Execution

Start by going to your Data Science project and make sure the Mission workbench have these settings:

  • Image: TrustyAI

  • Size: Standard

Go to the folder lab-materials/07 where you will find the model and code to help you analyze and build new ones.

Task 1 - Understand what’s wrong

Run through the code in notebook 1_model_training_and_evaluation.ipynb to build a model and see what might be wrong with it. How does it perform on the evaluation, are there any data features that seem to be suspiciously impactful?

Task 2 - Propose and test changes

After you have made some thoughts on what might be wrong, go back to the start of the notebook and change what data features are used and how the data is processed. The goal is to get as small of an error as possible while also having no/few negative prices (they are typically bad for business). You can change the datapoint you are analyzing with Counterfactual and SHAP (SHapley Additive exPlanations) by changing the value of DATAPOINT, do this to test with both points that predict below 0 and the worst prediction.

DATAPOINT refers to the specific data entry or observation that you are analyzing or testing within the model. By changing the value of DATAPOINT, you’re selecting different input data for the model to analyze.

If you re-run the notebook, make sure to restart the kernel so that no results from the previous session are introduced in your new one. One very easy way to do this is to click this fast-forward button:

run all button