Hosted by \r\nData Science London and Data Science Global as part of a\r\nBig Data Week event, and organised by Kaggle, the first ever global data science hackathon will take place at the same time in several cities around the world spanning a 24-hour period. During this time the data scientists\r\n will compete with each other for cash prizes using a large dataset provided by the Cook County, Illinois, local government.
\r\nThe challenge for the hackathon is to build with better more accurate predictive models of metropolitan air pollution. The EPA’s Air Quality Index is used daily by people suffering from asthma and other respiratory diseases to avoid dangerous levels of outdoor\r\n air pollutants, which can trigger attacks. According to the World Health Organisation there are now estimated to be 235 million people suffering from asthma. Globally, it is now the most common chronic disease among children, with incidence in the US doubling\r\n since 1980. The model we build could be used as the basis for an early warning system that is capable of accurately predicting dangerous levels of air pollutants on an hourly basis.
\r\nData Science Global is a non-profit organization dedicated to bringing together the world’s communities of data scientists, artists, technologists and visionaries. For our inaugural event, we are hosting a global data science hackathon. It will be taking\r\n place simultaneously in cities around the world: London, New York, Boston, Chicago, San Francisco, Melbourne, Canberra, Sydney and Turku, Finland, as well as remote participants competing directly through Kaggle. You can join in the live webcast from the\r\n participating venues at datascienceglobal.org
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Rules", "content": "\r\n\t\r\nYou cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.
\r\n\r\n Privately sharing code or data outside of teams is not permitted.\r\n It's okay to share code if made available to all participants on the forums.\r\n
\r\n\r\n Team mergers are allowed and can be performed by the team leader. In order to merge, the combined team must have a total submission count less than or equal to the maximum allowed as of the merge date. The maximum allowed is the number of submissions per day multiplied by the number of days the competition has been running.
\r\n
There is no maximum team size.
\r\nYou may submit a maximum of 8 entries per day.
\r\nYou may select up to 2 final submissions for judging.
\r\nStart Date: 4/28/2012 12:00 PM UTC
\r\nMerger Deadline: None
\r\nEntry Deadline: None
\r\nEnd Date: 4/29/2012 12:00 PM UTC
\r\n\t\r\nBoth the training and evaluation data sets have missing values, and our intention is to ignore these in calculating MAE. To do this, we have (in the solution file) transformed all NA's to "-1,000,000" and shown you where these occur by providing you with\r\n a sample submission that has these values in all of the correct places, and 0's everywhere else.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "SubmissionInstructions", "content": "There is a global first prize which all participants, competing in venues or remotely, are eligible to win. First place will be a cash prize, and there will be additional prizes in the form of Amazon Web Services vouchers.
\r\nEMC Data Science Global Hackathon 1st Prize – GBP 1,800 ( USD 2,850)
\r\n\r\n
Some venues have choosen to sponsor additional venues prizes for their local participants (you must have RSVP'd to the venue and be physically in attendance). Participants in these venues are also eligible to win the global prize
\r\nEMC Data Science London Hackathon 1st Prize – GBP 1,200 (USD 1,900)
\r\nNew York City @ Bloomberg Ventures - $500 USD equivalent in hardware, software and services.
\r\n(And an additional $500 for the related Visualization Contest)
\r\nAnd for the Melbourne Venue:
\r\nMelbourne Institute: USD $ 1050
\r\nhttp://www.melbourneinstitute.com/\r\n
\r\nLift Analytic: USD $520
\r\nhttp://www.liftanalytics.com.au \r\n
\r\nHuntel Global: USD $210
\r\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "data-description", "content": "The data consist of hourly measurements of various quantities (mostly are pollutants), where each row contains the measurements for one hour. Time slices ("chunks") of 11 days have been created, with the first 8 days of each chunk available in the training\r\n data. You are asked to make pdictions about various points within the following 3 days (1, 2 ,3, 4, 5, 10, 17, 24, 48, and 72 hours after the end of the 8-day training data).
\r\n
\r\nWithin the training data, you are provided the following:
The variables described above with "_(site_number)" are available for various sites, and similarly, "_(target_number)" will vary across several targets.
\r\nYou are provided with the lat/long of each sample site in a separate file.
\r\nDuring the 3-day pdiction periods, you are provided only:
\r\nYou should get these from the sample submission file provided.
\r\n
\r\nYour submission will include:
\r\nAll of the "target" variables have been transformed to be approximately on the same scale (each with mean approximately 0 [CORRECTION: only the variance was normalized, not the mean] and variance approximately 1). We will reveal what quantity each target variable\r\n is a measurement of after the competition ends.
\r\n
\r\nThere are many rows for which some of the measurements are missing. This occurs in both the training and evaluation data. Our intention is to ignore these in calculating your score (MAE). To do achieve that effect, we have (in the solution file) transformed\r\n all NA's to "-1,000,000" and shown you where these occur by providing you with a sample submission that has these values in all of the correct places, and 0's everywhere else. You should make sure your solution has "-1,000,000" in the appropriate places. We\r\n apologize for the inconvenience.