I had this small project, where a client wanted a small tool to 'predict' the amount of hours that the project will need over the following X weeks.
There are few assumptions here:
- The project takes X total hours
- The project takes up a lot of hours in the beginning. There is also a bump in hours at the end of the project in the last 4 weeks.
The aim here is to give an estimation about the hours per week that are needed for the project.
I first tried some weird stuff with a cubic function, but I quickly realized this was the wrong way to go.
Multi-modal distributions are a combination of multiple distributions.