Skip to main content

The short version

From a range of sources, we assemble a set of potential websites for each company. We call these candidates. We then scrape up to 25 pages of each candidate website. Finally, we apply a machine learning model to select the best candidate for each company. This model is trained on manually checked website matches for thousands of companies collected over the last decade. We measure the success of our model continuously. The two most important metrics are:
  • Precision: how often we pick the correct website, or no website (regardless of whether the company does actually have a website).
  • Accuracy: how often we pick the correct website, or no website if the company does not have one.
Precision tells us how likely a website match that you see in our product is to be correct. Accuracy is a broader measure. It considers that sometimes we won’t match small companies with basic websites to that website. In our latest releases our model regularly exceeds 97% precision, and 90% accuracy.

The long version

V6 of our industry engine represented our biggest ever step forward in website matching. We switched from a logical scoring method to a machine learning model trained on top of year’s worth of manually collected data. You can read about this in more detail in our blog post Industry Engine V6: What’s new?
Last modified on June 1, 2026