AI statistics
AI statistics give us an insight into how the AI performs and the parameters that influence the recommendations displayed. We can see various metrics, including the number of generated recommendations and the effectiveness of recommendations across different pages.
Recommendations performance
Total recommendations:
This metric indicates how many instances of recommendations have been generated. For instance, if a news article displays 3 recommendations at the bottom of the page, it counts as one recommendation. Therefore, there have been 29,350 instances where a single recommendation has been made, potentially with additional recommendations embedded within.
Users guided:
This metric represents the proportion, expressed as a percentage, of visitors who engaged with the displayed recommendations by clicking on them. In the example below, 17% of the viewers of the recommendations have engaged with them.
Avg. response time:
This metric, represented in milliseconds, signifies the duration of time taken for the recommendation to be processed on the server prior to being transmitted to the user.
Variation score:
This metric provides insight into the diversity of recommended pages that visitors have engaged with. A higher value indicates a wider array of recommendations, showcasing their appeal to a diverse audience. In this context, it's evident that 271 unique pages have been recommended, highlighting the breadth of content offered to users.
Top performing pages:
This list identifies the pages where recommendations yield the most favorable outcomes. These pages exemplify instances where users have derived the utmost benefit from the recommendations provided. In the list provided, we can see that "uppleva-och-gora" is the top-performing page with an 83% success rate.
Feature insights
In the "Feature Insights" tab, a diagram illustrates the external factors that influence the display of recommendations. Here, we can see that the most influential factors are "device type" and "referer website".
Browser language
If this parameter has the highest value, it indicates that the visitors of the website are looking for different content depending on the language settings of their browser.
Country
If this parameter has the highest value, it indicates that the visitors of the website are looking for different content depending on their geographical position (country).
Day in month
If "day in month" is the highest, it indicates that the visitors of the website are looking for different content depending on the day in month. For example, you might search for salary-related content around the 25th.
Day in week
If this parameter is the highest it indicates that the visitors search for different content during the different days in a week. During monday - friday, the visitors might be searching for information on how to report your child sick or the school's opening hours. While on the weekends, the visitors may be interested in exploring events, experiences and restaurants.
Device type
If the "device type" indicates the highest value, it implies significant variations in the demand for information on your website, depending on whether visitors are using a mobile phone or a desktop computer.
Distance
If "distance" has the highest value, it indicates that website visitors behave differently based on whether they are nearby or farther away. This could be applications for adult education, suggesting a desire to move there, but also experiences and activities, for example, a vacation. If one lives nearby, they might be more interested in what's happening in the municipality, power outages, etc.
Referer website
If "referer website" has the highest value, it indicates that the behavior of website visitors varies depending on the page they originate from. These visitors to not navigate through the homepage, instead they arrive directly on to the landing page through a direct link.
For instance, one visitor might arrive at the landing page about building permits through a link at aapplication page on another website. The second visitor might access the landing page through a link at a marketing site selling tickets for a specific event. Theese two visitors show two very different behavior. One read about building permits and the other one about an upcoming event but they both end up on at the same website, through a directlink at another website, only different landing pages.
Time of day
If this parameter is the highest, it indicates that the visitors of the website are looking for different content depending on the time of day.
Visiting site often
The browser remembers how often it visits the current website, and this figure is used as a parameter in recommendations.