So I have a time series set of data and I need to be able to forecast out in the future, however the data is highly reliant on what we asked for (the number) and the rates associated with that number. There are over 240,000 unique combinations that this data applies to. Does anyone have any experience with this type of data, or any recommendations on what to check out in order to help with the forecasting? Reference Forecasting seemed like my best bet so far, but I wasn't sure if there was some other algorithm that may prove useful.
[link][7 comments]