{
  "fetched_at": "2026-10-24T09:48:44Z",
  "source_url": "https://www.kaggle.com/competitions/consent-to-sex-app-defence-against-false-claims/data",
  "pages": [
    {
      "name": "Evaluation",
      "content": "Submissions are scored based on the quadratic weighted kappa, which measures the agreement between two outcomes. This metric typically varies from 0 (random agreement) to 1 (complete agreement). In the event that there is less agreement than expected by chance, the metric may go below 0.\n\nThe quadratic weighted kappa is calculated as follows. First, an N x N histogram matrix <em>O</em> is constructed, such that <em>O<sub>i,j</sub></em> corresponds to the number of `Id`s <em>i</em> (actual) that received a predicted value <em>j</em>. An <em>N-by-N </em>matrix of weights, <em>w</em>, is calculated based on the difference between actual and predicted values:\n\n$$w_{i,j} = \\frac{\\left(i-j\\right)^2}{\\left(N-1\\right)^2}$$\n\nAn <em>N-by-N</em> histogram matrix of expected outcomes, <em>E</em>, is calculated assuming that there is no correlation between values.  This is calculated as the outer product between the actual histogram vector of outcomes and the predicted histogram vector, normalized such that <em>E</em> and <em>O</em> have the same sum.\n\nFrom these three matrices, the quadratic weighted kappa is calculated as: \n\n$$\\kappa=1-\\frac{\\sum\\_{i,j}w\\_{i,j}O\\_{i,j}}{\\sum\\_{i,j}w\\_{i,j}E\\_{i,j}}.$$\n\n\n## Submission File\nFor each `Id` in the test set, you must predict the value for the target `quality`. The file should contain a header and have the following format:\n\n    Id,quality\n    2056,5\n    2057,7\n    2058,3\n    etc.\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "Let me know if you need more info? It would be great to jump on a call if you think it would be beneficial to chat some ideas through? There will be a prize for the winner but i'm yet to see what the rules are for that",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "The dataset for this competition (both train and test) was generated from a deep learning model trained on the [Wine Quality dataset](https://www.kaggle.com/datasets/yasserh/wine-quality-dataset). Feature distributions are close to, but not exactly the same, as the original. Feel free to use the original dataset as part of this competition, both to explore differences as well as to see whether incorporating the original in training improves model performance.\n\n## Files\n\n*   **train.csv** - the training dataset; `quality` is the target (ordinal, integer)\n*   **test.csv** - the test dataset; your objective is to predict `quality`\n*   **sample_submission.csv** - a sample submission file in the correct format",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "**Welcome to the 2023 Kaggle Playground Series!** Thank you to everyone who participated in and contributed to Season 3 Playground Series so far! \n\n**Your Goal:** For this Episode of the Series, your task is to use regression to predict the quality of wine based on various properties. Good luck!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Can this be done?",
      "content": "Are we in the right place for a POC? Having been wrongly accused of sexual assault from a bitter ex, (someone I went on 5 dates with) I was very close to ending my life. It went on for months, the police didn't just arrest me once, but twice! They come to your home, usually at a ridiculous time in the morning, midweek, almost knock the door off the hinges, arrest you with no details and remove you from your home, your safe space. And there's nothing you u can do about it. when you're innocent, this has got to be the most horrendous feeling ever and most heinous crime by the accuser who is proven to be lying later on. There should be some kind of repercussions for these people but unfortunately, there is not. Is there a way we can develop an ad, using consenting biomentrics or NFC tag or awful QR codes but not only that, how about a dating/ social/ sexual rating to go along with this? What would the data tell us and how could it protect us?",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Dating & Consent App",
      "content": "I'd like to build an app for single and poly people to rate dates and individuals based on their behavior and to also use their biometrix, NFC tags or QR codes to consent to sex. A rating will build up a social and sexual profile which will help infer dating decisions and hopefully rule out ambiguous claims where it is thought that this approach is aiding the perpetrator, more than protecting. in my opinion, the minute you meet your date, the phone is in listening mode which both parties are aware of and will act as proof/evidence should it be needed. Can the data make predictions and form opinions or predictions of a misjustice/criminal likelihood? Can we use data sets such as ratings, like trust pilot also? Building up a character score? ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}