When dealing with categorical values, should the 'year' column be encoded using OHE or OrdinalEncoder?

Question

It's a car prices dataset, and so I'm assuming that the more recent the more value a car should have. The values in the 'year' column simply consist of years from 1995 to 2020.
I am trying to predict the selling price of the car.

I'm a bit new to ML, currently still doing my undergraduate so any help / tips are appreciated. Thank you.

Answer 1

You should ask yourself if the order of years has an effect in predicting the price? It seems it is important. Therefore, OrdinalEncoder seems to be a better choice. If you use OneHotEncoder, you consider the years with equal weights in predicting the price.