{
  "fetched_at": "2026-10-24T15:55:22Z",
  "source_url": "https://www.kaggle.com/competitions/cse-465-kickstarter-projects-competition/data",
  "pages": [
    {
      "name": "data-description",
      "content": "<p>This dataset was scrapped from [Kickstarter](https://www.kickstarter.com/) to provide an opportunity for enthusiasts to build a success predictor for different projects hosted there</p>\n<p> Data here is close enough of what real problems can be like, different problems will be tackled through the building of the model and different trade offs will be explored in hope of achieving better accuracy. </p>\n  \n<h2>Files descriptions</h2>\n\n- `train.csv` has all the data you will need for training and validation\n- `test.csv` what you need to predict\n- `sample.csv` a sample of how the submitted file should look like (`id` are from `train.csv`)\n\n<h2>Data fields</h2>\n1. `id` : unique id for every record in the whole dataset (train + test)\n2. `name` : project name (from kickstart)\n3. `main_category` :  field of operation of the project (take care of the NaNs)\n4. `backers_count` :  number of investors in the project\n5. `blurb` :  project claim to achieve\n6. `category` :  specific field of category (needs cleaning)\n7. `converted_pledged_amount` :  amount of money invested in the project after currency conversion\n8. `country_displayable_name` :  the country which will host the project \n9. `created_at` :  time of project creation (in UNIX timestamp)\n10. `creator` :  name and other details of the creator (json dumped data)\n11. `currency_trailing_code` :  is the project money tracked or not\n12. `currency` :  the project native currency (not the backer's currency)\n13. `deadline` :  when will the kickstarter end\n14. `goal` :  the amount of money the project is attempting to raise\n15. `launched_at` :  when the project started to be funded\n16. `pledged` : the amount that has been pledged to the project. (in the currency of the `currency` column)\n17. `slug` :  creator-selected keyword for the project\n18. `source_url` : url of the project in kickstarter\n19. `spotlight` :  is the project spotlighted of not, learn more about spotlight from [here](https://help.kickstarter.com/hc/en-us/articles/115005135834-What-is-Spotlight-)\n20. `staff_pick` :  is the project recommended by kickstarter staff or not\n21. `state_changed_at` :  when the project state was changed\n22. `static_usd_rate` :  conversion rate\n23. `urls` :  project url with its rewards (if any), (in json format)\n24. `usd_pledged` :  amount of investment in us dollars \n25. `usd_type` : type of the dollar invested (international or not)  \n26. `usd_pledged_real` :  real us dollars which was invested\n27. `usd_goal_real` :  real goal in us dollars\n28. `state` :  the end result of the project (`failed`, `successful`, `canceled`)",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<h2>Can we predict if a kickstarter project will succeed or not?</h2>\n\n<p>With different tools and ideas explored through the semester in CSE465 ML Course, this project (competition) can be the grand finale as a challenge to test our understanding for everything we have been through together.</p>\n\n<p>And while the idea in itself is useful for everyone it's not the actual goal of this competition, the true target is to go with students in a new journey of challenges where they learn new and interesting ideas in data preprocessing and model development. They will get the chance to deal with encoded data formats like (unix timestamps), json dumped columns and NaN values across the whole dataset.</p>\n\n<h2>What should participants learn from this competition ? </h2>\n1. `sklearn` and its wide variety of algorithms and functionalities.\n2. `pandas` and how to preprocess data for better accuracy.\n3. Data Visualization using `matplotlib` or any other package.\n4. Working with large datasets in different formats.\n5. Using **Kaggle** notebooks for sharing code and ideas with others\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "## Evaluation\nThe evaluation metric for this competition is the Categorization Accuracy. It is the number of correct predictions made divided by the total number of predictions. Upload in the competition your predictions that reach the best accuracy and specify the parameters that you used.\n\n## Submission File\nFor each ID in the test set, you must predict the class variable. The file should contain a header and have the following format:\n\n```\nid,state\n307,failed\n308,successful\n309,successful\n310,failed\n311,successful\n312,successful\n```",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "This is a page where you can include rules that participants must accept before joining. You may wish to include rules like:\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}