![\"Gini](\"http://kaggle2.blob.core.windows.net/competitions/kaggle/2509/logos/gini.JPG\" "\\"Gini")
Risk varies widely from customer to customer, and a deep understanding of different risk factors helps predict the likelihood and cost of insurance claims. The goal of this competition is to better predict Bodily Injury Liability Insurance claim payments based on the characteristics of the insured customer’s vehicle.
\r\nMany factors contribute to the frequency and severity of car accidents including how, where and under what conditions people drive, as well as what they are driving.
\r\nBodily Injury Liability Insurance covers other people’s bodily injury or death for which the insured is responsible. The goal of this competition is to predict Bodily Injury Liability Insurance claim payments based on the characteristics of the insured’s vehicle.
", "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 2 entries per day.
\r\nYou may select up to 5 final submissions for judging.
\r\nStart Date: 7/13/2011 3:45 AM UTC
\r\nMerger Deadline: None
\r\nEntry Deadline: None
\r\nEnd Date: 10/12/2011 11:59 PM UTC
\r\n\t\r\nBy registering for and/or submitting an entry to this contest, you agree to abide by these rules as well as Kaggle’s terms and conditions (http://www.kaggle.com/pages/terms).
\r\nThe competition will run until October 12, 2011.
\r\nFor Prizes and Evaluation, see the \"Prizes\" and \"Evaluation\" pages.
\r\nParticipants will not try to identify individual policyholders or vehicle types within the dataset.
\r\nParticipants will not use the data for commercial purposes.
\r\nParticipants will not use the data for purposes unrelated to the competition.
\r\nIf necessary, the competition host may modify the training and/or testing dataset to address any problems/issues that come up during the competition.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "data-description", "content": "Each row contains one year’s worth information for insured vehicles. Since the goal of this competition is to improve the ability to use vehicle characteristics to accurately predict insurance claim payments, the response variable (dollar amount of claims experienced for that vehicle in that year) has been adjusted to control for known non-vehicle effects. Some non-vehicle characteristics (labeled as such in the data dictionary) are included in the set of independent variables. It is expected that no “main effects” corresponding will be found for these non-vehicle variables, but there may be interesting interactions with the vehicle variables.
\r\nCalendar_Year is the year that the vehicle was insured. Household_ID is a household identification number that allows year-to-year tracking of each household. Since a customer may insure multiple vehicles in one household, there may be multiple vehicles associated with each household identification number. \"Vehicle\" identifies these vehicles (but the same \"Vehicle\" number may not apply to the same vehicle from year to year). You also have the vehicle’s model year and a coded form of make (manufacturer), model, and submodel. The remaining columns contain miscellaneous vehicle characteristics, as well as other characteristics associated with the insurance policy. See the \"data dictionary\" (data_dictionary.txt) for additional information.
\r\nOur dataset naturally contained some missing values. Records containing missing values have been removed from the test data set but not from the training dataset. You can make use of the records with missing values, or completely ignore them if you wish. They are coded as \"?\".
\r\nThere are two datasets to download: training data and test data. You will use the training dataset to build your model, and will submit predictions for the test dataset. The training data has information from 2005-2007, while the test data has information from 2008 and 2009. Submissions should consist of a CSV file. Records from 2008 will be used to score the leaderboard, and records from 2009 will be used to determine the final winner.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Evaluation", "content": "The training data consists of observations from 2005 to 2007. Observations from 2008 make up the test data used to score the public leaderboard (during the competition), and observations from 2009 make up the test data used for the private leaderboard (for final scoring).
\r\nThe metric (for both the leaderboard and final winners) used to score entries will be \"normalized Gini coefficient\" (named for the similar Gini coefficient/index used in Economics).
\r\nWhen you submit an entry, the observations are sorted from \"largest prediction\" to \"smallest prediction\". This is the only step where your predictions come into play, so only the order determined by your predictions matters. Visualize the observations arranged from left to right, with the largest predictions on the left. We then move from left to right, asking \"In the leftmost x% of the data, how much of the actual observed loss have you accumulated?\" With no model, you can expect to accumulate 10% of the loss in 10% of the predictions, so no model (or a \"null\" model) achieves a straight line. We call the area between your curve and this straight line the Gini coefficient.
\r\nThere is a maximum achievable area for a \"perfect\" model. We will use the normalized Gini coefficient by dividing the Gini coefficient of your model by the Gini coefficient of the perfect model.
\r\n
1st place: $6,000.
\r\n2nd place: $3,000.
\r\n3rd place: $1,000.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }