System and method for linking qualified audiences with relevant media advertising through ip media zones
The system links Internet web page context with audience usage and location data to support advertising efficiency and effectiveness. An ontology of categories is created where domains and website pages are classified and scored against the links on those pages and the meta-tag key word pools that are harvested from those web pages. An ontology of high level categories are derived from the frequency of the key words appearing within the domain URL addresses of the pages, the domain of the links on those pages or within the content of the pages themselves. A method includes building a training set of web pages from a plurality of ad networks and sites where the system captures impressions in the form of real-time bids as well as click through events that include the IP address, the domain, the time of day and day of week, ad size and position, browser type, and bid amount whereby the training set is aggregated in a database whereby successful bids can be used in combination with audience and category attributes to model and score impression bids that combine the optimal mix of audience attributes, location, categorical affinity and bid price.
1 . A computer-implemented method using real-time impression data and real-time click through and conversion data, the method when executed by a computer and associated memory comprising:
capturing IP Address, site URL, time of day, day of week, browser type, creative ad size and position, and bid price from the real-time impression data and real-time click through and conversion data;
mapping the IP Addresses with a predetermined relationship to the plurality of site URLs to respective IP zones, wherein the IP Address, site URL, time of day, day of week, browser type, creative ad size and position, and bid price are appended with category and domain to each IP zone;
enhancing each of the plurality of IP zones with a series of normalized scores for the metadata indexed score values derived elements calculated by the computer from frequency distributions of domain and site URLs by zone and by category;
enhancing each of the plurality of IP zones by frequency of population by Zone and by Category for browser types, device type, IP Zone user type, high bid price, low bid price, average bid price, ad size and position, day of week and time of day, each having a predetermined relationship with the real-time impression data and real-time click through and conversion data as mapped to the IP Zone audience; and
each of the normalized scores, respectively, for each the IP Zone is obtained based on the formula
n
o
r
m
a
l
i
z
e
d
s
c
o
r
e
=
t
o
t
a
l
−
m
i
n
v
a
l
u
e
/
m
a
x
v
a
l
u
e
−
m
i
n
v
a
l
u
e
*
100
,
and
wherein each the IP Zone normalized score is aggregated based on the scale for each piece of metadata.
2 . The method of claim 1 , further comprising, linking internet web pages supporting advertising to an ontology of categories such that site pages and domains are classified against the categories.
3 . The method of claim 2 , wherein the ontology of high level categories are derived using frequency of the key words appearing within the domain URL addresses of the pages, the domain URLs of the links of the pages, or the meta-data tags within the content of the pages themselves.
4 . A computer-implemented system using real-time impression data and real-time click through and conversion data, the system comprising:
a computer processor and associated memory having program instructions stored thereon; the processor being configured to:
capture IP Address, site URL, time of day, day of week, browser type, creative ad size and position, and bid price from the real-time impression data and real-time click through and conversion data;
map the IP Addresses with a predetermined relationship to the plurality of site URLs to respective IP zones, wherein the IP Address, site URL, time of day, day of week, browser type, creative ad size and position, and bid price are appended with category and domain to each IP zone;
enhance each of the plurality of IP zones with a series of normalized scores for the metadata indexed score values derived elements calculated by the computer from frequency distributions of domain and site URLs by zone and by category, and
enhance each of the plurality of IP zones by frequency of population by Zone and by Category for browser types, device type, IP Zone user type, high bid price, low bid price, average bid price, ad size and position, day of week and time of day, each having a predetermined relationship with the real-time impression data and real-time click through and conversion data as mapped to the IP Zone audience; and
each of the normalized scores, respectively, for each the IP Zone being obtained based on the formula
n
o
r
m
a
l
i
z
e
d
s
c
o
r
e
=
t
o
t
a
l
−
m
i
n
v
a
l
u
e
/
m
a
x
v
a
l
u
e
−
m
i
n
v
a
l
u
e
*
100
,
and
wherein each of the IP Zone normalized scores is aggregated based on the scale for each piece of metadata.
5 . The system of claim 4 , wherein internet web pages supporting advertising to an ontology of categories are linked such that site pages and domains are classified against the categories.
6 . The system of claim 5 , wherein the ontology of high level categories are derived using frequency of the key words appearing within the domain URL addresses of the pages, the domain URLs of the links of the pages, or the meta-data tags within the content of the pages themselves.
7 . A non-transitory computer readable medium containing program instructions executable by a computer device, the program when executed for causing a computer to perform the method of:
capturing IP Address, site URL, time of day, day of week, browser type, creative ad size and position, and bid price from the real-time impression data and real-time click through and conversion data;
mapping the IP Addresses with a predetermined relationship to the plurality of site URLs to respective IP zones, wherein the IP Address, site URL, time of day, day of week, browser type, creative ad size and position, and bid price are appended with category and domain to each IP zone;
enhancing each of the plurality of IP zones with a series of normalized scores for the metadata indexed score values derived elements calculated by the computer from frequency distributions of domain and site URLs by zone and by category;
enhancing each of the plurality of IP zones by frequency of population by Zone and by Category for browser types, device type, IP Zone user type, high bid price, low bid price, average bid price, ad size and position, day of week and time of day, each having a predetermined relationship with the real-time impression data and real-time click through and conversion data as mapped to the IP Zone audience; and
each of the normalized scores, respectively, for each the IP Zone is obtained based on the formula
n
o
r
m
a
l
i
z
e
d
s
c
o
r
e
=
t
o
t
a
l
−
m
i
n
v
a
l
u
e
/
m
a
x
v
a
l
u
e
−
m
i
n
v
a
l
u
e
*
100
,
and
wherein each the IP Zone normalized score is aggregated based on the scale for each piece of metadata.
8 . The non-transitory computer readable memory of claim 7 , further comprising,
linking internet web pages supporting advertising to an ontology of categories such that site pages and domains are classified against the categories.
9 . The non-transitory computer readable memory of claim 8 , wherein the ontology of high level categories are derived using frequency of the key words appearing within the domain URL addresses of the pages, the domain URLs of the links of the pages, or the meta-data tags within the content of the pages themselves.