> For the complete documentation index, see [llms.txt](https://fall2019.fullstackdeeplearning.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://fall2019.fullstackdeeplearning.com/course-content/setting-up-machine-learning-projects/prioritizing.md).

# Prioritizing

{% embed url="<https://www.youtube.com/watch?v=Dx3hKmNJ-1E>" %}
Prioritizing - ML Projects
{% endembed %}

* 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.