0
$\begingroup$

I have a data set that includes sales dollars by sales order and I want to perform a time series forecast on it. Low dollar sales orders have very little noise and after detrending and doing some prelim analysis and testing it looks like a forecast would work pretty well.The issue is there is a lot of variability in large orders that can skew the time series. I can remove any large outliers, but I wanted to know if there was a way I could optimize the threshold that determines large v. small orders so I can get a reasonable time series that doesn't have too much variance. Any ideas?

$\endgroup$
  • $\begingroup$ "Large outliers" sounds like a synonym for "the sales that make my business profitable." That's worth considering when you think about eliminating them from the analysis! $\endgroup$ – whuber Nov 16 '18 at 19:35
  • 1
    $\begingroup$ We still forecast them, but in a different way because we have more visibility to what's in the funnel for those, but the "run rate" business has more seasonality etc. Definitely don't take them out altogether! $\endgroup$ – Ben Gidaro Nov 19 '18 at 0:11
0
$\begingroup$

In this case, you will want to not adjust for outliers. If there is no way to forecast by customer then you will have to live with this the way it is.

Typically, forecasting dollars is not the best way to do things. Forecast units and then dollarize the forecast based on the price afterwards.

$\endgroup$
  • 1
    $\begingroup$ Out of curiosity, what's the advantage of forecasting units as opposed to dollars? Typically we've been forecasting revenue, but obviously always open to new ideas! $\endgroup$ – Ben Gidaro Nov 19 '18 at 0:13

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.