Sales are up since summer. Are you growing, or is this just the time of year?

Many shops sell more in some months than others. If you only compare this month to last month, the season fools you. A real trend is what is left once the season is taken out.

Our position: never call it growth until you have compared like with like, the same season in the year before, or the season taken out by method.

The answer first

Sales are growing if the trend stays up after the repeating season is removed, and the rise is bigger than normal wobble. The check gives a direction and a range.

How the check works

  1. Find the season. Look for a pattern that repeats: a busy week each month, a busy month each year. The seasonality tool finds it.
  2. Take it out. Subtract the repeating pattern from your sales. What is left is the trend plus noise.
  3. Test the trend. Ask whether what is left moves up or down by more than chance explains. The trend test tool does this.

How much history you need

To see a yearly season, you need at least two years of data, so the pattern shows up twice. With less, you can still see weekly or monthly patterns, but the tool will say it cannot judge a yearly season. That is the honest answer.

What can fool you

  • One big event. A single huge day can tilt a trend. Check if the trend holds without it.
  • A change in what you sell. New products or new prices change the level. Note the dates.
  • Price and promotions. Sales driven by discounts are not the same as growth. See Did my sale work?

Run this on your GA4 or Shopify data

From Shopify: open Analytics, then Reports, then Sales over time. Set the dates to cover at least a few weeks before the change. Choose daily. Export as CSV.

From GA4: open Explore and make a table with date as the rows and purchase revenue (or sessions, or whatever you are judging) as the value. Export it as CSV.

What your file needs: one row per day, one column for the date, one column for the number. Add a column for the thing that changed if you have one, such as the day the sale began.

What you get back: the repeating pattern in your sales, the trend with the season removed, and a range that says how sure the direction is. Use the free seasonality tool and the trend test tool. If sales then drop and you want to know if it is real, see Is this drop in sales normal?

Questions owners ask

Can I check this with less than a year of data?

You can find weekly and monthly patterns. A yearly season needs about two years, and the tool will say so if you have less.

Is comparing to the same month last year enough?

It is a good quick check. It uses one month only, so it is noisy. Taking the season out of the whole series uses more of your data.

What if the trend is flat?

Then sales are steady once the season is removed. That is useful to know before you plan stock or spend.

Does this work for traffic and not just sales?

Yes. Any daily or weekly number works, such as visits, orders or sign-ups.