ADVERTISING RECOMMENDATIONS USING PERFORMANCE METRICS
This disclosure relates to systems and methods for generating an advertising recommendation. In one example, a method includes determining a statistical performance level threshold for a plurality of advertising entities advertising, identifying one of the advertising entities that fails to meet the statistical performance level threshold, determining a variance associated with the one advertising entity as compared with others of the plurality of advertising entities that do satisfy the performance threshold constraint, generating a recommendation to the one advertising entity that addresses the variance, and transmitting the recommendation to the one advertising entity.
1 . A system comprising:
a machine-readable medium having instructions stored thereon, which, when executed by a processor, performs operations comprising:
determining a statistical performance level threshold for a plurality of advertising entities advertising via an online social networking service, the performance level threshold based on results of advertisements from the advertising entities and disseminated using the online social networking service;
identifying one of the advertising entities that fails to meet the statistical performance level threshold;
determining a variance associated with the one advertising entity as compared with others of the plurality of advertising entities that do satisfy the performance threshold constraint;
generating a recommendation to the one advertising entity that addresses the variance; and
transmitting the recommendation to the one advertising entity.
2 . The system of claim 1 , wherein the operations further comprise providing a user interface to a user of the system that allows the user to perform at least one of viewing the statistical performance level threshold, viewing the variance, viewing the recommendation, applying the recommendation, and changing an advertising parameter.
3 . The system of claim 1 , wherein the plurality of advertising agencies are selected according to one of an industry, a similar budget size, a similar size, and a similar target audience.
4 . The system of claim 1 , wherein the recommendation includes the statistical performance level threshold and the variance.
5 . The system of claim 1 , wherein the operations further comprise generating more than one recommendation and scoring the recommendations based on an estimated level of effectiveness.
6 . The system of claim 1 , wherein the recommendation comprises at least one of a bid amount, a budget, use of a specific term, phrasing, and a property of an image.
7 . The system of claim 1 , wherein the operations further comprise automatically generating the recommendation in response to an entity's performance falling below the statistical performance level threshold.
8 . A method comprising:
determining a statistical performance level threshold for a plurality of advertising entities advertising via an online social networking service, the performance level threshold based on results of advertisements from the advertising entities and disseminated using the online social networking service;
identifying one of the advertising entities that fails to meet the statistical performance level threshold;
determining a variance associated with the one advertising entity as compared with others of the plurality of advertising entities that do satisfy the performance threshold constraint;
generating a recommendation to the one advertising entity that addresses the variance; and
transmitting the recommendation to the one advertising entity.
9 . The method of claim 8 , further comprising providing a user interface that allows the user to perform at least one of viewing the statistical performance level threshold, viewing the variance, viewing the recommendation, applying the recommendation, and changing an advertising parameter.
10 . The method of claim 8 , wherein the plurality of advertising agencies are selected according to one of an industry, a similar budget size, a similar size, and a similar target audience.
11 . The method of claim 8 , wherein the recommendation includes the statistical performance level threshold and the variance.
12 . The method of claim 8 , further comprising generating more than one recommendation and scoring the recommendations based on an estimated level of effectiveness, the transmitting comprises transmitting the recommendation with the highest estimated level of effectiveness.
13 . The method of claim 8 , wherein the recommendation comprises at least one of a bid amount, a budget, use of a specific term, phrasing, and a property of an image.
14 . The method of claim 8 , further comprising automatically generating the recommendation in response to an entity's performance falling below the statistical performance level threshold.
15 . A non-transitory machine-readable medium having instructions stored thereon, which, when executed by a processor, cause the processor to perform:
determining a statistical performance level threshold for a plurality of advertising entities advertising via an online social networking service, the performance level threshold based on results of advertisements from the advertising entities and disseminated using the online social networking service;
identifying one of the advertising entities that fails to meet the statistical performance level threshold;
determining a variance associated with the one advertising entity as compared with others of the plurality of advertising entities that do satisfy the performance threshold constraint;
generating a recommendation to the one advertising entity that addresses the variance; and
transmitting the recommendation to the one advertising entity.
16 . The non-transitory machine-readable medium of claim 15 , wherein the operations further cause the processor to provide a user interface to a user of the system that allows the user to perform at least one of viewing the statistical performance level threshold, viewing the variance, viewing the recommendation, applying the recommendation, and changing an advertising parameter.
17 . The non-transitory machine-readable medium of claim 15 , wherein the plurality of advertising agencies are selected according to one of an industry, a similar budget size, a similar size, and a similar target audience.
18 . The non-transitory machine-readable medium of claim 15 , wherein the recommendation includes the statistical performance level threshold and the variance.
19 . The non-transitory machine-readable medium of claim 15 , wherein the operations further cause the processor to generate more than one recommendation and score the recommendations based on an estimated level of effectiveness.
20 . The non-transitory machine-readable medium of claim 15 , wherein the operations further cause the processor to automatically generate the recommendation in response to an entity's performance falling below the statistical performance level threshold.