Method, apparatus, and computer program product for adaptive tail digital content object bid value generation

1. An apparatus for adaptively adjusting an electronic bid value for a tail digital content object, the apparatus comprising at least one processor and at least one memory including computer program code, the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to:

receive a training data cluster associated with a training digital content objects set, wherein each training digital content object of the training digital content objects set is associated with a training digital content object geolocation and a training digital content object category;

train a machine-learning model using the training data cluster associated with the training digital content objects set to generate a trained machine-learning model;

receive the tail digital content object;

extract a tail digital content object geolocation and a tail digital content object category associated with the tail digital content object;

retrieve a known data cluster associated with a related digital content objects set, wherein each related digital content object of the related digital content objects set is associated with the tail digital content object geolocation and the tail digital content object category, the known data cluster comprising a data records count and a historical digital content object interaction currency value for each related digital content object of the related digital content objects set;

compare the data records count to a data records count threshold, wherein the data record count threshold comprises a minimum number of data records for applying the trained machine-learning model to a final known data cluster;

upon determining that the data records count meets or exceeds the data records count threshold, transform the known data cluster into the final known data cluster;

programmatically generate, using the trained machine-learning model, an electronic bid value for the tail digital content object based at least in part on all of the historical digital content object interaction currency values of the final known data cluster; and

transmit the electronic bid value to a computing device.

2. The apparatus of claim 1 , wherein the data records count is a count of digital content object interactions having digital content object currency values associated therewith.

3. The apparatus of claim 1 , wherein the machine-learning model is trained using unsupervised learning.

4. The apparatus of claim 1 , wherein the machine-learning model is a clustering function.

5. The apparatus of claim 1 , wherein the tail digital content object is associated with a tail device rendered object.

6. The apparatus of claim 1 , wherein the computing device is associated with one or more of a search engine provider, a search engine marketing electronic auction or a display network auction.

7. The apparatus of claim 1 , wherein the tail digital content object is a keyword and wherein the keyword is associated with a digital content object interaction threshold that is based upon a digital content object conversion rate.

8. A method for adaptively adjusting an electronic bid value for a tail digital content object, the method comprising:

receiving a training data cluster associated with a training digital content objects set, wherein each training digital content object of the training digital content objects set is associated with a training digital content object geolocation and a training digital content object category;

training a machine-learning model using the training data cluster associated with the training digital content objects set to generate a trained machine-learning model;

receiving the tail digital content object;

extracting a tail digital content object geolocation and a tail digital content object category associated with the tail digital content object;

retrieving a known data cluster associated with a related digital content objects set, wherein each related digital content object of the related digital content objects set is associated with the tail digital content object geolocation and the tail digital content object category, the known data cluster comprising a data records count and a historical digital content object interaction currency value for each related digital content object of the related digital content objects set;

comparing the data records count to a data records count threshold, wherein the data records count threshold comprises a minimum number of data records for applying the trained machine-learning model to a final known data cluster;

upon determining that the data records count meets or exceeds the data records count threshold, transform the known data cluster into the final known data cluster;

programmatically generating, using the trained machine-learning model, an electronic bid value for the tail digital content object based at least in part on all of the historical digital content object interaction currency values of the final known data cluster; and

transmitting the electronic bid value to a computing device.

9. The method of claim 8 , wherein the data records count is a count of digital content object interactions having digital content object currency values associated therewith.

10. The method of claim 8 , wherein the machine-learning model is trained using unsupervised learning.

11. The method of claim 8 , wherein the machine-learning model is a clustering function.

12. The method of claim 8 , wherein the tail digital content object is associated with a tail device rendered object.

13. The method of claim 8 , wherein the computing device is associated with one or more of a search engine provider, a search engine marketing electronic auction or a display network auction.

14. The method of claim 8 , wherein the tail digital content object is a keyword and wherein the keyword is associated with a digital content object interaction threshold that is based upon a digital content object conversion rate.

15. A computer program product for adaptively adjusting an electronic bid value for a tail digital content object, the computer program product comprising at least one non-transitory computer-readable storage medium having computer-executable program code instructions stored therein, the computer-executable program code instructions comprising program code instructions for:

receiving a training data cluster associated with a training digital content objects set, wherein each training digital content object of the training digital content objects set is associated with a training digital content object geolocation and a training digital content object category;

training a machine-learning model using the training data cluster associated with the training digital content objects set to generate a trained machine-learning model;

receiving the tail digital content object;

extracting a tail digital content object geolocation and a tail digital content object category associated with the tail digital content object;

retrieving a known data cluster associated with a related digital content objects set, wherein each related digital content object of the related digital content objects set is associated with the tail digital content object geolocation and the tail digital content object category, the known data cluster comprising a data records count and a historical digital content object interaction currency value for each related digital content object of the related digital content objects set;

comparing the data records count to a data records count threshold, wherein the data records count threshold comprises a minimum number of data records for applying the trained machine-learning model to a final known data cluster;

upon determining that the data records count meets or exceeds the data records count threshold, transform the known data cluster into the final known data cluster;

programmatically generating, using the trained machine-learning model, an electronic bid value for the tail digital content object based at least in part on all of the historical digital content object interaction currency values of the final known data cluster; and

transmitting the electronic bid value to a computing device.

16. The computer program product of claim 15 , wherein the data records count is a count of digital content object interactions having digital content object currency values associated therewith.

17. The computer program product of claim 15 , wherein the machine-learning model is trained using unsupervised learning.

18. The computer program product of claim 15 , wherein the tail digital content object is associated with a tail device rendered object.

19. The computer program product of claim 15 , wherein the computing device is associated with one or more of a search engine provider, a search engine marketing electronic auction or a display network auction.

20. The computer program product of claim 15 , wherein the tail digital content object is a keyword and wherein the keyword is associated with a digital content object interaction threshold that is based upon a digital content object conversion rate.