Cross-device message touchpoint attribution
Fragmented user engagement stacks are generated from users that use multiple devices to view messages. The fragmented user engagement stacks include a universal unique identifier (UUID). A computer platform stores cross-device mapping information, derived from a shared characteristic between two or more devices, that associates the UUIDs of multiple devices to a single user. The computer platform processes the cross-device mapping data to identify the UUIDs from different devices associated with a single user and to join touchpoint encounters from the single user to generate at least one cross-device user engagement stack. The computer platform uses the cross-device user engagement stack and the response data to determine attribution as a measure of influence attributed to touchpoint encounters from a single user.
1. A computer-implemented method for generating attribution from fragmented user engagement stacks, comprising:
storing, in a computer platform, a plurality of fragmented user engagement stacks of a plurality of touchpoint encounters and response data for the touchpoint encounters, wherein the touchpoint encounters comprise a plurality of attributes that characterize exposure of a plurality of messages transmitted through a network to a plurality of devices common to a single user, and the attributes comprise a universal unique identifier (UUID);
storing, in the computer platform, at least one cross-device mapping data record, derived at least in part through at least one shared characteristic between two or more devices, that associates the UUIDs of at least two devices to a single user;
processing, in the computer platform, using the cross-device mapping data record, to identify at least two of the UUIDs from different devices associated with a single user and to join at least two touchpoint encounters from the single user that originated from the different devices so as to generate at least one cross-device user engagement stack;
generating a touchpoint response predictive model using cross-device user engagement stacks including the cross-device user engagement stack; and
generating, in the computer platform, using the touchpoint response predictive model, the cross-device user engagement stack, and the response data, attribution of the touchpoint encounters to responses to the messages based at least in part on a measure of an influence attributed to a respective touchpoint encounter in the cross-device user engagement stack, wherein the attribution attributes a first portion of the attribution of a first response to a first touchpoint for a first device in the cross-device user engagement stack and a second portion of the attribution for the first response to a second device in the cross-device user engagement stack, wherein first response is a conversion that occurred on the second device.
2. The computer-implemented method as set forth in claim 1 , wherein the messages exposed to a plurality of users comprise notification messages associated with an Internet of Things system.
3. The computer-implemented method as set forth in claim 1 , wherein the messages exposed to a plurality of users comprise marketing messages deployed across a plurality of media channels.
4. The computer-implemented method as set forth in claim 1 , wherein generating, in the computer platform, using the cross-device user engagement stack, attribution to responses to the messages comprises generating, in the computer platform, attribution to responses that measure a transition of the user from a first engagement state to a second engagement state.
5. The computer-implemented method as set forth in claim 1 , wherein generating, in the computer platform, using the cross-device user engagement stack, attribution to responses to the messages comprises generating, in the computer platform, at least one metric comprising of at least one of, a number of impressions, a number of clicks, a number of conversions, a number of true conversions, a CPA, a true CPA, a reach, or a lift.
6. The computer implemented method of claim 1 , wherein the shared characteristic between two or more devices comprises at least one of, login information, connection IP addresses, Wi-Fi networks used, websites visited, or any combination thereof.
7. The computer implemented method of claim 1 , further comprising generating the cross-device mapping data record using at least one of a deterministic matching or a probabilistic matching technique.
8. The computer implemented method of claim 1 , wherein generating, in the computer platform, using the cross-device user engagement stack and the response data, attribution to responses to the messages comprises:
storing, in a computer, response data for the touchpoint encounters that measures an effectiveness of the messages; and
training, using machine-learning techniques in a computer, the cross-device user engagement stack with the response data to generate the touchpoint response predictive model.
9. A computer readable medium, embodied in a non-transitory computer readable medium, the non-transitory computer readable medium having stored thereon a sequence of instructions which, when stored in memory and executed by a processor causes the processor to perform a set of acts, the acts comprising:
storing, in a computer platform, a plurality of fragmented user engagement stacks of a plurality of touchpoint encounters and response data for the touchpoint encounters, wherein the touchpoint encounters comprise a plurality of attributes that characterize exposure of a plurality of messages transmitted through a network to a plurality of devices common to a single user, and the attributes comprise a universal unique identifier (UUID);
storing, in the computer platform, at least one cross-device mapping data record, derived at least in part through at least one shared characteristic between two or more devices, that associates the UUIDs of at least two devices to a single user;
processing, in the computer platform, using the cross-device mapping data record, to identify at least two of the UUIDs from different devices associated with a single user and to join at least two touchpoint encounters from the single user that originated from the different devices so as to generate at least one cross-device user engagement stack;
generating a touchpoint response predictive model using cross-device user engagement stacks including the cross-device user engagement stack; and
generating, in the computer platform, using the touchpoint response predictive model, the cross-device user engagement stack, and the response data, attribution of the touchpoint encounters to responses to the messages based at least in part on a measure of an influence attributed to a respective touchpoint encounter in the cross-device user engagement stack, wherein the attribution attributes a first portion of the attribution of a first response to a first touchpoint for a first device in the cross-device user engagement stack and a second portion of the attribution for the first response to a second device in the cross-device user engagement stack, wherein first response is a conversion that occurred on the second device.
10. The computer readable medium as set forth in claim 9 , wherein the messages exposed to a plurality of users comprise notification messages associated with an Internet of Things system.
11. The computer readable medium as set forth in claim 9 , wherein the messages exposed to a plurality of users comprise marketing messages deployed across a plurality of media channels.
12. The computer readable medium as set forth in claim 9 , wherein generating, in the computer platform, using the cross-device user engagement stack, attribution to responses to the messages comprises generating, in the computer platform, attribution to responses that measure a transition of the user from a first engagement state to a second engagement state.
13. The computer readable medium as set forth in claim 9 , wherein generating, in the computer platform, using the cross-device user engagement stack, attribution to responses to the messages comprises generating, in the computer platform, at least one metric comprising of at least one of, a number of impressions, a number of clicks, a number of conversions, a number of true conversions, a CPA, a true CPA, a reach, or a lift.
14. The computer readable medium of claim 9 , wherein the shared characteristic between two or more devices comprises at least one of, login information, connection IP addresses, Wi-Fi networks used, websites visited, or any combination thereof.
15. The computer readable medium of claim 9 , further comprising generating the cross-device mapping data record using at least one of a deterministic matching or a probabilistic matching technique.
16. The computer readable medium of claim 9 , wherein generating, in the computer platform, using the cross-device user engagement stack and the response data, attribution to responses to the messages comprises:
storing, in a computer, response data for the touchpoint encounters that measures an effectiveness of the messages; and
training, using machine-learning techniques in a computer, the cross-device user engagement stack with the response data to generate the touchpoint response predictive model.
17. A system comprising:
a storage medium, having stored thereon, a sequence of instructions;
at least one processor, coupled to the storage medium, that executes the instructions to cause the processor to perform a set of acts comprising:
storing, in a computer platform, a plurality of fragmented user engagement stacks of a plurality of touchpoint encounters and response data for the touchpoint encounters, wherein the touchpoint encounters comprise a plurality of attributes that characterize exposure of a plurality of messages transmitted through a network to a plurality of devices common to a single user, and the attributes comprise a universal unique identifier (UUID);
storing, in the computer platform, at least one cross-device mapping data record, derived at least in part through at least one shared characteristic between two or more devices, that associates the UUIDs of at least two devices to a single user;
processing, in the computer platform, using the cross-device mapping data record, to identify at least two of the UUIDs from different devices associated with a single user and to join at least two touchpoint encounters from the single user that originated from the different devices so as to generate at least one cross-device user engagement stack; and
generating a touchpoint response predictive model using cross-device user engagement stacks including the cross-device user engagement stack; and
generating, in the computer platform, using the touchpoint response predictive model, the cross-device user engagement stack, and the response data, attribution of the touchpoint encounters to responses to the messages based at least in part on a measure of an influence attributed to a respective touchpoint encounter in the cross-device user engagement stack, wherein the attribution attributes a first portion of the attribution of a first response to a first touchpoint for a first device in the cross-device user engagement stack and a second portion of the attribution for the first response to a second device in the cross-device user engagement stack, wherein first response is a conversion that occurred on the second device.
18. The system as set forth in claim 17 , wherein the messages exposed to a plurality of users comprise notification messages associated with an Internet of Things system.
19. The system as set forth in claim 17 , wherein the messages exposed to a plurality of users comprise marketing messages deployed across a plurality of media channels.
20. The system as set forth in claim 17 , wherein generating, in the computer platform, using the cross-device user engagement stack, attribution to responses to the messages comprises generating, in the computer platform, attribution to responses that measure a transition of the user from a first engagement state to a second engagement state.