Evaluate Your Model's Performance in Amazon SageMaker Canvas

After you’ve built your model, you can evaluate how well your model performed on your data before using it to make predictions. You can use information, such as the model’s accuracy when predicting labels and advanced metrics, to determine whether your model can make sufficiently accurate predictions for your data.

The section Evaluate your model's performance describes how to view your model’s accuracy score, broken down by model type. For each model, there is an Overview tab, which gives you a general overview of the model’s performance, depending on the model type. There is also a Scoring tab, which shows visualizations that you can use to get more insights into your model's performance beyond the overall accuracy metric.

The Advanced metrics for your model contain information that you can use for a deeper understanding of your model's performance. For information about how to view metrics you can use to quantify your model’s accuracy, see Use advanced metrics in your analyses.