Network real estate analysis
View Patent ↗A method can be used to analyze the “real-estate” performance of content items within a network site. The method can comprise determining the click distance to reach each content item and determining the performance of each content item. The method can also comprise calculating a predicted value for performance based on statistical relationship between location and performance observed in a population of content items. The method can comprise comparing the predicted and actual performance. If a content item has an actual performance greater than its predicted performance, then it may be promoted to a better location in the site and the converse for poorer performing content.
1. A method for restructuring a site based on performance of content items, comprising:
at one or more server computers configured to provide a network site, storing a network activity log comprising network activity information;
at a second computer:
accessing the network activity log;
determining a network address of a content item within the network site;
determining a predicted performance for the content item at the network address;
determining an actual performance of the content item;
comparing the predicted performance to the actual performance; and
transform a structure of the network site, wherein transforming the structure of the network site comprises moving the content item to a new network address within the network site based on the comparing.
2. The method of claim 1 , wherein the network activity log is stored in a database.
3. The method of claim 1 , further comprising receiving at the one or more server computers a request from a client for one or more content items and recording a clickstream for the client in the network activity log.
4. The method of claim 1 , wherein the second computer is configured to access the network activity log.
5. The method of claim 1 , further comprising, at the second computer, executing one or more software code elements.
6. The method of claim 1 , wherein the second computer is one of the one or more server computers.
7. The method of claim 1 , wherein the second computer is a client computer.
8. The method according to claim 1 , wherein determining the predicted performance of the content item comprises analyzing a relationship between a location of the content item and performance of other content items.
9. The method of claim 8 , further comprising determining the location of the content item, wherein determining the location of the content item comprises determining an average number of clicks it takes users to arrive at the network address during a session at the network site.
10. The method of claim 8 , wherein determining the actual performance of the content item comprises summing a number of sessions in which the content item is requested.
11. The method of claim 1 , wherein the predicted performance of the content item is determined according to:
P
′
(
c
i
)
≈
∑
d
=
1
D
[
G
(
r
d
-
L
(
c
i
)
)
·
t
d
]
where:
c i represents the content item;
L(c i ) is a location of the content item;
D is a number of basis functions used for the approximation G(g)=g 2 *log(g);
r d is a prototypical location value for the d th basis function; and
t d is a parameter value that is chosen to minimize the sum of squared errors over a large “training set” of content items.
12. The method according to claim 11 , wherein comparing the actual performance to the predicted performance comprises determining a real estate performance value according to:
REP
(
c
i
)
=
P
(
c
i
)
P
′
(
c
i
)
13. The method according to claim 12 , wherein if the content item has a REP<1, the content item is determined to be underperforming.
14. A data processing system product comprising a non-transitory computer readable storage medium having computer readable program code embodied therein, the computer readable program code adapted to be executed by a computer to implement a method for analyzing performance of content items within a network site, the computer readable program code comprising instructions executable to:
determine a predicted performance for a content item at a network address;
determine an actual performance of the content item;
compare the predicted performance to the actual performance; and
recommend moving the content item to a new network address within the network site based on the comparison.
15. The data processing system product of claim 14 , wherein determining the predicted performance of the content item comprises analyzing a relationship between a location of the content item and performance of other content items.
16. The data processing system product of claim 15 , wherein the computer readable program code further comprises instructions executable to determine an average number of clicks it takes users to arrive at the network address during a session at the network site.
17. The data processing system product of claim 14 wherein determining the actual performance of the content item comprises summing a number of sessions in which the content item is requested.
18. The data processing system product of claim 14 , wherein the predicted performance of the content item is determined according to:
P
′
(
c
i
)
≈
∑
d
=
1
D
[
G
(
r
d
-
L
(
c
i
)
)
·
t
d
]
where:
c i represents the content item;
L(c i ) is a location of the content item;
D is a number of basis functions used for the approximation G(g)=g 2 *log(g);
r d is a prototypical location value for the d th basis function; and
t d is a parameter value that is chosen to minimize the sum of squared errors over a large “training set” of content items.
19. The data processing system product of claim 14 , wherein comparing the actual performance to the predicted performance comprises determining a real estate performance value according to:
REP
(
c
i
)
=
P
(
c
i
)
P
′
(
c
i
)
20. The data processing system product of claim 19 , wherein if the content item has a REP<1, the content item is determined to be underperforming.
21. A system for restructuring a network site, comprising:
a storage storing network activity information on the network site;
one or more servers configured to provide content associated with the network site to clients over a network and store a network activity log in the storage; and
a data processing system coupled to the storage comprising a processor and a computer readable storage medium storing computer executable instruction, the computer executable instructions comprising instructions executable to:
determine a predicted performance for a content item at a network address;
determine an actual performance of the content item;
compare the predicted performance to the actual performance; and
transform the network site by moving the content item to a new network address within the network site based on the comparison.
22. The system of claim 21 , wherein the data processing system is one of the one or more servers.
23. The system of claim 21 , wherein the data processing system is a client of the one or more servers and is coupled to the storage through the one or more servers.
24. The system of claim 21 , wherein determining the predicted performance of the content item comprises analyzing a relationship between a location of the content item and performance of other content items.
25. The system of claim 21 , wherein the predicted performance of the content item is determined according to:
P
′
(
c
i
)
≈
∑
d
=
1
D
[
G
(
r
d
-
L
(
c
i
)
)
·
t
d
]
where:
c i represents the content item;
L(c i ) is a location of the content item;
D is a number of basis functions used for the approximation G(g)=g 2 *log(g);
r d is a prototypical location value for the d th basis function; and
t d is a parameter value that is chosen to minimize the sum of squared errors over a large “training set” of content items.
26. The system of claim 25 , wherein comparing the actual performance to the predicted performance comprises determining a real estate performance value according to:
REP
(
c
i
)
=
P
(
c
i
)
P
′
(
c
i
)
27. The system of claim 26 , wherein if the content item has a REP<1, the content item is determined to be underperforming.
28. The method of claim 1 , further comprising:
determining that the content item is underperforming,
wherein the content item is moved to the new network address responsive to determining that the content item is underperforming.
29. The method of claim 1 , further comprising:
determining that the content item is over-performing,
wherein the content item is moved to the new network address responsive to determining that the content item is over-performing.
30. The data processing system product of claim 14 , wherein the computer readable program code further comprises instructions executable to:
determine if the content item is underperforming;
recommend moving the content item responsive to determining that the content item is underperforming.
31. The data processing system product of claim 14 , wherein the computer readable program code further comprises instructions executable to:
determine if the content item is over-performing;
recommend moving the content item responsive to determining that the content item is over-performing.
32. The system of claim 21 , wherein in the computer executable instructions further comprise instructions executable to determine that the content item is underperforming and wherein the content item is moved to the new network address responsive to determining that the content item is underperforming.
33. The system of claim 21 , wherein in the computer executable instructions further comprise instructions executable to determine that the content item is over-performing and wherein the content item is moved to the new network address responsive to determining that the content item is over-performing.