System and method using deep learning machine vision to conduct comparative campaign analyses

1. A computer-implemented method for using machine vision to categorize a locality to conduct lead mining analyses, the method comprising:

generating locality profile scores and economic categorizations for each locality of a plurality of localities, wherein the locality profile score includes percentage distributions of entity classes within the locality, the locality profile score for each locality being derived through neural network analyses of map images of the locality, the economic categorization being derived through neural network analyses of images of entities within the locality;

performing the neural network analysis via a convolutional neural network, the convolutional neural network consuming segmented pixel areas and distinguishing between areas containing at least one of text and icons from areas that do not contain at least one of text and icons;

grouping localities having similar locality profile scores;

extracting entities in a locality group;

retrieving historical data for the extracted entities in the locality group, wherein the historical data for the entities in the locality includes campaign vehicles hosted in the locality to promote sales of goods and/or services of an enterprise, leads generated by the campaign vehicles in the locality, and return on investment for the campaign vehicles in the locality;

generating a lead score for each entity in the locality group as a function of the locality profile score for the locality in which the entity is located, economic categorization of the locality in which the entity is located, and campaign vehicles used in the locality in which the entity is located, the lead score for an entity being further based on a number of employees of the entity and spending by the entity on products and/or services offered by the enterprise;

accessing a map image of a locality, wherein the map image includes geographical artefacts corresponding to entities within the locality;

analyzing the map image to detect the entities in the locality using the geographical artefacts;

assigning entity classes to detected entities in the locality, the assigning entity classes including assigning the detected entities on one of a first type and a second type, the neural network analysis being performed for each of the first type and the second type, respectively; and

assigning the locality profile score to the locality based on entity classes included in the locality; and,

generating a lead score for a green field entity using information obtained from a third-party resource.

2. The computer-implemented method of claim 1 , further comprising:

generating a lead quotient for the entity, wherein the lead quotient is a function of the historical return on investment of campaigns within the locality and the lead score.

3. The computer-implemented method of claim 2 , further comprising:

comparing the lead quotient with an n′ tile threshold value; and

setting a lead converted/not converted flag for the entity when the lead quotient does not reach the n′ tile threshold value.

4. The computer-implemented method of claim 1 , wherein grouping localities having similar locality profile scores comprises:

determining a statistical distance metric between locality profile scores of the plurality of localities; and

grouping localities having a statistical distance metric below a predetermined threshold.

5. A system comprising:

a processor;

a data bus coupled to the processor; and

a non-transitory, computer-readable storage medium embodying computer program code, the non-transitory, computer-readable storage medium being coupled to the data bus, the computer program code interacting with a plurality of computer operations and comprising instructions executable by the processor and configured for:

generating locality profile scores and economic categorizations for each locality of a plurality of localities, wherein the locality profile score includes percentage distributions of entity classes within the locality, the locality profile score for each locality being derived through neural network analyses of map images of the locality, the economic categorization being derived through neural network analyses of images of entities within the locality, the neural network analysis being performed via a convolutional neural network, the convolutional neural network consuming segmented pixel areas and distinguishing between areas containing at least one of text and icons from areas that do not contain at least one of text and icons;

performing the neural network analysis via a convolutional neural network, the convolutional neural network consuming segmented pixel areas and distinguishing between areas containing at least one of text and icons from areas that do not contain at least one of text and icons; grouping localities having similar locality profile scores;

extracting entities in a locality group;

retrieving historical data for the extracted entities in the locality group, wherein the historical data for the entities in the locality includes campaign vehicles hosted in the locality to promote sales of goods and/or services of an enterprise, leads generated by the campaign vehicles in the locality, and return on investment for the campaign vehicles in the locality;

generating a lead score for each entity in the locality group as a function of the locality profile score for the locality in which the entity is located, economic categorization of the locality in which the entity is located, and campaign vehicles used in the locality in which the entity is located, the lead score for an entity being further based on a number of employees of the entity and spending by the entity on products and/or services offered by the enterprise;

accessing a map image of a locality, wherein the map image includes geographical artefacts corresponding to entities within the locality;

analyzing the map image to detect the entities in the locality using the geographical artefacts;

assigning entity classes to detected entities in the locality, the assigning entity classes including assigning the detected entities on one of a first type and a second type, the neural network analysis being performed for each of the first type and the second type, respectively; and

assigning the locality profile score to the locality based on entity classes included in the locality; and,

generating a lead score for a green field entity using information obtained from a third-party resource.

6. The system of claim 5 , further comprising

generating a lead quotient for the entity, wherein the lead quotient is a function of the historical return on investment of campaigns within the locality and the lead score.

7. The system of claim 6 , further comprising:

comparing the lead quotient with an n′ tile threshold value; and

setting a lead converted/not converted flag for the entity when the lead quotient does not reach the n′ tile threshold value.

8. The system of claim 5 , wherein grouping localities having similar locality profile scores comprises:

determining a statistical distance metric between locality profile scores of the plurality of localities; and

grouping localities having a statistical distance metric below a predetermined threshold.

9. The system of claim 5 , further comprising:

accessing a map image of a locality, wherein the map image includes geographical artefacts corresponding to entities within the locality;

analyzing the map image to detect the entities in the locality using the geographical artefacts;

assigning entity classes to detected entities in the locality; and

assigning the locality profile score to the locality based on entity classes included in the locality.

10. A non-transitory, computer-readable storage medium embodying computer program code, the computer program code comprising computer executable instructions configured for:

generating locality profile scores and economic categorizations for each locality of a plurality of localities, wherein the locality profile score includes percentage distributions of entity classes within the locality, the locality profile score for each locality being derived through neural network analyses of map images of the locality, the economic categorization being derived through neural network analyses of images of entities within the locality;

performing the neural network analysis via a convolutional neural network, the convolutional neural network consuming segmented pixel areas and distinguishing between areas containing at least one of text and icons from areas that do not contain at least one of text and icons;

grouping localities having similar locality profile scores;

extracting entities in a locality group;

retrieving historical data for the extracted entities in the locality group, wherein the historical data for the entities in the locality includes campaign vehicles hosted in the locality to promote sales of goods and/or services of an enterprise, leads generated by the campaign vehicles in the locality, and return on investment for the campaign vehicles in the locality;

generating a lead score for each entity in the locality group as a function of the locality profile score for the locality in which the entity is located, economic categorization of the locality in which the entity is located, and campaign vehicles used in the locality in which the entity is located, the lead score for an entity being further based on a number of employees of the entity and spending by the entity on products and/or services offered by the enterprise;

accessing a map image of a locality, wherein the map image includes geographical artefacts corresponding to entities within the locality;

analyzing the map image to detect the entities in the locality using the geographical artefacts; assigning entity classes to detected entities in the locality, the assigning entity classes including assigning the detected entities on one of a first type and a second type, the neural network analysis being performed for each of the first type and the second type, respectively; and

assigning the locality profile score to the locality based on entity classes included in the locality; and,

generating a lead score for a green field entity using information obtained from a third-party resource.

11. The non-transitory, computer-readable storage medium of claim 10 , further comprising:

generating a lead quotient for the entity, wherein the lead quotient is a function of the historical return on investment of campaigns within the locality and the lead score.

12. The non-transitory, computer-readable storage medium of claim 11 , further comprising:

comparing the lead quotient with an n′ tile threshold value; and

setting a lead converted/not converted flag for the entity when the lead quotient does not reach the n′ tile threshold value.

13. The non-transitory, computer-readable storage medium of claim 10 , wherein grouping localities having similar locality profile scores comprises:

determining a statistical distance metric between locality profile scores of the plurality of localities; and

grouping localities having a statistical distance metric below a predetermined threshold.

14. The non-transitory, computer-readable storage medium of claim 10 , further comprising:

accessing a map image of a locality, wherein the map image includes geographical artefacts corresponding to entities within the locality;

analyzing the map image to detect the entities in the locality using the geographical artefacts;

assigning entity classes to detected entities in the locality; and

assigning the locality profile score to the locality based on entity classes included in the locality.