Systems and methods for recommending cold-start items on a website of a retailer

1. A system comprising:

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:

receiving an identification of one or more first items of a plurality of items recommended by one or more first models;

determining static features common to both the one or more first items and one or more second items;

training, using the static features of the one or more first items, a second model to recommend at least one new item as one of one or more recommended items;

determining, using the second model and one or more static features of the at least one new item, whether to recommend the at least one new item as at least one of the one or more recommended items; and

coordinating displaying the at least one new item as the at least one of the one or more recommended items.

2. The system of claim 1 , wherein:

determining the static features comprises:

determining, using ensemble learning, the static features common to both the one or more first items and the one or more second items; and

the static features comprise one or more of a title, a description, an image, a price, a category, oritem specifications.

3. The system of claim 2 , wherein:

the ensemble learning comprises a blend of a set of models; and

the set of models comprise a linear model, a matrix factorization model, and a neural network model.

4. The system of claim 1 , wherein the computing instructions are further configured to run on the one or more processors and perform:

labelling, with positive training labels, one or more existing recommendations of the one or more first items after a user has had an interaction on a website with the one or more second items; and

labelling, with negative training labels, additional items of the plurality of items not recommended after the user has had the interaction on the website with the one or more second items.

5. The system of claim 4 , wherein the interaction with the one or more second items comprises at least one of:

a viewed-ultimately-bought (VUB) interaction wherein the user had viewed the one or more second items and ultimately bought the one or more first items;

a viewed-also-viewed (VAV) interaction wherein the user had viewed the one or more second items and also viewed the one or more first items during a single browsing session; and

a bought-also-bought (BAB) interaction wherein the user had bought the one or more second items and also bought the one or more first items within a predetermined window of time.

6. The system of claim 5 , wherein the one or more first models comprise at least three first models comprising:

a VUB model configured to make a first recommendation of the one or more first items based on the VUB interaction of the user with the one or more second items and the one or more first items;

a VAV model configured to make a second recommendation of the one or more first items based on the VAV interaction of the user with the one or more second items and the one or more first items; and

a BAB model configured to make a third recommendation of the one or more first items based on the BAB interaction of the user with the one or more second items and the one or more first items.

7. The system of claim 6 , wherein:

the first recommendation is based on a combination of (1) the one or more first items substituting for the one or more second items and (2) the one or more first items complementing the one or more second items;

the second recommendation is based on the one or more first items substituting for the one or more second items; or

the third recommendation is based on the one or more first items complementing the one or more second items.

8. The system of claim 1 , wherein training the second model comprises:

training a probabilistic model to (1) combine scoring from the one or more first models and (2) determine whether to coordinate displaying of any of the at least one new item as the at least one of the one or more recommended items with any of the plurality of items.

9. The system of claim 1 , wherein the computing instructions are further configured to run on the one or more processors and perform:

determining a respective ranking of each respective new item of a plurality of new items based on a respective likelihood of an additional user selecting each respective new item of the plurality of new items when each respective new item of the plurality of new items is displayed as the at least one of the one or more recommended items when one or more of the plurality of items are displayed on a website, wherein the plurality of new items comprise the at least one new item;

determining a quality of a respective seller of each respective new item of the plurality of new items; and

adjusting the respective ranking of one or more respective new items of the plurality of new items based on the quality of the respective seller of each respective new item of the plurality of new items.

10. The system of claim 1 , wherein the computing instructions are further configured to run on the one or more processors and perform:

collecting feedback comprising statistics of how many users selected a display of the at least one new item when the at least one new item was displayed on a website as the at least one of the one or more recommended items; and

adjusting the second model through reinforcement learning based on the feedback.

11. A method comprising:

receiving an identification of one or more first items of a plurality of items recommended by one or more first models;

determining static features common to both the one or more first items and one or more second items;

training, using the static features of the one or more first items, a second model to recommend at least one new item as one of one or more recommended items;

determining, using the second model and one or more static features of the at least one new item, whether to recommend the at least one new item as at least one of the one or more recommended items; and

coordinating displaying the at least one new item as the at least one of the one or more recommended items.

12. The method of claim 11 , wherein:

determining the static features comprises:

determining, using ensemble learning, the static features common to both the one or more first items and the one or more second items; and

the static features comprise one or more of a title, a description, an image, a price, a category, oritem specifications.

13. The method of claim 12 , wherein:

the ensemble learning comprises a blend of a set of models; and

the set of models comprise a linear model, a matrix factorization model, and a neural network model.

14. The method of claim 11 further comprising:

labelling, with positive training labels, one or more existing recommendations of the one or more first items after a user has had an interaction on a website with the one or more second items; and

labelling, with negative training labels, additional items of the plurality of items not recommended after the user has had the interaction on the website with the one or more second items.

15. The method of claim 14 , wherein the interaction with the one or more second items comprises at least one of:

a viewed-ultimately-bought (VUB) interaction wherein the user had viewed the one or more second items and ultimately bought the one or more first items;

a viewed-also-viewed (VAV) interaction wherein the user had viewed the one or more second items and also viewed the one or more first items during a single browsing session; and

a bought-also-bought (BAB) interaction wherein the user had bought the one or more second items and also bought the one or more first items within a predetermined window of time.

16. The method of claim 15 , wherein the one or more first models comprise at least three first models comprising:

a VUB model configured to make a first recommendation of the one or more first items based on the VUB interaction of the user with the one or more second items and the one or more first items;

a VAV model configured to make a second recommendation of the one or more first items based on the VAV interaction of the user with the one or more second items and the one or more first items; and

a BAB model configured to make a third recommendation of the one or more first items based on the BAB interaction of the user with the one or more second items and the one or more first items.

17. The method of claim 16 , wherein:

the first recommendation is based on a combination of (1) the one or more first items substituting for the one or more second items and (2) the one or more first items complementing the one or more second items;

the second recommendation is based on the one or more first items substituting for the one or more second items; or

the third recommendation is based on the one or more first items complementing the one or more second items.

18. The method of claim 11 , wherein training the second model comprises:

training a probabilistic model to (1) combine scoring from the one or more first models and (2) determine whether to coordinate displaying of any of the at least one new item as the at least one of the one or more recommended items with any of the plurality of items.

19. The method of claim 11 further comprising:

determining a respective ranking of each respective new item of a plurality of new items based on a respective likelihood of an additional user selecting each respective new item of the plurality of new items when each respective new item of the plurality of new items is displayed as the at least one of the one or more recommended items when one or more of the plurality of items are displayed on a website, wherein the plurality of new items comprise the at least one new item;

determining a quality of a respective seller of each respective new item of the plurality of new items; and

adjusting the respective ranking of one or more respective new items of the plurality of new items based on the quality of the respective seller of each respective new item of the plurality of new items.

20. The method of claim 11 further comprising:

collecting feedback comprising statistics of how many users selected a display of the at least one new item when the at least one new item was displayed on a website as the at least one of the one or more recommended items; and

adjusting the second model through reinforcement learning based on the feedback.