What kind of supervised model to use when i have vectors as input and vectors as output?

Question

I am making a project in wich i have to predict a plane trajectory. I have 2 types of trajectory, the first one is the planned, and the second one is the real one that i recovered after the end of the flight.

The two trajectories are (x,y) points on a map and i want to predict the real one with the planned one.

What kind of model do you use? I heard about multivariate regression or recurrent neural network but i am not sure about both, i think multivariate is not appropriate and rnn include time as parameter and i would not want to use it first.

Do you have any ideas? Thank you

Answer 1

You could try either training single-target multiple regression models, and predict the x and y variables independently. The other way to go about is to use multi-target regression-based methods. The most commonly used method using Predictive Clustering trees. You can read about various methods from https://towardsdatascience.com/regression-models-with-multiple-target-variables-8baa75aacd to start with. I hope it is somewhat helpful. :)