Forecast based on similar consumption profiles

I have heat consumption measurements in 6 facilities (monthly).

Based on data from 5 objects, I try to forecast consumption in one object. I need a forecast for the next 3 months. I am currently using random forest and got these results

What other approach do you propose? Can a more accurate forecast be expected?

This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.

If you have a query related to it or one of the replies, start a new topic and refer back with a link.