{ "fetched_at": "2026-10-19T19:13:50Z", "source_url": "https://www.kaggle.com/competitions/actuarial-loss-estimation/data", "pages": [ { "name": "data-description", "content": "This dataset includes 90,000 realistic, synthetically generated worker compensation insurance policies, all of which have had an accident. For each record there is demographic and worker related information, as well as a text description of the accident. \n\n# File descriptions\n\n- `train.csv.`: The training set containing 54,000 insurance policies that you can use to train your model\n- `test.csv`: The test set. \n- `sample_submission.csv`: A sample submission file in the correct format\n\n# Data fields\n\n- **ClaimNumber**: Unique policy identifier\n- **DateTimeOfAccident**: Date and time of accident\n- **DateReported**: Date that accident was reported\n- **Age**: Age of worker\n- **Gender**: Gender of worker\n- **MaritalStatus**: Martial status of worker. (M)arried, (S)ingle, (U)nknown.\n- **DependentChildren**: The number of dependent children\n- **DependentsOther**: The number of dependants excluding children\n- **WeeklyWages**: Total weekly wage\n- **PartTimeFullTime**: Binary (P) or (F)\n- **HoursWorkedPerWeek**: Total hours worked per week\n- **DaysWorkedPerWeek**: Number of days worked per week\n- **ClaimDescription**: Free text description of the claim\n- **InitialIncurredClaimCost**: Initial estimate by the insurer of the claim cost\n- **UltimateIncurredClaimCost**: Total claims payments by the insurance company. This is the field you are asked to predict in the test set. ", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Description", "content": "The Actuaries Institute of Australia, Institute and Faculty of Actuaries and the Singapore Actuarial Society are delighted to host the **Actuarial loss prediction competition 2020/21** to promote development of data analytics talent especially among actuaries. The challenge is to predict Workers Compensation claims using highly realistic synthetic data.\n\nThe data is fully synthetic and not specific to any legal jurisdiction or country. We are grateful to Colin Priest for building and supplying the dataset. \n\nWe invite the competitors to take claims inflation into account.\n\nUpon completion of the competition we may get in touch with the winners for knowledge sharing opportunities within the actuarial community. \n\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Evaluation", "content": "## Root Mean Squared Error (RMSE)\n\nSubmissions are scored on the root mean squared error. RMSE is very common and is a suitable general-purpose error metric. Compared to the Mean Absolute Error, RMSE punishes large errors:\n\n$$ RMSE = \\sqrt{\\frac{1}{N}\\sum_{1}^{N}\\big( y(i) - \\hat{y}(i) \\big)^2} $$\n\nwhere \\\\( \\hat{y}(i) \\\\) the predicted value and \\\\( y(i) \\\\) is the original value.\n\n## Submission File\n\nFor every policy in the dataset, submission files should contain two columns: `ClaimNumber` and `UltimateIncurredClaimCost`. \n\nThe file should contain a header and have the following format:\n\n```\nClaimNumber,UltimateIncurredClaimCost\nWC8145235,1000.0\nWC2005111,1000.0\nWC6899143,1000.0\nWC4785156,1000.0\nWC8145238,1000.0\netc.\n```", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "rules", "content": "### One account per participant\n \nYou cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.\n \n### No private sharing outside teams\n \nPrivately sharing code or data outside of teams is not permitted. It's okay to share code if made available to all participants on the forums.\n \n### Team Mergers\n \nTeam 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.\n \n### Team Limits\n \nThe maximum team size is 5.\n \n### Submission Limits\n \nYou may submit a maximum of 5 entries per day.\n \nYou may select up to 2 final submissions for judging.\n \n \n### COMPETITION-SPECIFIC RULES\n \nYou understand and agree to these Competition-Specific Rules:\n \n#### **ELIGIBILITY OF PARTICIPANTS CONNECTED TO COMPETITION SPONSOR**\nThe full list of host organisations for this competition is as follows: Imperial College London, Institute and Faculty of Actuaries, Actuaries Institute Australia, Singapore Actuarial Institute and The Université du Québec à Montréal (UQAM).\n \nEmployees, Students, Interns, contractors, officers and directors of the host organisations can participate and win this competition unless:\n1. They have had any contact with individuals on the organising committee regarding this competition, excluding contact related to promotional efforts.\n2. They are members of the organising committee\n3. They have had access to the competition dataset in any form prior to the official launch of the competition.\n \n#### **INDIVIDUALS AND TEAMS.**\n \nA. *Individual Account*. You may make Submissions only under one, unique Kaggle.com account. You will be disqualified if you make Submissions through more than one Kaggle account, or attempt to falsify an account to act as your proxy. You may submit up to the maximum number of Submissions per day as specified on the Competition Website.\n \nB. *Teams*. If permitted under the Competition Website guidelines, multiple individuals may collaborate as a team (a \"Team\"); however, you may join or form only one Team. Each Team member must be a single individual with a separate Kaggle account. You must register individually for the Competition before joining a Team. You must confirm your Team membership to make it official by responding to the Team notification message sent to your Kaggle account. Team membership may not exceed the Maximum Team Size stated on the Competition Website.\n \nC. *Team Merger*. Teams may request to merge via the Competition Website. Team mergers may be allowed provided that: (i) the combined Team does not exceed the Maximum Team Size; (ii) the number of Submissions made by the merging Teams does not exceed the number of Submissions permissible for one Team at the date of the merger request; (iii) the merger is completed before the earlier of: any merger deadline or the Competition deadline; and (iv) the proposed combined Team otherwise meets all the requirements of these Rules.\n \n#### **DETERMINING WINNERS.**\n \nEach Submission will be scored and ranked by the evaluation metric stated on the Competition Website. During the Competition Period, the current ranking will be visible on the Competition Website's public leaderboard. The potential winner(s) are determined solely by the leaderboard ranking on the private leaderboard, subject to compliance with these Rules. The public leaderboard will be based on the public test set and the private leaderboard will be based on the private test set.\n \nIn the event of a tie, the Submission that was entered first to the Competition will be the winner. In the event a potential winner is disqualified for any reason, the Submission that received the next highest score rank will be chosen as the potential winner.\n ", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Timeline", "content": "The competition runs from 18 December 2020 to 11 April 2021 at 23:59 UTC*.\n\n * Original deadline was March 07 and was extended by 1 month. ", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Prizes", "content": "This competition has been made possible with the help of the following sponsors:\n\n\n * \n\n\n

* The Canadian Institute of Actuaries is the voice of the actuarial profession in Canada.

 \n\n-----------------------\n\nWinners will be determined based on the leaderboard. Sponsors’ employees are not precluded from participating in the competition because the judging process is kept independent.\n\nWinners may be contacted for knowledge sharing opportunities, including writing a summary paper and participating in a webinar or panel discussions hosted by leading actuarial societies. \n\nYou may wish to structure your summary paper based on the [Kaggle Winning Model Documentation Template](https://www.kaggle.com/WinningModelDocumentationGuidelines", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }