{ "fetched_at": "2026-10-24T23:17:58Z", "source_url": "https://www.kaggle.com/competitions/caltech-cs155-2022-miniproject1/data", "pages": [ { "name": "data-description", "content": "## Files\n\n* **LOANS_TRAIN.csv** - the training set, including labels\n* **LOANS_TEST** - the test set, excluding labels\n* **sample_submission.csv** - a sample submission file in the correct format\n\n## Columns\n\nSee **LCDataDictionary.xlsx** for column descriptions", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Description", "content": "# [Deprecated]\n\n## Miniproject #1\nFor this Kaggle competition, you will use data about loans (amount, location, borrower history) to predict whether or not the borrower will pay back the loan. These loans originated from LendingClub, a peer-to-peer lending platform, from 2007 to 2020, ranging from personal to business loans. \n\nThere can be 10 submissions per day per team, and the submission window will close on Wednesday 9 February 2022 at 2:00PM PST.\n\nYou may not use any additional data sources.\n\n## Acknowledgements\n\nWe thank the LendingClub database for this data, in addition to Yash for the data cleaning. This dataset was sourced from a different Kaggle competition (Lending Club 2007-2020Q3). **It is not permitted to visit that Kaggle page, read/use the associated Notebooks in any way, nor use any code online that was made for modeling this dataset, in order to make the competition fair. Doing so will be considered a violation of the Honor Code. Thanks for understanding!**", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Evaluation", "content": "### Metric\n\nThe evaluation metric for this competition is the Mean Column ROC AUC. This means we treat each loan as its own binary classification problem, and calculate the area under curve (AUC) of the receiver operating curve (ROC). It allows us to measure a balance of the false positive and true positive rate. It is elaborated on [here](https://scikit-learn.org/stable/modules/generated/sklearn.metrics.roc_auc_score.html).\n\nThe equivalent [sklearn command](https://scikit-learn.org/stable/modules/generated/sklearn.metrics.roc_auc_score.html) used by the Kaggle grader would be: \n```\nsklearn.metrics.roc_auc_score(y_ground_truth, y_predicted_probability)\n```\n\nSubmission Format\nFor every row of data in LOANS_TEST.csv, submission files should contain 2 columns:\n\n```id```: contains integers equal to the id's in the LOANS_TEST.csv file\n```loan_status```: contains an integer (0 or 1), with 0 representing that the loan is Fully Paid, and 1 representing that the loan is Charged Off. \n\nThe file should contain a header and have the following format:\n\n```\nid,loan_status\n200000,0.17\n200001,0.20\n...\n242479,0.67\n```", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "rules", "content": "## No Additional Data\nYou are not allowed to use any data outside that which has been provided on the two Kaggle sites. Any infractions will be treated as a violation of the honor code\n\n## One account per participant\nYou cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.\n\n## No private sharing outside teams\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\nTeam mergers are not allowed in this competition.\n\n## Team Limits\nThe maximum size of a team is 4 participants.\n\n## Submission Limits\nYou may submit a maximum of 10 entries per day.\n\nYou may select up to 2 final submissions for judging.\n\n## Competition Timeline\nStart Date: 2/2/2022\n\nEnd Date: 2/9/2022 2:00pm PST", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Tips", "content": "Credits to Jim Zhang for helping with these tips\n\n## Anaconda\nIf using Python, pandas is recommended for data manipulation. For prediction, one can start with some typical models in scikit-learn. pandas, numpy, sklearn are all included in Anaconda.\n\n## Useful pandas functions\n```\npd.read_csv('filename.csv', index_col='id')\npd.DataFrame.to_csv('submission.csv', index_label='id')\n```\n\n## Don't be afraid to try things you haven't heard of before\nAfter some basic models, one can progress to some more advanced models in other libraries. Maybe search around a bit for cool or successful models that people have used for classification.\n\n## IDE/Shortcuts\nLearn all the shortcuts to your development environment. Spyder and Jupyter are both included in Anaconda, and there are plenty of shortcuts to run specific code sections swiftly.\n\n## Missing data\nThink of how to fill in the missing/nan data. A starting point is `SimpleImputer`.\n\n## Feature engineering\nSee if you can create new features out of the existing columns, that would make the model perform better / have an easier time fitting the data\n\n## Model blending\nWhy use one model when you can take the average of multiple model outputs, or even use another model on top of the model outputs?\n\n## Probability calibration\nSome models don't have accurate classification probabilities, but one can calibrate them using various techniques. This doesn't help much for individual models due to the AUC metric, but allows for \"fairer\" model blending if you plan to take a simple average.\n\n## Hyperparameter tuning\nGain some intuition and then try some automatic tuners! Be aware, poor model types usually will not improve much with tuning.", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }