Conversion Rate Calculator
A percentage is a start. The interval is the honest part.
Conversion Rate Calculator
Turn visitors and conversions into a rate, a confidence interval, and the cost of each result.
Optional
Optional
A conversion is any completed action you define: a purchase, a form, a booked call. Keep the definition identical between periods or the rate is not comparable.
Embed this calculator
Put this calculator on your own site with the snippet below. The frame contains the tool only, reports its own height, and carries a visible link back to the full page. Embedding is free; keep the attribution link as it is, and do not wrap the frame in a way that hides it.
Preparing the embed code for this page...
What This Calculator Does
The Conversion Rate Calculator turns a visitor count and a conversion count into the percentage of visitors who completed the action, the cost and revenue attached to each conversion, and a 95% confidence interval for the underlying rate. It is for the ordinary marketing question: is this page, campaign, or checkout actually improving, or does the difference disappear once the sample size is taken seriously?
How It Works
The rate is conversions divided by visitors, multiplied by 100. Optional spend and revenue are divided by the same counts to give cost per conversion, revenue per visitor, and revenue per conversion. The confidence interval uses the Wilson score method rather than the textbook normal approximation, because Wilson behaves sensibly when the rate is near 0% or 100% and when the sample is small. Conversions must be whole numbers and cannot exceed visitors, because this model counts one conversion per visitor.
Example
A landing page receives 2,500 visitors and records 75 purchases. The conversion rate is 75 / 2,500 x 100 = 3.0%. With only 75 conversions the 95% interval is roughly 2.4% to 3.7%, so a week at 3.4% is not yet proof of improvement. At a 3.0% rate, reaching 100 conversions needs ceil(100 / 0.03) = 3,334 visitors.
Formula
rate = conversions / visitors x 100visitors / conversionsspend / conversionstarget conversions / (rate / 100)Rounded up to a whole visitor.
(p + z2/2n +/- z sqrt(p(1-p)/n + z2/4n2)) / (1 + z2/n)p is the observed rate and n is the visitor count. A 95% interval uses z = 1.96.
Reading the Results
Conversion rate
The share of visitors who completed the action. It is only comparable across periods and channels when the action and the counting method stay the same.
95% confidence interval
The range of underlying rates that is compatible with the observed data. Two campaigns with overlapping intervals have not shown a real difference yet.
Cost per conversion
Spend divided by conversions, shown only when spend is entered. A cheap conversion that never becomes a customer is still expensive.
Sources and References
Wilson, E. B. (1927), Probable inference, the law of succession, and statistical inference
Score interval for a binomial proportion
The confidence interval method used here. It is more reliable than the normal approximation for small samples and extreme rates.
Google Analytics 4 Help - Key events
How conversions (key events) are defined and counted
A reminder that the definition of the conversion is a choice. Changing it changes every rate that follows.
References identify the method or data behind this calculator. Where a standard or tariff changes, the current edition applies, and the assumptions stated above take precedence over a remembered figure.
Frequently Asked Questions
Should visitors be sessions or unique users?
Either can work, but pick one and keep it. Sessions count repeat visits, so a returning visitor can create several chances to convert; unique users count each person once. Mixing the two across reports makes a change look like a trend.
Why is the confidence interval so wide?
Small samples carry more uncertainty. At 3 conversions from 100 visitors the interval is roughly 1.0% to 8.5%; at 300 from 10,000 it tightens to roughly 2.7% to 3.4%. The point estimate is the same 3% in both cases, but only the second is precise enough to act on.
Can a conversion rate exceed 100%?
Not in this model, where each visitor can convert at most once. If one visitor can generate several conversions, such as multiple purchases or multiple form submissions, track events per visitor separately rather than forcing them into a single rate.
Is a higher conversion rate always better?
No. A 20% rate for a newsletter signup can be worth less than a 1% rate for a high-value purchase. Pair the rate with revenue per visitor or cost per conversion before deciding which page is doing the better job.
How many visitors do I need before trusting the number?
There is no universal threshold. It depends on the baseline rate and the size of the change you want to detect. Use the interval as a guide: if it is wide enough to contain both "no change" and "a meaningful gain", keep collecting data or run a proper power calculation.