The SERP can display multiple intents

[phonenumberlist]

We have attempted to outline AccuRanker's definitions with examples . Using these definitions and evaluating the machine learning model against these labels, we can achieve over 90% agreement with hand-labeled data. Additionally, we are often more likely to agree with the machine learning model than the human label when examining the differences.

AccuRanker’s new search intent model argentina whatsapp uses over a hundred SERP features to understand search intent. These features are interdependent, so it’s not easy to explain in detail how they work. If that were the case, we might as well use a rules-based approach.

Features include special words (translated into multiple languages) in keywords, titles, URLs, and descriptions, as well as SERP features and other SERP metadata such as cost per click and AdWords competition.

One way to understand the new search intent model is to look at SHAP visualizations of how features affect the model's outcome in different cases.

Viewing the characteristics that determine search intent
The following image shows the top twenty characteristics that determine whether the intent is transactional.


transactional intent chart
Here you can see inside the new search intent model and how decisions are made. It's all shown in a slightly simplified way.