This is very interesting data set, with features that are resemble of other Big Data. Also, there are definite features about history data and test data, which potentially affects interpretation of AUC values. These and other are very important research topics. I hope that sponsor and owner of this big data could allow some of us to write research papers. Please let me know.
", "messages": [ { "id": 420805, "postDate": "2018-11-14T06:33:53.400Z", "content": "Failure is the part of our life. Even I had failed my LSAT exam twice but still I didn’t lose hope. I had motivated myself for the third try and I pulled myself up for the best kind of preparations. I joined one of the best courses and even downloaded many sample Practice LSAT Questions. All this finally helped me score really well.
", "rawMarkdown": "Failure is the part of our life. Even I had failed my LSAT exam twice but still I didn’t lose hope. I had motivated myself for the third try and I pulled myself up for the best kind of preparations. I joined one of the best courses and even downloaded many sample [Practice LSAT Questions][1]. All this finally helped me score really well.\n\n\n [1]: https://testmaxprep.com/lsat/free-lsat-prep", "votes": 1 }, { "id": 50234, "postDate": "2014-07-10T00:40:10.227Z", "content": "This is very interesting data set, with features that are resemble of other Big Data. Also, there are definite features about history data and test data, which potentially affects interpretation of AUC values. These and other are very important research topics. I hope that sponsor and owner of this big data could allow some of us to write research papers. Please let me know.
", "votes": 10 }, { "id": 255082, "postDate": "2017-12-08T08:40:31.240Z", "content": "Did you find out the answer to your question \"Can this data set be used for writing research papers?\"?
\n\nIt seems that the paper
\n\nNikulin V. (2015) An On the Method for Data Streams Aggregation to Predict Shoppers Loyalty. IJCNN, Killarney, Ireland, July 12-17, pp. 1454-1461.
\n\nrefers to this competition. I guess it was possible to use this data then?
", "rawMarkdown": "Did you find out the answer to your question \"Can this data set be used for writing research papers?\"?\n\nIt seems that the paper\n\nNikulin V. (2015) An On the Method for Data Streams Aggregation to Predict Shoppers Loyalty. IJCNN, Killarney, Ireland, July 12-17, pp. 1454-1461.\n\nrefers to this competition. I guess it was possible to use this data then?", "votes": 2 }, { "id": 93101, "postDate": "2015-09-21T15:09:39.377Z", "content": "Some people may find this paper interesting/useful (13th place in the contest):
\n\nNikulin V. (2015) An On the Method for Data Streams Aggregation to Predict Shoppers Loyalty. IJCNN, Killarney, Ireland, July 12-17, pp. 1454-1461.
", "rawMarkdown": "Some people may find this paper interesting/useful (13th place in the contest):\r\n\r\nNikulin V. (2015) An On the Method for Data Streams Aggregation to Predict Shoppers Loyalty. IJCNN, Killarney, Ireland, July 12-17, pp. 1454-1461.", "votes": 3 }, { "id": 131021, "postDate": "2016-08-12T09:38:43.047Z", "content": "Me too ...
", "rawMarkdown": "Me too ...", "votes": 1 }, { "id": 100306, "postDate": "2015-12-05T00:49:01.377Z", "content": "I'd like to use this data for my Master's degree capstone project. So I would also like to know.
", "rawMarkdown": "I'd like to use this data for my Master's degree capstone project. So I would also like to know.", "votes": 1 }, { "id": 50872, "postDate": "2014-07-18T18:37:47.350Z", "content": "I am game!
", "votes": 3 }, { "id": 50808, "postDate": "2014-07-17T23:39:15.947Z", "content": "I am also interested to know!
", "votes": 3 }, { "id": 78270, "postDate": "2015-05-13T18:29:59.267Z", "content": "I asked Kaggle Support about this, and here's there reply -
\nThanks for your interest in the competition! You can find details on the re-use of particular datasets on a competition's Rules page. Each competition has different rules, so be sure to check carefully. In general, our competition hosts retain copyright on their data, so we'd suggest you contact them directly if you have any more questions.
\nBut the Host is anonymous. under "COMPETITION-SPECIFIC TERMS" states that -
"COMPETITION SPONSOR: Anonymous"
Any help?
", "votes": 1 }, { "id": 72847, "postDate": "2015-04-21T04:42:41.713Z", "content": "I am also interested to know! did anyone know?
", "votes": 1 }, { "id": 50876, "postDate": "2014-07-18T19:11:25.053Z", "content": "There is some precedent for this. You could see how these papers quote/cite and refer to datasets hosted by Kaggle.
\nA recent one: http://arxiv.org/abs/1406.7865 on the Chalearn Connectomics dataset.
\nAn older one: ieee.org Also interesting summary: ...the dataset was a graph obtained by crawling the popular Flickr social photo sharing website, with user identities scrubbed. By de-anonymizing much of the competition test set using our own Flickr crawl, we were able to effectively game the competition. Our attack represents a new application of de-anonymization to gaming machine learning contests, suggesting changes in how future competitions ...
\nAn interesting one if you look at the authors and recognize a few: http://link.springer.com/chapter/10.1007/978-3-642-42051-1_16
\nAnd more papers on Kaggle contests on Google Scholar.
\nDo carefully read the rules on data redistribution, especially since this was a commercial data set by anonymous company, not an opensourced academic one. Do not assume that you have permission through silence:
\nUnless otherwise permitted by the terms of the Competition Website, Participants must use the Data solely for the purpose and duration of the Competition, including but not limited to reading and learning from the Data, analyzing the Data, modifying the Data and generally preparing your Submission and any underlying models and participating in forum discussions on the Website. Participants agree to use suitable measures to prevent persons who have not formally agreed to these Competition Rules from gaining access to the Data and agree not to transmit, duplicate, publish, redistribute or otherwise provide or make available the Data to any party not participating in the Competition.
", "votes": 1 }, { "id": 50869, "postDate": "2014-07-18T18:10:48.450Z", "content": "I understand that each competition has its own policy about further use of data. Since the request is raised, there is no objection at this time. Is it fair to assume that the data organizer would agree with further use of this interesting data set. Of course, we will certainly keep this data set private, without releasing raw data. The only thing is to document features of such data set, and to share best-of-practice with the community when dealing with such data. Is it acceptable?
", "votes": 1 }, { "id": 50613, "postDate": "2014-07-15T21:19:41.427Z", "content": "I second this request, I don't think there is any public dataset of this size that has the transaction history. The owner of the dataset will do a great service to the community if they allow the use of this data for open source work
", "votes": 1 }, { "id": 89121, "postDate": "2015-08-11T17:08:40.457Z", "content": "it was interesting challenge: bigData + dataSteams with retail application. By definition, all related data are public by now. So, do not waste time, and submit your paper when it will be ready to go..
", "rawMarkdown": "it was interesting challenge: bigData + dataSteams with retail application. By definition, all related data are public by now. So, do not waste time, and submit your paper when it will be ready to go..", "votes": -1 }, { "id": 55634, "postDate": "2014-10-05T12:48:54.293Z", "content": "can anyone answer to this question? Can we use these data for papers or not?
\n\nmany thanks!
" }, { "id": 50873, "postDate": "2014-07-18T18:48:45.170Z", "content": "couldn't agree more, in fact all one has to say in their paper is that 'we use this public data set and provide a link to the Kaggle competition.
" }, { "id": 50805, "postDate": "2014-07-17T21:33:55.870Z", "content": "I wonder if the organizer will agree with us, to use the data set for the secondary analysis. Obviously, the competition is over. Learning more about data will help us to learn about issues with big data analytics and will help us to understand why some predictions are more successful than others. Are there any issues for using this data set, beyond computing the predicted probabilities?
" }, { "id": 92960, "postDate": "2015-09-19T03:24:42.090Z", "rawMarkdown": "", "isDeleted": true } ], "comments": [ { "id": 420805, "author_name": "Hiettu49", "author_url": "", "post_date": "2018-11-14T06:33:53.400000", "content": "Failure is the part of our life. Even I had failed my LSAT exam twice but still I didn’t lose hope. I had motivated myself for the third try and I pulled myself up for the best kind of preparations. I joined one of the best courses and even downloaded many sample Practice LSAT Questions. All this finally helped me score really well.
", "votes": 1, "replies": [] }, { "id": 255082, "author_name": "ArturoValdivia", "author_url": "", "post_date": "2017-12-08T08:40:31.240000", "content": "Did you find out the answer to your question \"Can this data set be used for writing research papers?\"?
\n\nIt seems that the paper
\n\nNikulin V. (2015) An On the Method for Data Streams Aggregation to Predict Shoppers Loyalty. IJCNN, Killarney, Ireland, July 12-17, pp. 1454-1461.
\n\nrefers to this competition. I guess it was possible to use this data then?
", "votes": 2, "replies": [] }, { "id": 93101, "author_name": "Mary Petik", "author_url": "", "post_date": "2015-09-21T15:09:39.377000", "content": "Some people may find this paper interesting/useful (13th place in the contest):
\n\nNikulin V. (2015) An On the Method for Data Streams Aggregation to Predict Shoppers Loyalty. IJCNN, Killarney, Ireland, July 12-17, pp. 1454-1461.
", "votes": 3, "replies": [] }, { "id": 131021, "author_name": "JoaoPires", "author_url": "", "post_date": "2016-08-12T09:38:43.047000", "content": "Me too ...
", "votes": 1, "replies": [] }, { "id": 100306, "author_name": "jeortiz", "author_url": "", "post_date": "2015-12-05T00:49:01.377000", "content": "I'd like to use this data for my Master's degree capstone project. So I would also like to know.
", "votes": 1, "replies": [] }, { "id": 50872, "author_name": "Μαριος Μιχαηλιδης KazAnova", "author_url": "", "post_date": "2014-07-18T18:37:47.350000", "content": "I am game!
", "votes": 3, "replies": [] }, { "id": 50808, "author_name": "Μαριος Μιχαηλιδης KazAnova", "author_url": "", "post_date": "2014-07-17T23:39:15.947000", "content": "I am also interested to know!
", "votes": 3, "replies": [] }, { "id": 78270, "author_name": "Aditya", "author_url": "", "post_date": "2015-05-13T18:29:59.267000", "content": "I asked Kaggle Support about this, and here's there reply -
\nThanks for your interest in the competition! You can find details on the re-use of particular datasets on a competition's Rules page. Each competition has different rules, so be sure to check carefully. In general, our competition hosts retain copyright on their data, so we'd suggest you contact them directly if you have any more questions.
\nBut the Host is anonymous. under "COMPETITION-SPECIFIC TERMS" states that -
"COMPETITION SPONSOR: Anonymous"
Any help?
", "votes": 1, "replies": [] }, { "id": 72847, "author_name": "Joey Lin", "author_url": "", "post_date": "2015-04-21T04:42:41.713000", "content": "I am also interested to know! did anyone know?
", "votes": 1, "replies": [] }, { "id": 50876, "author_name": "Triskelion", "author_url": "", "post_date": "2014-07-18T19:11:25.053000", "content": "There is some precedent for this. You could see how these papers quote/cite and refer to datasets hosted by Kaggle.
\nA recent one: http://arxiv.org/abs/1406.7865 on the Chalearn Connectomics dataset.
\nAn older one: ieee.org Also interesting summary: ...the dataset was a graph obtained by crawling the popular Flickr social photo sharing website, with user identities scrubbed. By de-anonymizing much of the competition test set using our own Flickr crawl, we were able to effectively game the competition. Our attack represents a new application of de-anonymization to gaming machine learning contests, suggesting changes in how future competitions ...
\nAn interesting one if you look at the authors and recognize a few: http://link.springer.com/chapter/10.1007/978-3-642-42051-1_16
\nAnd more papers on Kaggle contests on Google Scholar.
\nDo carefully read the rules on data redistribution, especially since this was a commercial data set by anonymous company, not an opensourced academic one. Do not assume that you have permission through silence:
\nUnless otherwise permitted by the terms of the Competition Website, Participants must use the Data solely for the purpose and duration of the Competition, including but not limited to reading and learning from the Data, analyzing the Data, modifying the Data and generally preparing your Submission and any underlying models and participating in forum discussions on the Website. Participants agree to use suitable measures to prevent persons who have not formally agreed to these Competition Rules from gaining access to the Data and agree not to transmit, duplicate, publish, redistribute or otherwise provide or make available the Data to any party not participating in the Competition.
", "votes": 1, "replies": [] }, { "id": 50869, "author_name": "Late Comer", "author_url": "", "post_date": "2014-07-18T18:10:48.450000", "content": "I understand that each competition has its own policy about further use of data. Since the request is raised, there is no objection at this time. Is it fair to assume that the data organizer would agree with further use of this interesting data set. Of course, we will certainly keep this data set private, without releasing raw data. The only thing is to document features of such data set, and to share best-of-practice with the community when dealing with such data. Is it acceptable?
", "votes": 1, "replies": [] }, { "id": 50613, "author_name": "sb79", "author_url": "", "post_date": "2014-07-15T21:19:41.427000", "content": "I second this request, I don't think there is any public dataset of this size that has the transaction history. The owner of the dataset will do a great service to the community if they allow the use of this data for open source work
", "votes": 1, "replies": [] }, { "id": 89121, "author_name": "", "author_url": "", "post_date": "2015-08-11T17:08:40.457000", "content": "it was interesting challenge: bigData + dataSteams with retail application. By definition, all related data are public by now. So, do not waste time, and submit your paper when it will be ready to go..
", "votes": -1, "replies": [] }, { "id": 55634, "author_name": "Reza", "author_url": "", "post_date": "2014-10-05T12:48:54.293000", "content": "can anyone answer to this question? Can we use these data for papers or not?
\n\nmany thanks!
", "votes": 0, "replies": [] }, { "id": 50873, "author_name": "sb79", "author_url": "", "post_date": "2014-07-18T18:48:45.170000", "content": "couldn't agree more, in fact all one has to say in their paper is that 'we use this public data set and provide a link to the Kaggle competition.
", "votes": 0, "replies": [] }, { "id": 50805, "author_name": "Late Comer", "author_url": "", "post_date": "2014-07-17T21:33:55.870000", "content": "I wonder if the organizer will agree with us, to use the data set for the secondary analysis. Obviously, the competition is over. Learning more about data will help us to learn about issues with big data analytics and will help us to understand why some predictions are more successful than others. Are there any issues for using this data set, beyond computing the predicted probabilities?
", "votes": 0, "replies": [] }, { "id": 92960, "author_name": "", "author_url": "", "post_date": "2015-09-19T03:24:42.090000", "content": "", "votes": 0, "replies": [] } ], "raw_markdown_by_id": { "420805": "Failure is the part of our life. Even I had failed my LSAT exam twice but still I didn’t lose hope. I had motivated myself for the third try and I pulled myself up for the best kind of preparations. I joined one of the best courses and even downloaded many sample [Practice LSAT Questions][1]. All this finally helped me score really well.\n\n\n [1]: https://testmaxprep.com/lsat/free-lsat-prep", "50234": "", "255082": "Did you find out the answer to your question \"Can this data set be used for writing research papers?\"?\n\nIt seems that the paper\n\nNikulin V. (2015) An On the Method for Data Streams Aggregation to Predict Shoppers Loyalty. IJCNN, Killarney, Ireland, July 12-17, pp. 1454-1461.\n\nrefers to this competition. I guess it was possible to use this data then?", "93101": "Some people may find this paper interesting/useful (13th place in the contest):\r\n\r\nNikulin V. (2015) An On the Method for Data Streams Aggregation to Predict Shoppers Loyalty. IJCNN, Killarney, Ireland, July 12-17, pp. 1454-1461.", "131021": "Me too ...", "100306": "I'd like to use this data for my Master's degree capstone project. So I would also like to know.", "50872": "", "50808": "", "78270": "", "72847": "", "50876": "", "50869": "", "50613": "", "89121": "it was interesting challenge: bigData + dataSteams with retail application. By definition, all related data are public by now. So, do not waste time, and submit your paper when it will be ready to go..", "55634": "", "50873": "", "50805": "", "92960": "" } }