The Goal

Can you analyze a property's features to accurately estimate its market value?

Your goal is to build a regression model to predict the sale price of a house. The target column you are predicting is Price_in_Lakhs, which is a continuous numerical value.

The Challenge

This is a classic and highly practical machine learning problem. Your task is to perform a complete data science workflow:

Exploratory Data Analysis (EDA): Understand the features. Which ones are most correlated with price? How are features like Location or Num_Bedrooms distributed?

Feature Engineering: Create new, predictive features from the data provided. For example, does Area_sq_ft per bedroom matter?

Modeling: Build and train a regression model (like Linear Regression, Decision Trees, Gradient Boosting, etc.) to minimize the error of your price predictions.

How to Get Started

Participation: This is an individual competition.

Explore the Data: Download train.csv and test.csv. Check the Data tab for a full description of all columns.

Build Your Model: Start your .ipynb notebook.

Submit Your Predictions: When you're ready, submit your predictions for test.csv. Your submission must be a .csv file with two columns: ID and Price_in_Lakhs. The sample_submission.csv file shows the exact format required.

Final Ranking & Deliverables

Your ranking on the Public Leaderboard is for your reference (scored on a portion of the test data). Your final, official score will be calculated on the Private Leaderboard (scored on the rest of the test data), which will be revealed only after the competition deadline.

To be eligible for final rankings and prizes, you must submit two items:

Kaggle Submission: Your prediction .csv file submitted to the Kaggle leaderboard.

Code Notebook (.ipynb): You must also submit your final Jupyter Notebook, named with your name, to the official submission link (to be provided by organizers). Your final rank is conditional on submitting a working notebook that can reproduce your leaderboard score.

Good luck!