Features at a higher resolution than the Dependant variable

time_series
temporal

#1

I have my dependant variable at hourly resolution and many of my features at 15 min resolution. My obvious instinct is to aggregate up, using a sum or mean ( depending on the nature of the variable). What other options do I have?

Does anyone have experience with this kid of situation?


#2

Hi @c3josh.

Definitely, the best way to bridge the gap between your dependent variable and independent variables is to use aggregation. This is also logically very correct.

Though I’ll appreciate you telling something more about your need for alternatives.