Discount lift calculator
Every tool that hands out a code reports the orders that used it. This works out how many of those orders needed the code, using a holdout group as the comparison. Nothing is sent anywhere and no email is asked for.
How much of that revenue did the discount cause?
Fill in what you have. If you do not run a holdout yet, the second box is the one to start with: without it there is no comparison and the honest answer is that you cannot know.
Drag any control to see how the answer moves. Amounts come out in whatever currency you put in. Nothing is sent anywhere; the numbers stay in your browser.
What the numbers mean
The held-back group gives you the conversion rate you would have had without any offer. Applying that rate to the shoppers who did see the offer tells you how many of their orders were going to happen anyway. Everything above that line is what the discount caused.
The part most dashboards never show is the second half: the discount is paid on every order that used the code, including the ones that did not need it. That is why the net can be negative while the attributed revenue looks healthy.
What to do with a negative result
It is not a reason to stop discounting, it is a reason to narrow the offer: later in the session, to fewer shoppers, or at a smaller percentage. Then measure again. The method is in the guide on how to know if a discount code actually increased sales.
Where the holdout comes from
Running one by hand means splitting your own traffic and keeping the two groups comparable, which is doable on a store with enough volume. Clinch does it automatically on every store, which is why this calculator exists, but the arithmetic above is the same whoever collects the numbers.
Common questions
What numbers do I need to use this?
Four: how many shoppers saw the offer and how many of them ordered, and the same two for a group that was held back and never saw it. Without the second pair there is nothing to compare against and no lift can be calculated.
What is a holdout group?
A random slice of the shoppers who would normally qualify for the offer, who are deliberately not shown it. Their conversion rate is what you would have got with no offer at all, which is the number you otherwise have to guess.
Why is the net sometimes negative?
Because the discount is paid on every order that used the code, including the ones that were happening anyway, while the revenue it adds comes only from the orders it caused. When most redeemers had already decided, the margin given away is larger than the revenue gained.
How much data do I need before the result means anything?
As a floor, a few hundred shoppers in the smaller group and at least five orders in the holdout. Below that a single order moves the answer more than the effect being measured, and the calculator says so rather than showing a confident number.
Try it on your own store
Clinch is free to install. The Free plan costs $0 per month and takes 10% of revenue it actually recovers, so if it recovers nothing you pay nothing.
Install on Shopify