Register now to learn Fabric in free live sessions led by the best Microsoft experts. From Apr 16 to May 9, in English and Spanish.
Hi all, I have been searching high and low for a way to populate a column of forecasted values using DAX. Other than forecasting by moving average, I have not been able to find any methods to perform exponential smoothing forecasting using DAX.
I am currently exploring ways to do so on Query Editor. Assume I have the following simple dataset. How do I populate a column containing the forecasted numbers?
Here is the PBIX file:
https://www.dropbox.com/s/wc30mt5kron382t/Inventory%20Forecasting.pbix?dl=0
Thank you!
Hi @Anonymous,
The Exponential Smoothing is a little complicated. There could be a solution here by R.
# 'dataset' holds the input data for this script temp <- dataset temp$Date <- as.Date(temp$Date, '%Y-%m-%d') es <- c() minDate <- temp$Date[1] ds_length <- length(temp$Date) for (index in c(1:ds_length)) { if (temp[index,1] == minDate) { st <- temp[index, 3] } else { st <- 0.2 * temp[index, 3] + (1 - 0.2) * es[index - 1] } es[index] <- st } temp$es <- es
Best Regards,
Dale
Could you please clarify how to make this code reusable to just replace parameters (Date, Value)?
when I executed this code I received an error
(Error in if (temp[index, 1] == minDate) { :
missing value where TRUE/FALSE needed
Execution halted
)
Also, @v-jiascu-msft how do I forecast for the following year? Could you share the code for me (I don't know R language yet)? The calculation you provided only allows for forecasting in the same period.
anyone?
Thank you @v-jiascu-msft! Could you suggest me some resources to learning R on Power BI?
Covering the world! 9:00-10:30 AM Sydney, 4:00-5:30 PM CET (Paris/Berlin), 7:00-8:30 PM Mexico City
Check out the April 2024 Power BI update to learn about new features.
User | Count |
---|---|
110 | |
96 | |
76 | |
63 | |
55 |
User | Count |
---|---|
142 | |
107 | |
89 | |
84 | |
65 |