Website data surfacing

1. A computer-implemented method comprising:

compiling, using a database, an inventory list for a plurality of websites comprising a first website and a second website;

detecting, using a browser extension on a user device associated with a user, user interaction information comprising a cursor selecting a first product out of stock at the first website;

collecting, using the browser extension on the user device, product information associated with one or more attributes of the first product displayed in the first website;

determining, based on the product information, that the first product is in the inventory list;

providing, as input to a first machine learning model, the user interaction information;

determining, based on output from the first machine learning model, a likelihood that the user would navigate away from the first website;

after determining that the likelihood does not exceed a threshold value:

monitoring further user interaction information associated the first product displayed in the first website;

providing, as input to the first machine learning model, the further user interaction information; and

updating, based on output from the first machine learning model, the likelihood that the user would navigate away from the first website; and

after determining that the likelihood exceeds the threshold value and before the user navigates away from the first website:

processing the product information to generate a record comprising a plurality of key words;

converting, based on the key words, the record into text embeddings or image embeddings corresponding to a vector of features;

determining, using a second machine learning model and based on the vector of features, a second product in the inventory list that is similar to the first product displayed in the first website, wherein the second product is in stock at the second website; and

causing, using the browser extension on the user device, display of the second product in an overlay window displayed in the first website.

2. The computer-implemented method of claim 1 , wherein the user interaction information further comprises operations associated with:

a cursor movement towards a back button or a close button on the first website;

navigating to a different tab in the first website.

3. The computer-implemented method of claim 1 , wherein determining the second product in the inventory list that is similar to the first product is based on at least one of:

a color variation,

a model variation; and

a variation in entities that provide the first product and the second product.

4. The computer-implemented method of claim 1 , further comprising:

receiving, from the user device, an indication of a user purchase of the second product in the overlay window;

assigning a first commission to a first interaction entity associated with the first website; and

assigning a second commission to a second interaction entity associated with the second website.

5. The computer-implemented method of claim 1 , further comprising:

training the first machine learning model to determine user intent based on first training data comprising:

a time period indicating user interaction with one or more products on a training website;

first information indicating whether a training user adds the one or more products into a cart on the training website;

second information indicating prior websites that the training user visited before arriving at the training website; and

third information indicating whether the training user visited the training website in the past.

6. The computer-implemented method of claim 5 , wherein the first training data further comprises:

search terms used by the training user on the training website; and

search results presented to the training user on the training website.

7. The computer-implemented method of claim 5 , wherein the first training data further comprises user attributes comprising:

a location of the training user;

an age of the training user; and

an IP address of the training user.

8. The computer-implemented method of claim 1 , further comprising:

training the second machine learning model to determine similar product based on second training data comprising:

a product category associated with a training product;

a price range of the training product; and

a color of the training product.

9. The computer-implemented method of claim 1 , further comprising:

receiving, from the user device, an indication of a user purchase of the second product in the overlay window; and

presenting, to the user device, one or more products complementary to the second product in the overlay window.

10. An electronic data sharing system comprising:

one or more processors; and

memory storing instructions that, when executed by the one or more processors, cause the electronic data sharing system to:

compile, using a database, an inventory list for a plurality of websites comprising a first website and a second website;

detect, using a browser extension on a user device associated with a user, user interaction information comprising a cursor selecting a first product out of stock at the first website;

collect, using the browser extension on the user device, product information associated with one or more attributes of the first product displayed in the first website;

determine, based on the product information, that the first product is in the inventory list;

provide, as input to a first machine learning model, the user interaction information;

determine, based on output from the first machine learning model, a likelihood that the user would navigate away from the first website;

after determining that the likelihood exceeds a threshold value and before the user navigates away from the first website:

process the product information to generate a record comprising a plurality of key words;

convert, based on the key words, the record into text embeddings or image embeddings corresponding to a vector of features;

determine, using a second machine learning model and based on the vector of features, a second product in the inventory list that is similar to the first product displayed in the first website, wherein the second product is in stock at the second website;

cause, using the browser extension on the user device, display of the second product in an overlay window displayed in the first website;

receive, from the user device, an indication of a user purchase of the second product in the overlay window;

assign a first commission to a first interaction entity associated with the first website; and

assign a second commission to a second interaction entity associated with the second website.

11. The electronic data sharing system of claim 10 , wherein the user interaction information comprises operations associated with:

a cursor movement towards a back button or a close button on the first website;

navigating to a different tab in the first website.

12. The electronic data sharing system of claim 10 , wherein the instructions cause the electronic data sharing system to:

determine the second product in the inventory list that is similar to the first product based on at least one of:

a color variation,

a model variation; and

a variation in entities that provide the first product and the second product.

13. The electronic data sharing system of claim 10 , wherein the instructions cause the electronic data sharing system to:

train the first machine learning model to determine user intent based on first training data comprising:

a time period indicating user interaction with one or more products on a training website;

first information indicating whether a training user adds the one or more products into a cart on the training website;

second information indicating prior websites that the training user visited before arriving at the training website; and

third information indicating whether the training user visited the training website in the past.

14. The electronic data sharing system of claim 10 , wherein the instructions cause the electronic data sharing system to:

train the second machine learning model to determine similar product based on second training data comprising:

a product category associated with a training product;

a price range of the training product; and

a color of the training product.

15. The electronic data sharing system of claim 10 , wherein the instructions cause the electronic data sharing system to:

after receiving the indication of the user purchase of the second product, present, to the user device, one or more products complementary to the second product in the overlay window.

16. The electronic data sharing system of claim 10 , wherein the instructions cause the electronic data sharing system to:

after determining that the likelihood does not exceed the threshold value, monitor further user interaction information associated the first product displayed in the first website;

provide, as input to the first machine learning model, the further user interaction information; and

determine, based on output from the first machine learning model, an updated likelihood that the user would navigate away from the first website.

17. One or more non-transitory media storing instructions that, when executed by one or more processors, cause the one or more processors to perform steps comprising:

compiling, using a database, an inventory list for a plurality of websites comprising a first website and a second website;

detecting, using a browser extension on a user device associated with a user, user interaction information comprising a cursor selecting a first product out of stock at the first website;

collecting, using the browser extension on the user device, product information associated with one or more attributes of the first product displayed in the first website;

determining, based on the product information, that the first product is in the inventory list;

providing, as input to a first machine learning model, the user interaction information;

determining, based on output from the first machine learning model, a likelihood that the user would navigate away from the first website; and

after determining that the likelihood exceeds a threshold value and before the user navigates away from the first website:

processing the product information to generate a record comprising a plurality of key words;

converting, based on the key words, the record into text embeddings or image embeddings corresponding to a vector of features;

determining, using a second machine learning model and based on the vector of features, a second product in the inventory list that is similar to the first product displayed in the first website, wherein the second product is in stock at the second website; and

causing, using the browser extension on the user device, display of the second product in an overlay window displayed in the first website.

18. The non-transitory media of claim 17 , wherein the instructions when executed by the one or more processors, cause the one or more processors to further perform steps comprising:

training the first machine learning model to determine user intent based on first training data comprising:

a time period indicating user interaction with one or more products on a training website;

first information indicating whether a training user adds the one or more products into a cart on the training website;

second information indicating prior websites that the training user visited before arriving at the training website; and

third information indicating whether the training user visited the training website in the past.

19. The non-transitory media of claim 17 , wherein the instructions when executed by the one or more processors, cause the one or more processors to further perform steps comprising:

training the second machine learning model to determine similar product based on second training data comprising:

a product category associated with a training product;

a price range of the training product; and

a color of the training product.

20. The non-transitory media of claim 17 , wherein the instructions when executed by the one or more processors, cause the one or more processors to further perform steps comprising:

after determining that the likelihood does not exceed the threshold value:

monitoring further user interaction information associated the first product displayed in the first website;

providing, as input to the first machine learning model, the further user interaction information; and

updating, based on output from the first machine learning model, the likelihood that the user would navigate away from the first website.