Systems and methods for machine learning model to calculate user elasticity and generate recommendations using heterogeneous data
A method may include generating a feature table, hierarchical segments, and a graph network based on raw interaction data of a set of users. The method may further include generating a set of rankings for features in the feature table. The method may further include targeting hierarchical segments of the set of users through marketing campaigns and calculate a set of elasticity scores for the set of users in response to the marketing campaigns in the hierarchical segments. The method may further include generating item recommendations for the set of users based on the graph network. The method may further include executing a machine learning model to generate an uplift score for each user from the set of users based on at least one of the raw interaction data, the set of rankings, hierarchical segments, the set of elasticity scores, or the item recommendations.
1. A method comprising:
generating, by a processor, a graph corresponding to a set of features extracted from a set of data associated with activities of a set of users;
calculating, by the processor, a set of elasticity scores for a subset of users within the set of users corresponding to a segment of the set of users responding to a targeted marketing campaign, each of the set of elasticity scores being a numeric value representing a magnitude of change in purchasing probability for a respective user of the subset of users relative to a magnitude of change in price indicated in the targeted marketing campaign;
generating, by the processor, an item offer recommendation for at least a user within the subset of users;
training, by the processor, a neural network based at least on historic offers provided to historic users and a subset of the historic offers that were accepted by the historic users, the neural network trained to generate uplift scores as output using at least one or more elasticity scores as input, the uplift scores representing an impact on purchasing probability for one or more users due to offers being presented to the one or more users; and
generating, by the processor, an uplift score for at least one user within the subset of users by executing the trained neural network and using at least one elasticity score of the calculated set of elasticity scores corresponding to the at least one user.
2. The method of claim 1 , wherein the set of data comprises at least one of user transactional data, campaign data, marketing touchpoint data, loyalty information, geographical data, behavioral data, user segments, or de-identified user encoding data.
3. The method of claim 1 , wherein the set of data corresponds to heterogeneous data including at least one of multiple data types or originating from one or more data sources.
4. The method of claim 1 , further comprising receiving, by the processor, a number of segments for which to calculate elasticity scores from a client computing device.
5. The method of claim 1 , further comprising receiving, by the processor, an attribute of the segment from a client computing device.
6. The method of claim 1 , further comprising calculating, by the processor, using the set of elasticity scores, a threshold for identifying the segment.
7. The method of claim 1 , wherein the uplift score indicates an impact of the targeted marketing campaign on the at least one user.
8. The method of claim 1 , further comprising:
ranking, by the processor, each feature within the set of features, wherein the processor uses a subset of the set of features in accordance with their respective ranking to generate the graph.
9. The method of claim 1 , further comprising:
presenting, by the processor for display on a user interface, a graphical indication of a distribution of elasticity score among at least a portion of the set of users.
10. The method of claim 1 , further comprising:
presenting, by the processor for display on a user interface, a graphical indication of a distribution of uplift scores among at least a portion of the set of users.
11. A computer system comprising:
a server having at least one processor configured to:
generate a graph corresponding to a set of features extracted from a set of data associated with activities of a set of users;
calculate a set of elasticity scores for a subset of users within the set of users corresponding to a segment of the set of users responding to a targeted marketing campaign, each of the set of elasticity scores being a numeric value representing a magnitude of change in purchasing probability for a respective user of the subset of users relative to a magnitude of change in price indicated in the targeted marketing campaign;
generate an item offer recommendation for at least a user within the subset of users;
train a neural network based at least on historic offers provided to historic users and a subset of the historic offers that were accepted by the historic users, the neural network trained to generate uplift scores as output using at least one or more elasticity scores as input, the uplift scores representing an impact on purchasing probability for one or more users due to offers being presented to the one or more users; and
generate an uplift score for at least one user within the subset of users by executing the trained neural network and using at least one elasticity score of the calculated set of elasticity scores corresponding to the at least one user.
12. The computer system of claim 11 , wherein the set of data comprises at least one of user transactional data, campaign data, marketing touchpoint data, loyalty information, geographical data, behavioral data, user segments, or de-identified user encoding data.
13. The computer system of claim 11 , wherein the set of data corresponds to heterogeneous data including at least one of multiple data types or originating from one or more data sources.
14. The computer system of claim 11 , wherein the at least one processor is further configured to receive a number of segments from a client computing device.
15. The computer system of claim 11 , wherein the at least one processor is further configured to receive an attribute of the segment from a client computing device.
16. The computer system of claim 11 , wherein the at least one processor is further configured calculate, using the set of elasticity scores, a threshold for identifying the segment.
17. The computer system of claim 11 , wherein the uplift score indicates an impact of the targeted marketing campaign on the at least one user.
18. The computer system of claim 11 , wherein the at least one processor is further configured to rank each feature within the set of features, wherein the at least one processor uses a subset of the set of features in accordance with their respective ranking to generate the graph.
19. The computer system of claim 11 , wherein the at least one processor is further configured to present, for display on a user interface, a graphical indication of a distribution of elasticity score among at least a portion of the set of users.
20. The computer system of claim 11 , wherein the at least one processor is further configured to present, for display on a user interface, a graphical indication of a distribution of uplift scores among at least a portion of the set of users.