Systems and methods for analyzing data element distribution across a network

A computer readable storage medium having instructions that, when executed by a processing device, cause the processing device to perform operations comprising:

• selecting, by the processing device, a population of persons;
• determining conversion metrics of a product or service from the population of persons over a time period;
• determining a media impression concentration that the population has received from a media data element for the product or service over the time period, wherein the media impression concentration is based on a number of impressions delivered to the population;
• determining, by the processing device, an effect that the media impression concentration of the media data element for the product or service has on the conversion metrics;
• calculating a plurality of values for a degree of targetedness for the media data element to the population of persons, wherein the degree of targetedness comprises a similarity function that measures how close the targeted population of persons is to a predetermined target;
• determining, by the processing device, an effect that the degree of targetedness for the media data element has on the conversion metrics;
• generating, by the processing device, a multi-dimensional model that measures the combined effects of the media impression concentration and the degree of targetedness on the conversion metrics;
• combining conversion estimates generated based on the multi-dimensional model with inventory quantity availability data for the product or service;
• and
• predicting future inventory quantities for the product or service based on a planned application of media impression concentration and a particular degree of targetedness to a population in a given time period.

A computing device comprising:

• a memory to store instructions for generating a multi-dimensional model of media data element effectiveness;
• and
• a processing device coupled to the memory, to execute the instructions, wherein the processing device is configured to:
• select a population of persons;
• determine conversion metrics of a product or service from the population of persons over a time period, wherein the conversion metrics comprise at least one of conversions per capita, probability of conversion during the time period, or conversions per day;
• determine a media impression concentration that the population has received from a media data element for the product or service over the time period, wherein the media impression concentration is based on a number of impressions delivered to the population;
• determine an effect that the media impression concentration of the media data element for the product or service has on the conversion metrics;
• calculate a plurality of values for a degree of targetedness for the media data element to the population of persons, wherein the degree of targetedness comprises a similarity function that measures how close the targeted population of persons is to a predetermined target;
• determine an effect that the degree of targetedness for the media data element has on the conversion metrics;
• generate a multi-dimensional model that measures the combined effects of the media impression concentration and the degree of targetedness on the conversion metrics;
• combining conversion estimates generated based on the multi-dimensional model with inventory quantity availability data for the product or service;
• and
• predicting future inventory quantities for the product or service based on a planned application of media impression concentration and a particular degree of targetedness to a population in a given time period.