As the title suggests, I have a longitudinal database (also called panel data). (I have over 100.000 observations. The time period is X years. This means that for every year I have the values of the same variables. So I can see how every variable fluctuates over these X years for a specific observation).
Now my question is: As I am doing some research on what machine learning (AND deep learning ) methods should be used I find barely any information about machine learning on this kind of data. In most cases you have a lot of observations on a specific moment OR one observation over a longer time period. Here it is a combination. F.e. I used LSTM in the past for time-series but I don't know how I can use it here as each year has multiple variables for a specific observation, not one. Someone that can help me or has experience with this?