discoverychallenge / dc-evaluator-2016 Goto Github PK

@frederickayala How can we add new team members

Dear Sir / Madam

1. Do I have to participate on both tasks?
2. What kind of programming languages / libraries I could use? Do I have to use Python, or I can choose other language?

Thank you very much

Hello

I submitted a submission several hours ago, and still now it is in evaluation. Usually how does it take for evaluation?

Thanks

Will you post the full results? And can those see how they did on the full test set who didn't participate at the conference?

Many thanks,
Roland

hello, I am a member of one team of the challenge ECML/PKDD 2016.I want to know the content of the solution file to upload(code source or csv file?).thanks in advance

It looks like it uploads the solution, then there's a grey popup without text and nothing happens.

Hello!

I (from Degrees of Freedom) have uploaded a submission for Task 1 but I can't see its score and I haven't received any error message. Is there any problem with my solution format? Could you please check it?

Thanks in advance!
Tibi

Hi, when will we see the results or is it still possible to upload solutions?

I am facing problem while downloading data. It shows some bar progress when I click on download datasets but data never gets downloaded. I have tried using Chrome and Mozilla.

Please help out.

Hello,

I have read the instructions about the paper format and I have some related questions. LLNCS is the same as LNCS (Lecture Notes in Computer Science) and do I understand well that it is a LateX format? So, the paper should be made in LateX or it is possible to use other text editors (e.g. MS Word)?
The four pages limit is per tasks or is it an overall limit?

Thanks in advance,
Tibi

I consume that GEO_X is the latitude and GEO_Y is the longitude.
The "664808 244104" means the latitude is 66.4808 and the longitude is 24.4104. There is a problem that the latitude can be 85.9443 and couldn't find the place. Is that I am wrong in interpreting the Geolocation information?

As it was noted in Issue #14 users can apply for credit card multiple times. I wonder how the date in this column determined if a test user applies twice during 2014-15? The first one goes there?
Certainly too late to pop up with this question and I am happy with getting answer only after deadline.

I tried several times but it did not work.

I also used IE. It downloaded the dataset but the file was broken.

I have been approved.
I use Chrome to open the download dataset page. It shows me "please wait for the download to finish". But nothing to be download in Chrome after a few seconds.

There is no reaction when I submit my solution to task 2.

Hello,

The test data for the first half of 2015 has credit card transactions, which means some of the users already have credit cards.

When we say the prediction should be for the second half of the year, will it be possible to apply for second credit card by a user who already has a credit card from the bank ?

Is it correct to assume that the users who have made CC transactions are using this Bank's CC.

Thanks,
Suresh

I tried several times, the pages shows "There was an error while downloading the file. Please try again"

How can I solve this problem? Thanks!

The rules state: "Each team can upload a maximum 3 solutions per day."

How is the end time for the "submission day" defined? Is it defined according to a specific time zone? Or relative to the time of the team's first submission?

Thank you.
Lorenzo

In users_2014,
MIN(target_task_2) = 2014/01/31
MAX(target_task_2) = 2015/12/31

What are those of users_2015?
MIN(target_task_2) = 2014/01/31, 2015/01/31 or 2015/07/31

Dear Organizers,

I cannot find any information about the csv structure of first submission, can you share the file format information or give us an example submission file?

Thanks,
Ádám

What is the rule for final evaluation? How can participants control which submission to evaluate as the final model?

Hi everyone,
I am one of participants.
In task1, we combined the transaction and user dataset into a huge matrix (number of bank * number of user in 2014, number of features) as our training dataset. The features we extracted are
(1) user gender,
(2) user age category,
(3) user income category,
(4) user wealth category in 16 month,
(5) whether user has credict card in 16 month,
(6) user location geo information x and y,
(7) user location category,
(8) number of pos visits in first half of 2014 per user,
(9) number of webshop visits in first half of 2014 per user,
(10) number of amount of spent low, mid, high in first half of 2014 per user,
(11) number of transaction in market category a to j in first half of 2014 per user,
(12) number of transaction in the morning, afternoon, evening in first half of 2014 per user,
(13) number of credit card use in first half of 2014 per user,
(14) number of debit card use in first half of 2014 per user,
(15) the distance between user location and branch location,
(16) the distance between user social center location and branch location
(the social center of each user is determined by
sum( number of transaction in "a" pos * ("a" pos geo x, "a" pos geo y) ),
(17) number of branch visit decided by neighbors (based on user location geo)
in first half of 2014 per user,
(18) number of branch visit decided by users near social center
in first half of 2014 per user,