When forecasting sales to see how much inventory will be needed to meet demand in your eCommerce store, it can be difficult deciding which forecast to use. Seasonal? Year-round? Top-down? Bottom-up? How are you supposed to know which is best?
While there are many forecasting options available, available sales history, seasonality, and importance of recent trends can help to determine which is the best approach.
Use for: Products that sell with a constant sales velocity year-round.
Year-round forecasting is a combination of sales velocity and recent trends, which is the rate of sales excluding out of stock days (units sold divided by days in stock). This type of forecasting is appropriate for variants and products that sell consistently from month to month and still allows for increases in demand over time. Any sort of changes that happen to demand are not linked to the calendar—holidays, fashion seasons, back-to-school, etc. An example of year-round forecasting is alarm clocks. They sell consistently, and sales don’t spike in any month for any particular reason.
Use for: Inventory that peaks during particular times of the year.
Seasonal products emphasize the sales trends from the same month in the prior year rather than the most recent months. If you are forecasting August 2019, look back to August 2018 and August 2017. By looking at multiple years of seasonal sales, you can incorporate year over year growth.
One example of this is back-to-school sales, which always peak in August and September. Gauging sales of backpacks in May is inconsequential to what determining how many you need in stock to meet the demand in the fall.
If you see an increase from 2017 to 2018, apply that same increase to 2019 so you factor in year over year increases. For example, if there is a 25% increase from 2017 to 2018, apply a 25% increase to the 2018 sales to determine your 2019 forecast.
Use when: You want to forecast by variant using only the sales history for that variant.
Bottom-up forecasting considers each SKU, the most granular level of data of your products. It focuses on the variant level—each size, each color. Only the history of a particular variant is applicable to its forecast. For example, a pair of silver sandals in a size 9 will use data for that exact color and that exact size. It doesn’t matter what happened in the category, the same style, other sizes, or other colors. Only the history of the silver sandals size 9 matters to the forecast—not the black sandals, nor the size 8.
Use when: You have seasonal items with a short sales history or want to project sales by category.
Top-down forecasting looks at the category sales history to generate a forecast. If a category sells well in the summer but not in the winter, that seasonal trend will be used and applied to all variants in the category. A variant’s contribution to the category remains constant. For example, if the silver size 9 sandals contribute 2% to the total sales (units) for a category, the forecast should continue to show the silver sandals contributing 2% to the category sales (units sold).
Combining Forecasting Methods
Commonly, these forecasting methods are combined in particular ways that work for the majority of merchants:
Bottom-up and Year-round
Bottom-up forecasting is often the default method to make forecasts. Bottom-up forecasting can be good to use for non-seasonal products because even just a couple months’ worth of sales history can really inform your forecast.
Top-down and Seasonal Forecasting
Use top-down forecasting for seasonal items with a short sales history. You know that categories such as backpacks peak in August and September. If you introduce a particular backpack style in May, you wouldn’t know how many to forecast to have ready in August and September. However, if you sold a few in May and June and it is trending overall within the backpack category, then you can examine that category trendline. Sales will ramp up in August and September, so you need to have a lot more on hand. You know how that backpack will compare to the category overall because you know how it’s performing within the category.
Available sales history, seasonality, and importance of recent trends are important considerations when choosing a forecasting method. By applying the correct combination of forecasting approaches, you can have the right products in the right place at the right time.