{ "fetched_at": "2026-10-20T02:42:30Z", "source_url": "https://www.kaggle.com/competitions/fire-171-spring-2019-data-classification-challenge/data", "pages": [ { "name": "rules", "content": "# One account per participant\nYou cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.\n\n# Submission Limits\nYou may submit a maximum of 10 public entries per day. You may select up to 1 final private submission for judging. If you do not select, your top scoring submission automatically enters final private submission.\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "data-description", "content": "

Files

\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Description", "content": "# Prerequisites\n1. Create a new Kaggle account (if you don't already have one).\n2. Go to the [Team](https://www.kaggle.com/c/fire-171-spring-2019-data-classification-challenge/team) tab and set your Team Name as your UMD directory ID (all lowercase, not your number ID, not your full name), e.g. hh2. If you've set this up correctly, your submission result will be publicly shown as your UMD directory ID.\n\n# Goal\nIt is your job to predict if a customer will make a payment for the billed amount next month or not. \nFor each ID in the test set, you must predict a 1 or 0 value for the PAID_NEXT_MONTH variable.\n\n# What’s the difference between a private and public leaderboard?\nThe Kaggle leaderboard has a public and private component to prevent participants from “overfitting” to the leaderboard. If your model is “overfit” to a dataset then it is not generalizable outside of the dataset you trained it on. This means that your model would have low accuracy on another sample of data taken from a similar dataset.\n\n# Public Leaderboard\nFor all participants, the same 50% of predictions from the test set are assigned to the public leaderboard. The score you see on the public leaderboard reflects your model’s accuracy on this portion of the test set. If you overfit the test set, you can do very well on the public leaderboard and very bad on the private leaderboard.\n\n# Private Leaderboard\nThe other 50% of predictions from the test set are assigned to the private leaderboard. The private leaderboard is not visible to participants until the competition has concluded. At the end of a competition, we will reveal the private leaderboard so you can see your score on the other 50% of the test data. The scores on the private leaderboard are used to determine the competition winners. \n\n# Getting Started\nYou may explore and run your machine learning code with [Kernels](https://www.kaggle.com/c/fire-171-spring-2019-data-classification-challenge/kernels), a cloud computing environment that enables reproducible and collaborative analysis. More info: [Kernels Documentation](https://www.kaggle.com/docs/kernels)\n\n# Submission\n- Submit in the same format as sample submission, you can download an example submission file (sample-submission.csv) on the Data page.\n- Make sure the ID match your prediction. Your submission will show an error if you have extra columns (beyond ID and PAID_NEXT_MONTH) or rows.\n- Set your Team Name = your UMD Directory ID (not the numbers, not your full name).\n\nSubmission Deadline: Mar 27 2019, 2:00pm EST\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Evaluation", "content": "

The evaluation metric for this competition is Mean F1-Score. The F1 score, commonly used in information retrieval, measures accuracy using the statistics precision p and recall r. Precision is the ratio of true positives (tp) to all predicted positives (tp + fp). Recall is the ratio of true positives to all actual positives (tp + fn). The F1 score is given by:

\n

\\[ F1 = 2\\frac{p \\cdot r}{p+r}\\ \\ \\mathrm{where}\\ \\ p = \\frac{tp}{tp+fp},\\ \\ r = \\frac{tp}{tp+fn} \\]

\n

The F1 Score is the weighted average of Precision and Recall. Therefore, this score takes both false positives and false negatives into account. Intuitively it is not as easy to understand as accuracy, but F1 is usually more useful than accuracy, especially if you have an uneven class distribution. Accuracy works best if false positives and false negatives have similar cost. If the cost of false positives and false negatives are very different, it’s better to look at both Precision and Recall. The F1 metric weights recall and precision equally, and a good retrieval algorithm will maximize both precision and recall simultaneously. Thus, moderately good performance on both will be favored over extremely good performance on one and poor performance on the other.

\n\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }