Ben Letham

Basically the multiplicative model is ``` y(t) = trend(t) * (1 + daily(t) + weekly(t) + yearly(t)) ``` where each of the seasonalities is stationary; so, `daily(t)` repeats itself exactly...

@numeric-lee to understand better - you have weekly data, and for each week there are multiple observations. It sounds like these are being averaged? And the sample size is the...

I think that if you wanted to prototype this in a local fork for your current use case, it actually wouldn't be too involved. You would add the weights into...

There is not. I can point you to the R reference manual (https://cran.r-project.org/web/packages/prophet/prophet.pdf). All of these functions are described at some point in the documentation so you could see how...

Some transforms for ObservationData require knowing ObservationFeatures. Particularly StratifiedStandardizeY, which standardizes Y but stratified on some conditions on X (https://github.com/facebook/Ax/blob/main/ax/modelbridge/transforms/stratified_standardize_y.py#L34). It is used for multi-task modeling, where data from different...

+1 for @rbagd's comment, Prophet assumes stationary seasonalities which is probably untrue for most human-related time series right now. In some areas there may be a long enough period of...

I had a discussion with some other forecasters on this question last week, and one thing that came up that I wanted to mention for other people trying to salvage...

@yuzuhikorunrun the problem there is that you're fitting a yearly seasonality (`annually-post-corona`) with quite a bit less than a year of data. The 2020 seasonality for June on is thus...

@shoaibkhanz I guess what you're doing is along the lines of fitting a model to the residuals (in this case the model is a rolling mean). That makes a lot...

@yuzuhikorunrun Monthly seasonality would mean a cycle within a month, and so wouldn't be appropriate here. Unfortunately with monthly data I don't think there is a whole lot that can...