Economic optimization for product search relevancy

1 . A system, comprising:

a processor; and

a non-transitory computer-readable medium having stored thereon instructions that when executed by the processor cause the system to perform operations comprising:

receiving a request for web page content;

parsing the request for the web page content to generate a new set of parsed content;

updating, based on the new set of parsed content, a hierarchical machine learning model that includes one or more existing sets of parsed content and a plurality of web page machine learning models, wherein the updating includes assigning the new set of parsed content, tracking data indicating user traffic for the new set of parsed content, and a corresponding web page machine learning model to a node in the hierarchical machine learning model;

traversing the updated hierarchical machine learning model based on the received request for the web page content;

selecting, based on the traversing, one or more models of the plurality of web page machine learning models included in the updated hierarchical machine learning model; and

executing the selected one or more models of the plurality of web page machine learning models to generate a customized web page for the requested web page content, wherein the generating includes optimizing the customized web page for user traffic on the requested web page content included in the customized web page.

2 . The system of claim 1 , wherein the plurality of web page machine learning models are further executable to customize one or more web pages based on one or more requests for web page content such that the customized one or more web pages are optimized for user traffic on the one or more web pages.

3 . The system of claim 1 , wherein updating the hierarchical machine learning model includes adding the new set of parsed content and a corresponding web page machine learning model to the hierarchical machine learning model, and wherein adding the new set of parsed content incorporates a new set of search queries that correspond to the new set of parsed content into the hierarchical machine learning model.

4 . The system of claim 1 , wherein the hierarchical machine learning model is a decision tree.

5 . The system of claim 4 , wherein updating the decision tree includes:

identifying, based on the new set of parsed content, one of the plurality of web page machine learning models; and

assigning the new set of parsed content and the identified web page machine learning model to a node of the decision tree.

6 . The system of claim 5 , wherein nodes of the decision tree are organized such that a shortest path to a highest return on investment (ROI) value is generated.

7 . The system of claim 1 , wherein updating the hierarchical machine learning model includes adding tracking data associated with at least one of selections or search queries performed on an existing web page.

8 . The system of claim 1 , wherein the instructions are further executable by the processor to cause the system to perform operations comprising:

querying a web page content database to retrieve one or more web page objects stored in the web page content database; and

inputting one or more of the web page objects retrieved from the web page content database during the querying into respective ones of the plurality of web page machine learning models.

9 . The system of claim 1 , wherein the operations further comprise:

storing the updated hierarchical machine learning model in a hierarchical data store for subsequent use.

10 . A non-transitory computer-readable medium having instructions stored thereon that when executed cause a computing device to perform operations comprising:

receiving a request for web page content;

parsing the request for the web page content to generate a new set of parsed content;

updating, based on the new set of parsed content, a hierarchical machine learning model that includes one or more existing sets of parsed content and a plurality of web page machine learning models, wherein the updating includes assigning the new set of parsed content, tracking data indicating user traffic for the new set of parsed content, and a corresponding web page machine learning model to a node in the hierarchical machine learning model;

traversing the updated hierarchical machine learning model based on the received request for the web page content;

selecting, based on the traversing, one or more models of the plurality of web page machine learning models included in the updated hierarchical machine learning model; and

executing the selected one or more models of the plurality of web page machine learning models to generate a customized web page for the requested web page content, wherein the generating includes optimizing the customized web page for user traffic on the requested web page content included in the customized web page.

11 . The non-transitory computer-readable medium of claim 10 , wherein updating the hierarchical machine learning model includes adding the new set of parsed content and a corresponding web page machine learning model to the hierarchical machine learning model, and wherein adding the new set of parsed content incorporates a new set of search queries that correspond to the new set of parsed content into the hierarchical machine learning model.

12 . The non-transitory computer-readable medium of claim 10 , wherein updating the hierarchical machine learning model includes adding tracking data relating to at least one of selections or search queries performed on a web page.

13 . The non-transitory computer-readable medium of claim 10 , wherein the hierarchical machine learning model is a decision tree, and wherein updating the decision tree includes:

identifying, based on the new set of parsed content, one of the plurality of web page machine learning models; and

assigning the new set of parsed content and the identified web page machine learning model to a node of the decision tree.

14 . The non-transitory computer-readable medium of claim 10 , wherein the operations further comprise:

querying a web page content database to retrieve one or more web page objects stored in the web page content database; and

inputting one or more of the web page objects retrieved from the web page content database during the querying into respective ones of the plurality of web page machine learning models.

15 . The non-transitory computer-readable medium of claim 10 , wherein at least one of the plurality of web page machine learning models is a deterministic algorithm.

16 . A method, comprising:

receiving, by a computer system, a request for web page content;

parsing, by the computer system, the request for the web page content to generate a new set of parsed content;

updating, by the computer system based on the new set of parsed content, a hierarchical machine learning model that includes one or more existing sets of parsed content and a plurality of web page machine learning models, wherein the updating includes assigning the new set of parsed content, tracking data indicating user traffic for the new set of parsed content, and a corresponding web page machine learning model to a node in the hierarchical machine learning model;

traversing, by the computer system, the updated hierarchical machine learning model based on the received request for the web page content;

selecting, by the computer system based on the traversing, one or more models of the plurality of web page machine learning models included in the updated hierarchical machine learning model; and

executing, by the computer system, the selected one or more models of the plurality of web page machine learning models to generate a customized web page for the requested web page content, wherein the generating includes optimizing the customized web page for user traffic on the requested web page content included in the customized web page.

17 . The method of claim 16 , wherein the plurality of web page machine learning models are further executable to customize one or more web pages based on one or more requests for web page content such that the customized one or more web pages are optimized for user traffic on the one or more web pages.

18 . The method of claim 16 , wherein updating the hierarchical machine learning model includes adding the new set of parsed content and a corresponding web page machine learning model to the hierarchical machine learning model, and wherein adding the new set of parsed content incorporates a new set of search queries that correspond to the new set of parsed content into the hierarchical machine learning model.

19 . The method of claim 16 , wherein the hierarchical machine learning model is a decision tree.

20 . The method of claim 19 , wherein updating the decision tree includes:

identifying, based on the new set of parsed content, one of the plurality of web page machine learning models; and

assigning the new set of parsed content and the identified web page machine learning model to a node of the decision tree.