Forecasting Without Sales History

If you don’t have any sales history then it can be pretty tricky to plan inventory. However new businesses, businesses that have just migrated to a new ERP system or existing businesses that introduce new product lines will, inevitably, have to create forecasts at some point for products with little to no sales history.

SkuBrain, of course, allows you to manually adjust forecasts for any of the products that you sell. So if the statistical forecast that SkuBrain comes up with is 0 units (which would be pretty typical for products without any sales history) you can always manually override this with some estimates that you’ve come up with after talking to suppliers or some other kind of market research.

Previously, such manual adjustments would have been required for any product that had less than one month of sales history since, until a month is fully completed, SkuBrain considers it part of the “forecast horizon” rather than the “sales history” and most statistical forecasting algorithms only use sales history in order to generate forecasts.

However now SkuBrain includes a handy feature called extrapolated forecasts, which lets it create ballpark forecasts for products, even when you only have a couple of days worth of sales history for these.

Extrapolated Forecasts

Extrapolation is super simple. Essentially, if you create a forecast on October 13th for a product that you’ve only been selling since October 1st, SkuBrain extrapolates those early sales figures out so that the estimated sales for the full month of October (for that SKU) will be:

    Forecasted Sales  = Sales to Date * Days in Month / Days Elapsed
                      = Sales to Date * 31 / 13

The result is non-zero forecasts even for products with no “sales history” (in strict forecasting terms).

extrapolated forecast

The above forecast was generated on October 13th… so roughly one third of the way through the month of October. The projected sales for the full month are therefore roughly 3 times (31/13 times to be precise) sales to date. This is probably pretty much the process you’d use if you were going to generate these forecasts manually.

Hopefully this helps make things smoother for folks that are just starting out or anyone who often needs to forecast new products!