Submissions are evaluated based on the [Mean Absolute Error (MAE)](https://www.kaggle.com/code/metric/mean-absolute-error/log?scriptVersionId=151169616), which measures the average magnitude of errors between the predicted and actual home values. A mean absolute error of 10,000 would suggests that, across all homes in the test sample, you can expect the predictions to be approximately $10,000 away from the actual home values.

## Submission File
For each **homeid** in the test set, you must predict the **target_homevalue** variable, which reflects the dollar amount for a given house. The file should contain a header and have the following format:

    homeid,target_homevalue
    01624,123456
    07647,654321
    08202,99999
    etc.