Machine for audience propensity ranking using internet of things (IoT) inputs
A specially programmed machine and method generates propensity information based on inputs received from machines connected as part of an Internet of Things (IoT) environment, where the machine appends a predictive segmentation attribute to each data input received and generates a matrix based on the counts of each attribute-input combination. The attribute-input counts for each combination are converted to a statistical metric that represents propensity information for consumers fitting into the segment associated with the particular attribute. The propensity information can be relayed to a client in a variety of ways, including a direct display of the propensity information, appendage of the propensity information to the clients database, or using the information to provide an audience report to the client.
1. A specially programmed machine useful for generating propensity information, the machine being in communication with a plurality of devices across a network, the machine comprising:
a. a data layer configured to execute instructions that when executed cause the machine to:
i. receive from the plurality of devices a plurality of input messages comprising a plurality of consumer input data points;
ii. read from the plurality of input messages the consumer input data points; and
iii. append to each of the consumer input data points one of a number of predictive segmentation attributes thereby creating a plurality of different combinations of consumer-attribute pairs;
b. a platform layer configured to execute instructions that when executed cause the machine to:
i. generate a summary matrix, wherein generating the summary matrix comprises counting an amount of each consumer-attribute pair combination;
ii. convert each of the counts of consumer-attribute pair combinations to a statistical metric relaying propensity information; and
iii. construct an insight graph displaying the propensity information;
c. a client layer configured to execute instructions that when executed cause the machine to perform one or more of the following result relaying tasks:
i. transmit the insight graph;
ii. append the propensity information to data housed at a client database; and
iii. match the propensity information to a matching universe to generate an audience report, wherein the matching universe comprises audience data pertaining to consumers associated with the plurality of devices.
2. The machine of claim 1 , wherein the at least one result relaying task of the client layer is configured to be sent to a client machine in communication with the machine across the network.
3. The machine of claim 1 , wherein the plurality of consumer input data points comprises one or more of identifier data points, geographic data points, digital data points, virtual reality data points, social data points, time data points, camera data points, health data points, transactional data points, television data points, and demand data points.
4. The machine of claim 1 , wherein the number of predictive segmentation attributes comprises a plurality of consumer categories based on demographic information.
5. The machine of claim 1 , wherein each statistical metric is an index value.
6. The machine of claim 1 , wherein each statistical metric is a delta value.
7. A system useful for generating consumer propensity information, the system comprising:
a. a plurality of consumer machines connected to a network, each of the plurality of consumer machines configured to derive consumer data points associated with a plurality of consumers;
b. a predictive segmentation machine in communication with the plurality of consumer machines over the network, the predictive segmentation machine comprising:
i. a data layer executing instructions that cause the machine to:
A. receive a plurality of input messages comprising at least a portion of the consumer data points derived by the plurality of consumer machines;
B. read from the plurality of input messages the consumer input data points; and
C. append to each of the consumer input data points one of a number of predictive segmentation attributes thereby creating a plurality of different combinations of consumer-attribute pairs;
ii. a platform layer executing instructions that cause the machine to:
A. generate a summary matrix, wherein generating the summary matrix comprises counting an amount of each consumer-attribute pair combination;
B. convert each of the counts of consumer-attribute pair combinations to a statistical metric relaying propensity information;
C. construct an insight graph displaying the propensity information; and
iii. a client layer configured executing instructions that cause the machine to perform at least one of the following result relaying tasks:
A. transmit the insight graph to a user interface at a client machine for displaying the insight graph at a client location;
B. append the propensity information to data housed at a client database; and
C. match the propensity information to a matching universe to generate an audience report, wherein the matching universe comprises audience data pertaining to consumers associated with the plurality of devices.
8. The system of claim 7 , wherein the plurality of consumer data points comprises at least one of identifier data points, geographic data points, digital data points, virtual reality data points, social data points, time data points, camera data points, health data points, transactional data points, television data points, and demand data points.
9. The system of claim 7 , wherein the number of predictive segmentation attributes comprises a plurality of consumer categories based on demographic information.
10. The system of claim 7 , wherein each statistical metric is an index value.
11. The system of claim 7 , wherein each statistical metric is a delta value.
12. A method useful for generating propensity information, the method comprising the steps of:
a. receiving at a predictive segmentation machine a plurality of input messages from a plurality of consumer devices in communication with the predictive segmentation machine across a network, each of the plurality of consumer devices configured to derive consumer data associated with a number of consumers, and the plurality of input messages comprising at least a portion of the consumer data points derived by the plurality of consumer devices;
b. reading from the plurality of input messages the consumer data points received from the consumer devices;
c. appending to each of the consumer input data points one of a number of predictive segmentation attributes thereby creating a plurality of consumer-attribute pair combinations;
d. counting a total number of consumer-attribute pair combinations;
e. converting the total number of consumer-attribute pair combinations into a statistical metric, wherein each statistical metric is an index value relaying propensity information;
f. and constructing an insight graph displaying the propensity information.
13. The method of claim 12 , further comprising the step of performing one or more of the following result relaying tasks:
a. transmitting the insight graph;
b. appending the propensity information to data housed at a client database; and
c. matching the propensity information to a matching universe to generate an audience report, wherein the matching universe comprises audience data pertaining to consumers associated with the plurality of devices.
14. The method of claim 13 , further wherein the step of performing one or more of the following result relaying tasks comprises outputting results to at least one client machine over the network.