How do you decide which machine learning projects to work on?

  • The project should have high impact, where cheap prediction is valuable for the complex parts of your business process.

  • The project should have high feasibility, which is driven by the data availability, accuracy requirements, and problem difficulty.

  • Here are 3 types of hard machine learning problems:

    • (1) The output is complex.

    • (2) Reliability is required.

    • (3) Generalization is expected.

Last updated