{ "id": 3073, "title": "Aftermath & What now?", "url": "/competitions/predict-closed-questions-on-stack-overflow/discussion/3073", "author_name": "", "post_date": "2012-11-05T14:19:32.993Z", "votes": null, "comment_count": 2, "views": 3408, "content": "

Whew! That was fun, wasn't it? Many thanks to StackOverflow and Kaggle for making that happen. I never did any real data mining before, so this contest was a great opportunity for me to try it. It was very educational -- got to learn some octave, python\r\n and numpy / scipy. Obviously nobody could touch mr. Melis, but at the 2nd place and below the competition was pretty fierce, and luck was definitely a factor there.

\r\n

So, what happens now? My understanding is that the organizers will try to reproduce the results of all in-the-money teams on their hardware, asking the teams for instructions and clarifications when necessary; then the winners list will be finalized and\r\n the prizes will be distributed. Is there an approximate timeline for that, or something?

", "messages": [ { "id": "16609", "postDate": "11/05/2012 14:19:32", "content": "

Whew! That was fun, wasn't it? Many thanks to StackOverflow and Kaggle for making that happen. I never did any real data mining before, so this contest was a great opportunity for me to try it. It was very educational -- got to learn some octave, python\r\n and numpy / scipy. Obviously nobody could touch mr. Melis, but at the 2nd place and below the competition was pretty fierce, and luck was definitely a factor there.

\r\n

So, what happens now? My understanding is that the organizers will try to reproduce the results of all in-the-money teams on their hardware, asking the teams for instructions and clarifications when necessary; then the winners list will be finalized and\r\n the prizes will be distributed. Is there an approximate timeline for that, or something?

", "rawMarkdown": "", "votes": null }, { "id": "16673", "postDate": "11/07/2012 16:52:39", "content": "

I also think I read that the winning solution(s) would be made publicly available / described somewhere? I'm interested to know how the winning teams did so well- maybe some kind of post-mortem blog post or something?

", "rawMarkdown": "", "votes": null }, { "id": "20976", "postDate": "03/01/2013 18:39:58", "content": "

Can we not get a brief writeup from the top-9 \r\nwinners? Similar to #10 \r\nMarco Lui's

\r\n

What text classification did you use? What model? What features?

\r\n
    \r\n
  1. Gabor Melis ('Malacka')
    \r\n
  2. nbu (Leonid Kalmankin &\r\nDmitry Kim)\r\n
  3. James Crosby\r\n
  4. F# with Composite\r\n Networks
  5. MaBu\r\n
  6. vikas\r\n
  7. Daniel Velkov\r\n
  8. Glen\r\n
  9. SquaredLoss\r\n
\r\n

 

\r\n

 

", "rawMarkdown": "", "votes": null } ], "comments": [ { "id": 16673, "author_name": "thomasfletcher", "author_url": "", "post_date": "11/07/2012 16:52:39", "content": "

I also think I read that the winning solution(s) would be made publicly available / described somewhere? I'm interested to know how the winning teams did so well- maybe some kind of post-mortem blog post or something?

", "votes": null, "replies": [] }, { "id": 20976, "author_name": "smcinerney", "author_url": "", "post_date": "03/01/2013 18:39:58", "content": "

Can we not get a brief writeup from the top-9 \r\nwinners? Similar to #10 \r\nMarco Lui's

\r\n

What text classification did you use? What model? What features?

\r\n
    \r\n
  1. Gabor Melis ('Malacka')
    \r\n
  2. nbu (Leonid Kalmankin &\r\nDmitry Kim)\r\n
  3. James Crosby\r\n
  4. F# with Composite\r\n Networks
  5. MaBu\r\n
  6. vikas\r\n
  7. Daniel Velkov\r\n
  8. Glen\r\n
  9. SquaredLoss\r\n
\r\n

 

\r\n

 

", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "16609": "", "16673": "", "20976": "" }, "source": "meta" }