On the y-axis are the most important characteristics to determine whether a keyword belongs to the transactional category.
On the x-axis, you can see the impact of each feature on the model output, from negative to positive. The vertical line separates the negative impact from the positive one.
Each dot corresponds to a keyword. The color of the dot corresponds to the value of the corresponding feature for this keyword. Red indicates a high value, blue a low value.
Transactional Intent
The graph in the previous paragraph algeria whatsapp showed which characteristics determine whether the search intent is transactional. Let's examine this graph and take the competition on AdWords (competition_adwords) as an example.
In the graph, next to competition_adowrds, you can see red dots to the right of the vertical line. This means that high competition on AdWords (a red dot) makes a transactional keyword (to the right of the vertical line) more likely.
On the other hand, look for a [featured snippet page feature dsnippet . If this value is high (red dot) it means that there is a featured snippet in the SERP. The red dots are all to the left of the vertical line. This means that it is less likely to be a transactional keyword when there is a featured snippet.
Another thing you may notice in the graph is that the presence of Amazon one or more times ( urlscountamazon .) makes the SERP more likely to be transactional, while the opposite is true for Wikipedia.