How to Choose the Best Retail Demand Planning Strategy for Your Business With SkuBrain: Bottom Up vs. Top Down Forecasting

Izze’s Amp Warehouse

Several years ago, I started a small retail business providing guitar amplifiers and effects pedals to musicians. Izze’s Amp Warehouse starred my English Bulldog who bullied suppliers for the best prices. After some initial success, we established a demand plan to support our e-commerce site and three locations in California. We forecasted our sales at a company level then allocated targets to each location. Can you guess what happened?

Our sales forecast was actually pretty decent, statistically speaking. But, we ran into problems with stock levels. The fact was, our model predicted total future sales for Amp Warehouse – but did nothing to account for current stock levels or store lead times. I will finish this chapter of the story by noting that by the time we should have started on a different demand planning approach, Amazon caused us to rethink our commitment to the business.

But, for me it’s a good place to kick-off a discussion about how to choose a demand planning approach. In fact, you have two basic options:

  • 1. Top Down

  • 2. Bottom Up

Most experts consider the Bottom Up approach to be best today – but, the vast majority of retailers still practice Top Down forecasting. Why? Let’s consider the options.

Top Down Forecasting

The basic idea of Top Down Forecasting is to generate a total sales volume forecast over a time horizon for the business – then “disaggregate” the volume by sharing it out to each store. The top down approach is OK when you have little or no sales history and you want your corporate headquarters to control the prediction of your growth.

Assuming you have some experience with sales at each location, you can also make some good estimates about the percentage to allocate to each store. So, its not a bad approach for an executive strategic plan. But, Top Down, doesn’t deal with stock levels or lead times. Thus, you can forecast sales but its much harder to optimize inventory at a local level. That was the core problem at Izze’s Amp Warehouse.

Top Down forecasting is more in-grained in business processes and there is a traditional approach to applying it. Basically, local stores take the “target” number and then apply “Min/Max” rules that indicate when to reduce inventory and when to re-order. The problem with these approaches is they tend to be reactive. Introducing new products, dealing with seasonality and local demographic preferences across store trade areas make it hard to optimize inventory.

Bottom Up

The bottom up approach creates a forecast at the lowest product level (e.g., SKU or prduct), then “rolls” that estimate along with every other product to the next level in the product hierarchy. Thus, you are assured that your top level forecast will align with your results. Bottom up forecasting gathers individual forecasts from each store and applies those predictions to drive replenishment choices.

As such, bottom up has more tactical value. It can be used to understand and improve customer profitability, to improve customer satisfaction at the store level, and to do so while minimizing local inventory.

By managing inventory at store level, you are gaining a level of granularity that will help you optimize your working capital and ensure you meet your desired service levels. More specifically, you will be better prepared with address varying sales patterns, such as caused by seasonality in demand or promotional activities. A quick increase in sales can lead to “stock outs” while a sudden drop will may mean you are over-stocked. And both situations will reduce the profitability of the business.

Once you’ve implemented a bottom up approach, you will no longer need to forecast at the distribution center level – its simply the summation of your retail locations. And, the challenges of breaking down a Top Down, corporate forecast to be used by your production team for capacity planning is reduced. Both sales and production are now looking at product level unit forecasts.

To Summarize

SkuBrain allows both top down and bottom up forecasts. We recommend:

  • A top down forecast for new businesses or where you lack at least 2 years of sales history
  • A bottom up approach when you are focused on reducing inventory and working capital – and have a few years of data to work from.

SkuBrain is free to use for 7 days. Sign up here and start forecasting!


Keith Peterson

Keith Peterson is the President and CEO of Halo. Keith assists clients in developing business strategies that are enhanced through data, analytics, and technology.
Follow Keith on Twitter for the latest on Supply Chain Analytics and Business Intelligence at @KPeteHalo