I am currently working on a project where I have to forecast the revenue for (the duration of) projects within the organisation. The organisation has several departments that occupy themselves with a certain subject (such as Financial services or Data & Analytics). Within these departments there are numerous amounts of projects taking place. Each project has revenue that is booked each month.
Since the historical pattern of the revenue of the project doesn't give an indication as to what comes next (such as when using univariate models), I have been looking at multivariate models and ML/DL models (under which RNN and NBeats of darts). These models allow me to use other time series to forecast the 'current' one. I am however not completely sure this is the right approach.
Has anyone had experience with such type of forecasting? Do you have any tips perhaps?