Method, system, and apparatus for programmatically generating a channel incrementality ratio
Embodiments of the present disclosure provide methods, systems, and apparatuses for computing a channel incrementality ratio using a machine learning model.
1. A 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 to:
generate a sorted list comprising a plurality of channel identifiers, wherein each channel identifier of the plurality of channel identifiers is associated with a unique channel of a plurality of channels associated with a touchpoint timestamps subset associated with a first transaction timestamp of a plurality of transaction timestamps, and wherein the sorted list is in an order according to a latest channel landing-page touchpoint timestamp associated with each unique channel; and
generate, utilizing a machine learning model, a channel incrementality ratio associated with each unique channel based at least in part on the plurality of transaction timestamps and the sorted list.
2. The computer program product of claim 1 , wherein the computer-executable program code instructions further comprise program code instructions to:
generate, utilizing the machine learning model, the channel incrementality ratio associated with each unique channel based at least in part on a weighting factor assigned to each unique channel.
3. The computer program product of claim 2 , wherein the weighting factor assigned to each channel is programmatically generated based on a location of the channel identifier associated with the unique channel in the sorted list.
4. The computer program product of claim 2 , wherein the weighting factor assigned to each channel is a numerical value.
5. The computer program product of claim 1 , wherein the computer-executable program code instructions further comprise program code instructions to:
generate, utilizing the machine learning model, the channel incrementality ratio associated with each unique channel based at least in part on the touchpoint timestamps subset.
6. The computer program product of claim 1 , wherein the computer-executable program code instructions further comprise program code instructions to:
generate the touchpoint timestamps subset based at least in part on a plurality of touchpoint timestamps associated with the first transaction timestamp.
7. The computer program product of claim 6 , wherein each touchpoint timestamp of the touchpoint timestamps subset was received within a period of network time prior to the first transaction timestamp.
8. The computer program product of claim 6 , wherein each unique channel of the plurality of channels is associated with at least one touchpoint timestamp of the touchpoint timestamps subset.
9. The computer program product of claim 1 , wherein the computer-executable program code instructions further comprise program code instructions to:
determine each latest channel landing-page touchpoint timestamp associated with each unique channel.
10. The computer program product of claim 1 , wherein the computer-executable program code instructions further comprise program code instructions to:
receive a plurality of touchpoint signals from a plurality of client devices.
11. The computer program product of claim 10 , wherein each touchpoint timestamp of the touchpoint timestamps subset is associated with a touchpoint signal of the plurality of touchpoint signals.
12. The computer program product of claim 10 , wherein the computer-executable program code instructions further comprise program code instructions to:
receive a plurality of transaction signals from the plurality of client devices.
13. The computer program product of claim 12 , wherein the first transaction timestamp of the plurality of transaction timestamps is associated with a transaction signal of the plurality of transaction signals.
14. The computer program product of claim 1 , wherein a transaction timestamp represents a transaction signal receiving time and a touchpoint timestamp represents a touchpoint signal receiving time.
15. The computer program product of claim 1 , wherein the computer-executable program code instructions further comprise program code instructions to:
determine or adjust a channel currency allocation value associated with each unique channel based at least in part on its associated channel incrementality ratio.
16. An apparatus comprising at least one processor and at least one memory storing instructions that, with the at least one processor, configure the apparatus to:
generate a sorted list comprising a plurality of channel identifiers, wherein each channel identifier of the plurality of channel identifiers is associated with a unique channel of a plurality of channels associated with a touchpoint timestamps subset associated with a first transaction timestamp of a plurality of transaction timestamps, and wherein the sorted list is in an order according to a latest channel landing-page touchpoint timestamp associated with each unique channel; and
generate, utilizing a machine learning model, a channel incrementality ratio associated with each unique channel based at least in part on the plurality of transaction timestamps and the sorted list.
17. The apparatus of claim 16 , wherein the at least one memory stores instructions that, with the at least one processor, further configure the apparatus to:
generate, utilizing the machine learning model, the channel incrementality ratio associated with each unique channel based at least in part on a weighting factor assigned to each unique channel.
18. The apparatus of claim 17 , wherein the weighting factor assigned to each channel is programmatically generated based on a location of the channel identifier associated with the unique channel in the sorted list.
19. A computer-implemented method, comprising:
generating a sorted list comprising a plurality of channel identifiers, wherein each channel identifier of the plurality of channel identifiers is associated with a unique channel of a plurality of channels associated with a touchpoint timestamps subset associated with a first transaction timestamp of a plurality of transaction timestamps, and wherein the sorted list is in an order according to a latest channel landing-page touchpoint timestamp associated with each unique channel; and
generating, utilizing a machine learning model, a channel incrementality ratio associated with each unique channel based at least in part on the plurality of transaction timestamps and the sorted list.
20. The method of claim 19 , further comprising:
generating, utilizing the machine learning model, the channel incrementality ratio associated with each unique channel based at least in part on a weighting factor assigned to each unique channel.