How can I strengthen my machine learning model?

Answer:

There are several methods to try if you want to refine and strengthen a machine learning model. Leverage the EDA Report and Results Summary Report to figure out what will work best for your model.

• Recipe Reconfiguration
  • Increase or decrease history training intervals
  • Increase or decrease how far in the future you are predicting
  • Change the scope of what core attributes are being tried by your model to include more features or better features
  • Manually exclude bad columns from being included in your model
  • Create and include more or better generative attributes
• Create separate models for different parts of your organization
• Hone in on a subset of your population when building your model
• Adjust your global settings to allow more columns to be tried
• Perform per column interventions
  • Null Fill columns that are being dropped due to missing data
  • Adjust the droppability to allow the model to try columns that are being automatically dropped due to global settings
• Configure the dimensionality reduction to increase or decrease the amount of columns your model includes
• Work with your CS Lead and Data engineer to bring in new data such as compensation data, survey data, or performance data

Check out this help content about Refining a Machine Learning Model in One AI for more information and specific instructions.