Systems and methods for determining price bands and user price affinity predictions using machine learning architectures and techniques
Systems and methods including one or more processors and one or more non-transitory storage devices storing computing instructions configured to run on the one or more processors and perform acts of: providing a machine learning architecture that is configured to evaluate expensiveness of items relative to each other, wherein the items are included in an item type category; receiving prices associated with the items included in the item type category; generating, using a price band determination model associated with the machine learning architecture, price bands based, at least in part, on the prices associated with the items, each of the price bands being associated with separate price range boundaries for the item type category; and assigning each of the items to one of the price bands. Other embodiments are disclosed herein.
1. A system comprising:
one or more processors; and
one or more non-transitory computer-readable media storing computing instructions that, when executed on the one or more processors, cause the one or more processors to perform functions comprising:
receiving prices associated with items included in item type categories;
evaluating, using a price band determination model associated with a machine learning architecture, degrees of expensiveness of items relative to each other, wherein the items are included in the item type categories;
generating, using the price band determination model associated with the machine learning architecture, price bands for the items, wherein the price bands are based, at least in part, on the prices associated with the items, each of the price bands being associated with a respective price range boundary for a respective item type category;
assigning each of the items to one of the price bands associated with the respective item type category; and
presenting one or more other items corresponding to each one of the price bands associated with the respective item type category to one or more end-user applications.
2. The system of claim 1 , wherein:
the price bands for the item type categories comprises a low price band or a high price band;
expensiveness indicators for the degrees of expensiveness are stored in metadata associated with the items;
the expensiveness indicators identify the price bands that are associated with the items; and
the one or more end-user applications utilize the expensiveness indicators associated with the items to generate outputs.
3. The system of claim 2 , wherein the outputs generated by the one or more end-user applications include one or more of:
recommendation results that have been ranked based, at least in part, on the expensiveness indicators;
search results that have been ordered based, at least in part, on the expensiveness indicators; or
advertisements that have been selected based, at least in part, on the expensiveness indicators.
4. The system of claim 1 , wherein the price band determination model associated with the machine learning architecture executes a transaction balancing model to identify the respective price range boundaries associated with respective price bands of the price bands for the respective item type categories.
5. The system of claim 4 , where the transaction balancing model identifies the respective price range boundaries for the respective price bands in a manner that accounts for transaction volumes associated with respective ones of the items included in the respective item type category.
6. The system of claim 1 , wherein the price band determination model associated with the machine learning architecture executes a clustering model to identify the respective price range boundaries associated with the price bands.
7. The system of claim 6 , wherein the clustering model is selected from a group consisting of:
a K-means clustering model and a Gaussian mixture model.
8. The system of claim 1 , wherein the price band determination model associated with the machine learning architecture executes a statistical model to identify the respective price range boundaries associated with the price bands, and the statistical model is selected from a group consisting of: a range-based statistical model and a percentile-based statistical model.
9. The system of claim 1 , wherein the machine learning architecture further comprises an affinity prediction model that is configured to generate price affinity predictions for users, and the price affinity predictions predict preferences with respect to the price bands for the respective item type categories.
10. The system of claim 1 , wherein the machine learning architecture further comprises a ranking engine that is configured to order outputs generated by the one or more end-user applications, and the ranking engine is configured to order the outputs based, at least in part, on the price bands associated with the items.
11. A method being implemented via execution of computing instructions configured to run at one or more processors and configured to be stored at non-transitory computer-readable media, the method comprising:
receiving prices associated with items included in item type categories;
evaluating, using a price band determination model associated with a machine learning architecture, degrees of expensiveness of items relative to each other, wherein the items are included in the item type categories;
generating, using the price band determination model associated with the machine learning architecture, price bands for the items, wherein the price bands are based, at least in part, on the prices associated with the items, each of the price bands being associated with a respective price range boundary for a respective item type category;
assigning each of the items to one of the price bands associated with the respective item type category; and
presenting one or more other items corresponding to each one of the price bands associated with the respective item type category to one or more end-user applications.
12. The method of claim 11 , wherein:
the price bands for the item type categories comprises a low price band or a high price band;
expensiveness indicators for the degrees of expensiveness are stored in metadata associated with the items;
the expensiveness indicators identify the price bands that are associated with the items; and
the one or more end-user applications utilize the expensiveness indicators associated with the items to generate outputs.
13. The method of claim 12 , wherein the outputs generated by the one or more end-user applications include one or more of:
recommendation results that have been ranked based, at least in part, on the expensiveness indicators;
search results that have been ordered based, at least in part, on the expensiveness indicators; or
advertisements that have been selected based, at least in part, on the expensiveness indicators.
14. The method of claim 11 , wherein the price band determination model associated with the machine learning architecture executes a transaction balancing model to identify the respective price range boundaries associated with respective price bands of the price bands for the respective item type categories.
15. The method of claim 14 , where the transaction balancing model identifies the respective price range boundaries for the respective price bands in a manner that accounts for transaction volumes associated with respective ones of the items included in the respective item type category.
16. The method of claim 11 , wherein the price band determination model associated with the machine learning architecture executes a clustering model to identify the respective price range boundaries associated with the price bands.
17. The method of claim 16 , wherein the clustering model is selected from a group consisting of:
a K-means clustering model and a Gaussian mixture model.
18. The method of claim 11 , wherein the price band determination model associated with the machine learning architecture executes a statistical model to identify the respective price range boundaries associated with the price bands, and the statistical model is selected from a group consisting of:
a range-based statistical model and a percentile-based statistical model.
19. The method of claim 11 , wherein the machine learning architecture further comprises an affinity prediction model that is configured to generate price affinity predictions for users, and the price affinity predictions predict preferences with respect to the price bands for the respective item type categories.
20. The method of claim 11 , wherein the machine learning architecture further comprises a ranking engine that is configured to order outputs generated by one or more end-user applications, and the ranking engine is configured to order the outputs based, at least in part, on the price bands associated with the items.