# Evaluation

## Goal
The goal of this competition is to predict property value scores for residential houses based on their characteristics and features. Your task is to build a model that can accurately estimate these scores using the provided features.

## Metric
This competition is evaluated using Root Mean Square Error (RMSE). The RMSE is calculated as:

$$ RMSE = \sqrt{\frac{1}{n}\sum_{i=1}^{n}(y_i - \hat{y}_i)^2} $$

Where:
- $n$ is the number of houses in the test set
- $y_i$ is the actual property value score for house $i$
- $\hat{y}_i$ is the predicted property value score for house $i$

Lower RMSE values indicate better performance. The RMSE particularly penalizes large prediction errors due to the squared term in the formula.

## Submission Format
For each house in the test set, you must predict a property value score. The file should contain exactly two columns:

- `id`: The ID of the house
- `property_value_score`: Your predicted value (between 0 and 100)

## Timeline
The competition is split into two stages:
1. Public leaderboard (30% of test data)
2. Private leaderboard (70% of test data)

Your final rank will be determined by your score on the private leaderboard.

## Notes
- Predictions should be between 0 and 100
- The evaluation metric (RMSE) penalizes larger prediction errors more heavily than smaller ones
- Multiple submissions per day are allowed
- The final winners will be selected based on their private leaderboard scores

Remember that the goal is to create a robust model that generalizes well to unseen data, rather than one that simply memorizes the training set patterns.