PowerBi team announced a wonderful forecasting feature. It allows beautiful visual exploration of forecast, hindcast & confidence interval. It also allows detection of
You can play/read about it here.
On other hand last year we helped customers forecasting with help of R and they were pretty happy. R’s forecast package was written by Hyndman who has kindly recorded a great video on it. His cran documentation too is very neat and detailed.
The forecast package by itself allows creation of “period/season”. It allows analysis by different methods and plot them to show the deviation.
Power BI –
For first time I have seen teams describing algorithms they have used and how they diverge- validation window – compute the sum of squares of prediction errors for the window as a whole – thus dampening the variation . Team is also generous with links, references and best practices.
As the fan chart indicates error definitely goes up as the “period” becomes large for prediction.
BTW – Excel itself has decent trending abilities in form of trendline(linest) and lately forecasting.
The challenge with exponential smoothing is in terms of base which is mostly chosen as an average or worst case recent observations are given more weightage. Holt-Winter’s
Multiplicative exponential smoothing can take care of seasonality and auto-co-relation.
Gotta do the same exercise as R one day in PowerBI – I like the ease of use, visualization. R on other hand provides lot more ways to try out.