015 at 12:37 PM, Nirmal Fernando <[email protected]> wrote:
> What does multi-class multi-label means? What's the use case you are
> trying to solve?
>
> On Sun, Dec 13, 2015 at 12:31 PM, NIFRAS ISMAIL <[email protected]>
> wrote:
>
>> Hi Maheshakya,
>> Thank your reply I have did those earlier on multi-class classification
>> techniques but my issue is not only multi-class classification it's
>> multi-class multi-label problem.
>>
>> That is on multi-class, I only predict which class label is suitable for
>> me. . Here I need to predict which labels are suitable.
>>
>> Example
>>
>> consider the following
>> dataset
>> :
>>
>>
>> I have got result from WSO2 ML is 'kill'
>>
>>
>>
>> But I should got the list of predictions like "kill" , "Yes"
>>
>>
>> Do I get this list from WSO2 ML? Is there any other possibilities. I am
>> not aware of WSO2 CEP.
>>
>> Looking forward your great support.
>>
>> Thank you
>>
>> Nifras
>>
>>
>>
>>
>>
>>
>> On Dec 10, 2015 9:45 AM, "Maheshakya Wijewardena" <[email protected]>
>> wrote:
>>
>>> Hi,
>>>
>>> You can use the multi class classification algorithms in WSO2 Machine
>>> Learner for your task. The quick start guide(
>>> https://docs.wso2.com/display/ML100/Quick+Start+Guide) describes the
>>> steps you have to follow from uploading a dataset to predicting from a
>>> trained a model.
>>> If you need to predict from data online (in case a new customer comes),
>>> use WSO2 CEP extension for ML predictions(
>>> https://docs.wso2.com/display/ML100/WSO2+CEP+Extension+for+ML+Predictions
>>> ).
>>>
>>> Best regards.
>>>
>>> On Wed, Dec 9, 2015 at 4:41 PM, NIFRAS ISMAIL <[email protected]>
>>> wrote:
>>>
>>>> Hi Machine Learners,
>>>>
>>>> Again I need your favour for Data Anaysis on My final year projects.
>>>>
>>>> My Meta Data Labels are
>>>>
>>>>
>>>> "city","country","birthdate","education","gender","houseowner","marital_status","member_card","num_cars_owned","num_children_at_home","occupation","postal_code","state_province","total_children","yearly_income","product_name"
>>>>
>>>> You may notice that this is a customer and his transaction mapping data
>>>> of a shopping mall.
>>>>
>>>> Class Label is : product_name
>>>>
>>>> Problem: My issue is I need to find the interest classes from my data
>>>> which contains the above headers.
>>>>
>>>> then If a new customer come to the mall I may predict which item he
>>>> will looking for using Multi Class Multi Label Classification.
>>>>
>>>>
>>>> Could Any one there to help to me ? Looking forward your reply ML Team
>>>>
>>>> Thank you
>>>>
>>>>
>>>> Regards.
>>>> *M. Nifras Ismail*
>>>> [image: LinkedIn] <http://lk.linkedin.com/pub/nifras-ismail/54/343/94b>
>>>>
>>>>
>>>>
>>>>
>>>>
>>>> Sent with MailTrack
>>>> <https://mailtrack.io/install?source=signature&lang=en&[email protected]&idSignature=22>
>>>>
>>>> _______________________________________________
>>>> Dev mailing list
>>>> [email protected]
>>>> http://wso2.org/cgi-bin/mailman/listinfo/dev
>>>>
>>>>
>>>
>>>
>>> --
>>> Pruthuvi Maheshakya Wijewardena
>>> Software Engineer
>>> WSO2 : http://wso2.com/
>>> Email: [email protected]
>>> Mobile: +94711228855
>>>
>>>
>>>
>>
>>
>> Sent with MailTrack
>> <https://mailtrack.io/install?source=signature&lang=en&[email protected]&idSignature=22>
>>
>>
>>
>> Sent with MailTrack
>> <https://mailtrack.io/install?source=signature&lang=en&[email protected]&idSignature=22>
>>
>> _______________________________________________
>> Dev mailing list
>> [email protected]
>> http://wso2.org/cgi-bin/mailman/listinfo/dev
>>
>>
>
>
> --
>
> Thanks & regards,
> Nirmal
>
> Team Lead - WSO2 Machine Learner
> Associate Technical Lead - Data Technologies Team, WSO2 Inc.
> Mobile: +94715779733
> Blog: http://nirmalfdo.blogspot.com/
>
>
>
_______________________________________________
Dev mailing list
[email protected]
http://wso2.org/cgi-bin/mailman/listinfo/dev
