What does a regional demand forecast look like by state?
The short answer
Next quarter's regional demand forecast starts with the same quarter last year, by state and category. Adjust each state's units for its recent sales trend and its change in active customers, then add known events such as new stores or promotions. State the assumptions beside the numbers so planners can challenge them.
Why it matters
A single national forecast hides states moving in opposite directions, so stock lands where demand is cooling and runs short where it is growing. A state-level view lets you allocate inventory, staff and marketing budget to match demand ahead of the quarter.
The question to ask
Copy this into Lexi as written.
What the answer looks like
Illustrative output on sample data
Illustrative example: how Lexi answers this for an outdoor retailer forecasting insulated jacket units next quarter. It applies each state's year-on-year trend to last year's units and checks the active customers behind it.
- Colorado: 9,200 units, up 6%, plus 600 from a new store. Forecast about 10,350.
- Arizona: 4,100 units, down 8%. Forecast about 3,770.
- Washington: 7,400 units, up 2%. Forecast about 7,550.
What the data shows
Total demand is up about 5%, with Colorado up about 1,150 units and Arizona down about 330.
What it means
Arizona's active customers are down 5% and new customers are falling fastest, so the decline is likely to continue. Washington's growth comes from existing customers buying more, which can fade quickly.
What to do
Plan Arizona at the forecast or lower, and keep a reserve for Washington.
Trends assume a normal winter. Would you like the forecast split by store?
Frequently asked questions
How granular should regional demand forecasting in retail be?
Forecast at the level you make decisions. If stock is allocated by state and category, forecast there. Going finer, such as by store and SKU, adds noise unless each cell has enough sales to show a pattern. Roll small states or slow categories together and split them out once volumes grow.
Why do state forecasts built on last year's sales go wrong?
Last year's sales record what you sold, which reflects last year's stock, promotions and store count as much as demand. If a state ran out of key sizes or had a one-off event, those effects carry forward. Correct last year for stock-outs and events before applying any trend.
How do you forecast demand for a new product by region?
Borrow from a similar product. Find a past launch with a comparable price, category and customer, then use its first-quarter sales by state as the starting curve. Scale it by how many likely buyers live in each state, using customers who bought the comparable product.