How to get the best combinations of features for a sale optimization problem?

Question

I have a database of shoes items from the same brand with many variables (features) like the size, the color or the shape. I also have the produced and sold quantity for the last years.

This is a sample of the database:

I would like to know what are the best combinations of features to have the perfect shoes, i.e the shoes which will be sold the most for sure. The Ratio (last column) is the variable which gives a "score" to an item (=an combination of features). For example, the best combination can be : construction=vulcanized + colour=brown but without width=welded.

I am using Python to read the database and using the library Pandas. This problem can be an optimization problem. What are the possibilities in data science to solve this kind of problem ?

Answer 1

Whenever you have an optimization problem the first question that you have to ask yourself is.

Can I make it a Linear Programming problem?

For python I normally use Gurobi. Here is a basic example to get started: https://www.gurobi.com/resources/food-manufacture-i/

You can also do Machine Learning with it, that is the hot topic nowadays, but if you can make it a linear programming problem you will achieve optimality.