Machine learning digital promotion processing system based upon low-frequency and high-frequency data and related methods
A digital promotion system may include a user device and a digital promotion processing server. The digital promotion processing server is configured to repeatedly obtain low-frequency purchase data associated with a given user for a first category of purchases, and repeatedly obtain high-frequency purchase data associated with the given user for a second category of purchases different than the first category of purchases. The high-frequency purchase data may represent a greater number of purchases made in a given time period relative to the low-frequency purchase data. The digital promotion processing server is also configured to use machine learning to generate a current loyalty indicator based upon the repeatedly-obtained low-frequency purchase data and based upon the repeatedly-obtained high-frequency purchase data, and generate a digital promotion based upon the current loyalty indicator and communicate the digital promotion to the user device.
1. A digital promotion system comprising:
a user device; and
a digital promotion processing server configured to use machine learning to
repeatedly obtain low-frequency purchase data associated with a given user for non-grocery-related purchases purchased at a store other than a grocery store,
repeatedly obtain high-frequency purchase data associated with the given user for grocery-related purchases purchased at the grocery store, the high-frequency purchase data representing a greater number of purchases made in a given time period relative to the low-frequency purchase data and purchases made on at least a weekly basis, and the high frequency purchase data comprising purchased product brand data, purchased product pricing data, and purchased product quantity data,
learn correlations between the high-frequency purchase data and the low-frequency purchase data to generate a current loyalty indicator based upon the correlations so that the loyalty indicator is representative of how likely the given user is to make the non-grocery-related purchases,
update, on an ongoing basis, the current loyalty indicator based upon the learned correlations so that the current loyalty indicator is updated with each iteration of obtaining the repeatedly obtained high-frequency purchase data and with each iteration of obtaining the repeatedly obtained low-frequency purchase data, and
generate a digital promotion based upon the current loyalty indicator and communicate the digital promotion to the user device.
2. The digital promotion system of claim 1 wherein the non-grocery-related purchases comprise automotive-related purchases.
3. The digital promotion system of claim 1 wherein the non-grocery-related purchases comprise medical-related purchases.
4. The digital promotion system of claim 1 wherein the digital promotion processing server is configured to repeatedly obtain the low-frequency purchase data from at least one point-of-sale (POS) terminal.
5. The digital promotion system of claim 1 wherein the digital promotion processing server is configured to repeatedly obtain the high-frequency purchase data from at least one point-of-sale (POS) terminal.
6. The digital promotion system of claim 1 wherein the digital promotion has a value based upon the current loyalty indicator.
7. The digital promotion system of claim 1 wherein the digital promotion server is configured to learn grocery-related purchase patterns based upon the high-frequency purchase data and generate the loyalty indicator based upon the grocery-related purchase patterns.
8. A digital promotion processing server comprising:
a processor and an associated memory configured to use machine learning to
repeatedly obtain low-frequency purchase data associated with a given user for non-grocery-related purchases purchased at a store other than a grocery store,
repeatedly obtain high-frequency purchase data associated with the given user for grocery-related purchases purchased at the grocery store, the high-frequency purchase data representing a greater number of purchases made in a given time period relative to the low-frequency purchase data and purchases made on at least a weekly basis, and the high frequency purchase data comprising purchased product brand data, purchased product pricing data, and purchased product quantity data,
learn correlations between the high-frequency purchase data and the low-frequency purchase data to generate a current loyalty indicator based upon the repeatedly-obtained low-frequency purchase data and based upon the correlations so that the loyalty indicator is representative of how likely the given user is to make the non-grocery-related purchases,
update, on an ongoing basis, the current loyalty indicator based upon the learned correlations so that the current loyalty indicator is updated with each iteration of obtaining the repeatedly obtained high-frequency purchase data and with each iteration of obtaining the repeatedly obtained low-frequency purchase data, and
generate a digital promotion based upon the current loyalty indicator and communicate the digital promotion to a user device.
9. The digital promotion processing server of claim 8 wherein the non-grocery-related purchases comprise automotive-related purchases.
10. The digital promotion processing server of claim 8 wherein the non-grocery-related purchases comprise medical-related purchases.
11. The digital promotion processing server of claim 8 wherein the processor is configured to learn grocery-related purchase patterns based upon the high-frequency purchase data and generate the loyalty indicator based upon the grocery-related purchase patterns.
12. A method of processing a digital promotion comprising:
using a digital promotion processing server to use machine learning to
repeatedly obtain low-frequency purchase data associated with a given user for non-grocery-related purchases purchased at a store other than a grocery store,
repeatedly obtain high-frequency purchase data associated with the given user for grocery-related purchases made at the grocery store, the high-frequency purchase data representing a greater number of purchases made in a given time period relative to the low-frequency purchase data and purchases made on at least a weekly basis, and the high frequency purchase data comprising purchased product brand data, purchased product pricing data, and purchased product quantity data,
learn correlations between the high-frequency purchase data and the low-frequency purchase data to generate a current loyalty indicator based upon the correlations so that the loyalty indicator is representative of how likely the given user is to make the non-grocery-related purchases,
update, on an ongoing basis, the current loyalty indicator based upon the learned correlations so that the current loyalty indicator is updated with each iteration of obtaining the repeatedly obtained high-frequency purchase data and with each iteration of obtaining the repeatedly obtained low-frequency purchase data, and
generate a digital promotion based upon the current loyalty indicator and communicate the digital promotion to a user device.
13. The method of claim 12 wherein the non-grocery-related purchases comprise automotive-related purchases.
14. The method of claim 12 wherein the non-grocery-related purchases comprise medical-related purchases.
15. The method of claim 12 wherein using the digital promotion processing server comprises using the digital promotion processing server to learn grocery-related purchase patterns based upon the high-frequency purchase data and generate the loyalty indicator based upon the grocery-related purchase patterns.
16. A non-transitory computer readable medium for processing a digital promotion, the non-transitory computer readable medium comprising computer executable instructions that when executed by a processor cause the processor to perform operations comprising:
using machine learning for
repeatedly obtaining low-frequency purchase data associated with a given user for non-grocery-related purchases made at a store other than a grocery store,
repeatedly obtaining high-frequency purchase data associated with the given user for grocery-related purchases made at the grocery store, the high-frequency purchase data representing a greater number of purchases made in a given time period relative to the low-frequency purchase data and purchases made on at least a weekly basis, and the high frequency purchase data comprising purchased product brand data, purchased product pricing data, and purchased product quantity data,
learning correlations between the high-frequency purchase data and the low-frequency purchase data to generate a current loyalty indicator based upon the correlations so that the loyalty indicator is representative of how likely the given user is to make the non-grocery-related purchases,
updating, on an ongoing basis, the current loyalty indicator based upon the learned correlations so that the current loyalty indicator is updated with each iteration of obtaining the repeatedly obtained high-frequency purchase data and with each iteration of obtaining the repeatedly obtained low-frequency purchase data, and
generating a digital promotion based upon the current loyalty indicator and communicating the digital promotion to a user device.
17. The non-transitory computer readable medium of claim 16 wherein the non-grocery-related purchases comprise automotive-related purchases.
18. The non-transitory computer readable medium of claim 16 wherein the grocery-related purchases comprise medical-related purchases.
19. The non-transitory computer readable medium of claim 16 wherein the operations comprise learning grocery-related purchase patterns based upon the high-frequency purchase data and generate the loyalty indicator based upon the grocery-related purchase patterns.