Content position recommendations
View Patent ↗A user data-driven method and system for generating position recommendations for content links on a web page is disclosed. The method and system collect user activity data associated with a set of content links positioned in one or more content position boxes of the multiple content position boxes of a web page during an activity window. An engagement measurement associated with a particular content link of the set of content links during the activity window is determined. A performance delta for a particular content link based on the calculated engagement measurement associated with the particular content link is determined. Multiple predicted user engagement measurements associated with moving the particular content link to a plurality of updated positions is determined. The method and system generate content position recommendations associated with the particular content link based on a comparison of the multiple predicted user engagement measurements.
1. A method comprising:
collecting, during a first activity window, user activity data associated with a set of content links positioned in one or more content position boxes of a plurality of content position boxes of a first web page;
calculating based on the user activity data collected during the first activity window, a first engagement measurement associated with a first instance of a particular content link of the set of content links;
determining a first Y-position value associated with the first instance of the particular content link on the first web page, wherein a second instance of the particular content link appears with the first instance on the first web page, and wherein the second instance has a second Y-position value;
calculating a positional benchmark engagement measurement associated with each of the plurality of content position boxes of the first web page;
determining a performance delta for the first instance of the particular content link based on the first engagement measurement associated with the first instance of the particular content link at a first content position box and a positional benchmark engagement measurement associated with the first content position box of the first web page;
determining a plurality of predicted user engagement measurements associated with placing the particular content link at each of the plurality of content position boxes of the web page, wherein a first predicted user engagement measurement is determined based on the performance delta for the particular content link, the first Y-position value associated with the particular content link, and the positional benchmark engagement measurement associated with the first content position box of the web page;
generating, by a processing device, a first content position recommendation associated with the particular content link based on a comparison of the plurality of predicted user engagement measurements; and
generating a second position recommendation associated with the particular content link based on user activity data collected during a second activity window.
2. The method of claim 1 , further comprising capturing a layout of the first web page.
3. The method of claim 2 , further comprising:
identifying a plurality of content zones and the plurality of content position boxes based on the layout of the first web page.
4. The method of claim 3 , further comprising:
assigning the set of content links to one or more of the plurality of content position boxes; and
generating a mapping identifying a positioning of the set of content links to the one or more of the plurality of content position boxes.
5. The method of claim 1 , wherein the first activity window comprises at least thirty days.
6. A system comprising:
a memory to store instructions; and
a processing device operatively coupled to the memory, the processing device to execute the instructions to:
collect, during a first activity window, user activity data associated with a set of content links positioned in one or more content position boxes of a plurality of content position boxes of a first web page;
calculate, based on the user activity data collected during the first activity window, a first engagement measurement associated with a first instance of a particular content link of the set of content links;
determine a first Y-position value associated with the first instance of the particular content link on the first web page, wherein a second instance of the particular content link appears with the first instance on the first web page, and wherein the second instance has a second Y-position value;
calculate a positional benchmark engagement measurement associated with each of the plurality of content position boxes of the first web page;
determine a performance delta for the first instance of the particular content link based on the first engagement measurement associated with the first instance of the particular content link at a first content position box and a positional benchmark engagement measurement associated with the first content position box of the first web page;
determine a plurality of predicted user engagement measurements associated with placing the particular content link at each of the plurality of content position boxes of the web page, wherein a first predicted user engagement measurement is determined based on the performance delta for the particular content link, the first Y-position value associated with the particular content link, and the positional benchmark engagement measurement associated with the first content position box of the first web page;
generate a first content position recommendation associated with the particular content link based on a comparison of the plurality of predicted user engagement measurements; and
generate a second position recommendation associated with the particular content link based on user activity data collected during a second activity window.
7. The system of claim 6 , wherein the processing device is further configured to capture a layout of the first web page.
8. The system of claim 7 , wherein the processing device is further configured to identify a plurality of content zones and the plurality of content position boxes based on the layout of the first web page.
9. The system of claim 8 , wherein the processing device is further configured to:
assign the set of content links to one or more of the plurality of content position boxes, and
generate a mapping identifying a positioning of the set of content links to the one or more of the plurality of content position boxes.
10. A non-transitory computer readable storage medium comprising instructions thereon that, in response to execution by a processing device, cause the processing device to:
collect, during a first activity window, user activity data associated with a set of content links positioned in one or more content position boxes of a plurality of content position boxes of a first web page;
calculate, based on the user activity data collected during the first activity window, a first engagement measurement associated with a first instance of a particular content link of the set of content links;
determine a first Y-position value associated with the first instance of the particular content link on the first web page, wherein a second instance of the particular content link appears with the first instance on the first web page, and wherein the second instance has a second Y-position value;
calculate a positional benchmark engagement measurement associated with each of the plurality of content position boxes of the first web page;
determine a performance delta for the first instance of the particular content link based on the first engagement measurement associated with the first instance of the particular content link at a first content position box and a positional benchmark engagement measurement associated with the first content position box of the first web page;
determine a plurality of predicted user engagement measurements associated with placing the particular content link at each of the plurality of content position boxes of the web page, wherein a first predicted user engagement measurement is determined based on the performance delta for the particular content link, the first Y-position value associated with the particular content link, and the positional benchmark engagement measurement associated with the first content position box of the first web page;
generate a first content position recommendation associated with the particular content link based on a comparison of the plurality of predicted user engagement measurements; and
generate a second position recommendation associated with the particular content link based on user activity data collected during a second activity window.
11. The non-transitory computer readable storage medium of claim 10 , the processing device to capture a layout of the first web page.
12. The non-transitory computer readable storage medium of claim 11 , the processing device to:
identify a plurality of content zones and the plurality of content position boxes based on the layout of the first web page.
13. The non-transitory computer readable storage medium of claim 12 , the processing device to:
assign the set of content links to one or more of the plurality of content position boxes; and
generate a mapping identifying a positioning of the set of content links to the one or more of the plurality of content position boxes.