Choose the scoring metric you’d like to use for your competition in the drop down menu, or see below for how to write your own metric in Python.

There are many ways to determine “how accurate” a submission may be. In the grocery store competition example, you may want to reward underestimates more than overestimates, or reward predictions exponentially more the closer they get to the ground truth. If you are unfamiliar with the types of common evaluation metrics used in machine learning, we’d encourage you to take a look at the details of common evaluation metrics to find the right fit.

Kaggle provides two types of metrics: Python (tagged with the  icon ) and Legacy (no icon). There are a few key differences. The source code for Legacy metrics is not publicly available and they typically have limited documentation. The setup process is also slightly different: Legacy metrics require manually mapping every column. However, Legacy metrics do offer speed advantages in some circumstances.