{ "fetched_at": "2026-10-20T03:35:36Z", "source_url": "https://www.kaggle.com/competitions/become-a-kaggle-master-2024-hw1/data", "pages": [ { "name": "data-description", "content": "# File descriptions\n- train.csv - the training set\n- test.csv - the test set\n- data_description.txt - full description of each column, originally prepared by Dean De Cock but lightly edited to match the column names used here\n- sample_submission.csv - a benchmark submission from a linear regression on year and month of sale, lot square footage, and number of bedrooms\n\n# Data fields\nYou can find a description of all 79 features in features_description.csv", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Description", "content": "# Description\n\nThe \"Become a Kaggle Master\" course is an essential component of the IASD Master 2 program, offered in collaboration among Université Paris Dauphine, ENS, and Mines ParisTech. This course introduces students to Kaggle competitions, which are recognized globally for their challenging, practical data science problems.\n\n## The Dataset\n\nIn this assignment, students will work with a modified version of the Ames Housing dataset. The dataset contains 79 variables describing various attributes of residential homes, such as the year built, lot size, number of rooms, material quality, and house condition. This rich variety of data types offers a realistic challenge similar to those encountered in professional data science roles.\n\n## The Problem\n\nStudents are tasked with developing a model to predict house prices based on the dataset's extensive features. This predictive modeling exercise requires understanding the complex interactions between various house attributes and their impact on pricing, which is vital for real-world real estate valuation.\n\n## Learning Objectives\n\nKey learning outcomes of this competition include:\n\n- Practical experience with data cleaning and preprocessing.\n- Data exploration and visualization to identify patterns.\n- Building and tuning machine learning models using Python libraries such as scikit-learn and TensorFlow.\n- Evaluating model performance using metrics like the Root Mean Square Error (RMSE).\n\n## Submission and Evaluation\n\nSubmissions will be evaluated on a provided test set, with the RMSE metric determining performance. The goal for participants is to achieve the lowest possible RMSE, indicating high accuracy in their price predictions.\n\n## Conclusion\n\nThis competition is designed to provide foundational skills in data science, preparing students to address complex problems through data-driven decision making and predictive modeling in their future careers.\n\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Evaluation", "content": "## Evaluation Criteria\n\nThe evaluation of your submissions will be conducted by computing a score based on your model's performance. The baseline score will set a standard where achieving this score will correspond to a grade of 10 out of 20. The best performing group's score will set the benchmark for a grade of 20 out of 20. All other participants' grades will be determined linearly in proportion to these two benchmarks. This method ensures that your grade reflects how your performance compares to the established benchmarks of the baseline and best scores.\n\n## Submission Guidelines\n\nParticipants must submit all required materials through Moodle by the specified deadline. It is crucial to adhere to the submission timeline as late submissions risk not being graded. Ensure that you check and include all necessary files and documentation to support your project.\n\n### Key Points to Remember:\n\n- **Deadline Compliance:** Submit your materials on or before the due date to avoid penalties.\n- **Complete Submissions:** Include all required documents, code files, and write-ups as specified in the assignment instructions.\n\nFailure to comply with these guidelines could result in your submission not being evaluated, which would impact your grade for this course. Please plan accordingly to ensure timely and complete submissions.\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "rules", "content": "# No external data allowed in this competition\nIf participants are using external data, they will be automatically disqualified.\n\n\nTwo participants per group\nYou cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.\n\nNo 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\nTeam Limits\nThe maximum team size is 2", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "abstract", "content": "# Context\nThis is homework 1 of the course 'Become a Kaggle Master'.\nThis course is part of the IASD Master 2 in Machine Learning, Artificial Intelligence, and Data Science program, jointly run by Université Paris Dauphine, ENS and Mines ParisTech.\n\n# Goal\nThe goal of the competition is to predict house prices using a modified version of the Ames Housing dataset, which includes 79 features describing various aspects of residential homes. The objective is to develop a model that can accurately predict house prices based on the provided features. The competition is open to all students enrolled in the course and serves as an introduction to Kaggle and practical machine learning", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }