Copying bestsellers is survivorship bias
Browsing what sells shows you the winners only. The near-identical products that failed are invisible, which makes any pattern you spot from that view unreliable.
Three platforms, three answers, one budget to defend. Your GA4 export already holds the answer, and the first finding is free and never leaves your browser. Get your first finding free
By Joris van Huët, Founder & CEOUpdated 2 min read
You are looking at a filtered list and drawing conclusions as though it were the whole population. That is the error, and it has a name.
The shape of it
You browse bestsellers. You notice a pattern. You conclude the pattern causes sales.
Missing from the view: every product sharing that pattern which did not sell. If there were a hundred of those, the pattern is not a success factor, it is just a common thing to try.
Why this specific version is so persistent
The advice to study what sells is good advice, right up to the point where it becomes a theory of causation. Studying winners is a fine way to generate hypotheses. It is a poor way to test them, and the step between the two is usually skipped entirely.
What the filtered view cannot show you
| You can see | You cannot see |
|---|---|
| Which products sold well | How many similar ones did not |
| What winners have in common | Whether losers had it too |
| The current top of the list | What the traffic behind it was |
| That a category is busy | Whether it is busy because it works |
Row two is the whole argument. A feature shared by every winner and also by every loser explains nothing.
The correction
Look at the losers. On most platforms you can see products with few or no reviews in the same category, and that is your comparison group. If the pattern you spotted is equally present there, you have learned something genuinely useful and saved yourself a launch.
That comparison is crude and it is still enormously better than reading the winners alone.
Then test rather than infer
Once a hypothesis survives the loser check, isolate it. Vary one element across a batch and read the interval.
Causality Engine uses causal inference on the GA4 history you already have to estimate what each channel caused. 99 euro once, refundable within 30 days, no questions asked.
Related answers
Frequently asked questions
What is survivorship bias in product research?
Drawing conclusions from a list of winners while the failures that shared the same features are invisible. A pattern common to every winner and also to every loser explains nothing.Is studying bestsellers useless then?
No. It is a good way to generate hypotheses and a poor way to test them. The error is skipping the step between the two.How do I check for survivorship bias cheaply?
Look at products in the same category with few or no reviews. If the pattern you spotted is equally present there, it is not a success factor, and you have saved yourself a launch.
Go deeper: Causal attribution, explained.
Sixty-second versions of these ideas: Causality Engine on YouTube Shorts.
Have an audience of ecommerce operators? Earn 20% recurring commission by recommending the €99 read.
Keep reading
Terms in this article
- AttributionAttribution identifies user actions that contribute to a desired outcome and assigns value to each. It reveals which marketing touchpoints drive conversions.
- Causal InferenceCausal inference is the set of methods for estimating how much an outcome changes because of a cause, rather than alongside it. It works by comparing what happened with an estimate of what would have happened without the cause.
- CausalityCausality is the relationship where one event directly causes another, essential for identifying specific actions that drive desired outcomes in marketing.
- CausationCausation is the relationship where a change in one variable directly causes a change in another.
- Product PageProduct Page is a webpage dedicated to a single product. It includes images, descriptions, pricing, and purchase options.