Machine learning to automate request tagging for conversion funnels
Methods, computer readable media, and devices for machine learning for automated tagging of requests for e-commerce conversion funnel tracking. One method may include retrieving a plurality of requests previously grouped into a user session, generating preprocessed request information by determining a request type, a relative time, and a keyword count for each of the plurality of requests and determining a determining a relative time distribution for each of the plurality of keywords, and applying a machine learning model to the plurality of requests and the preprocessed request information to tag each of the plurality of requests as being associated with one of the plurality of conversion classifications.
1. A computer-implemented method for improving the efficiency of an e-commerce hosting system having a machine learning model, to streamline and enhance user experience, comprising:
retrieving a plurality of requests previously grouped into a user session, wherein:
each request comprises a uniform resource locator (URL), a timestamp, a request method, a referrer, and a session identifier; and
the user session comprises a session start time, a session end time, and a session length;
generating preprocessed request information related to a plurality of conversion funnel metrics by:
determining a request type for each of the plurality of requests;
determining a relative time for each of the plurality of requests, the relative time being relative to the session length;
determining, for each of the plurality of requests, a keyword count for each of a plurality of keywords, wherein:
each of the plurality of keywords belongs to one or more keyword lists; and
each keyword list corresponds to one of a plurality of conversion classifications; and
determining a relative time distribution for each of the plurality of keywords, the relative time distribution being relative to the session length;
applying the machine learning model to the plurality of requests and the preprocessed request information to tag each of the plurality of requests as being associated with one of the plurality of conversion classifications;
creating a conversion funnel for the user session based on the preprocessed request information and the plurality of conversion funnel metrics, the conversion funnel comprising a plurality of conversion stages through a website; and
determining whether the user session results in a purchase based upon the conversion funnel.
2. The computer-implemented method of claim 1 , wherein the plurality of requests comprises requests made by a user to a website.
3. The computer-implemented method of claim 1 , wherein each request type is one of a top-level page request or a child request.
4. The computer-implemented method of claim 1 , wherein each relative time is one of early, middle, or late.
5. The computer-implemented method of claim 1 , wherein each relative time distribution is one of early, middle, late, or uniform.
6. The computer-implemented method of claim 1 , wherein the machine learning model comprises a decision tree or a random forest.
7. The computer-implemented method of claim 1 , wherein the conversion funnel is created further based on a tag of each of the plurality of requests.
8. The computer-implemented method of claim 1 , further comprising:
retrieving a second plurality of requests previously grouped into a second user session;
generating second preprocessed request information by:
determining a request type for each of the second plurality of requests;
determining a relative time for each of the second plurality of requests;
determining, for each of the second plurality of requests, a keyword count for each of a second plurality of keywords; and
determining a relative time distribution for each of the second plurality of keywords; and
applying the machine learning model to the second plurality of requests and the second preprocessed request information to tag each of the second plurality of requests as being associated with one of the plurality of conversion classifications.
9. A non-transitory machine-readable storage medium that provides
instructions that, if executed by a processor, are configurable to cause the processor to perform operations for improving the efficiency of an e-commerce hosting system having a machine learning model, to streamline and enhance user experience, comprising:
retrieving a plurality of requests previously grouped into a user session, wherein:
each request comprises a uniform resource locator (URL), a timestamp, a request method, a referrer, and a session identifier; and
the user session comprises a session start time, a session end time, and a session length;
generating preprocessed request information related to a plurality of conversion funnel metrics by:
determining a request type for each of the plurality of requests;
determining a relative time for each of the plurality of requests, the relative time being relative to the session length;
determining, for each of the plurality of requests, a keyword count for each of a plurality of keywords, wherein:
each of the plurality of keywords belongs to one or more keyword lists; and
each keyword list corresponds to one of a plurality of conversion classifications; and
determining a relative time distribution for each of the plurality of keywords, the relative time distribution being relative to the session length;
applying the machine learning model to the plurality of requests and the preprocessed request information to tag each of the plurality of requests as being associated with one of the plurality of conversion classifications;
creating a conversion funnel for the user session based on the preprocessed request information and the plurality of conversion funnel metrics, the conversion funnel comprising a plurality of conversion stages through a website; and
determining whether the user session results in a purchase based upon the conversion funnel.
10. The non-transitory machine-readable storage medium of claim 9 , wherein the plurality of requests comprises requests made by a user to a website.
11. The non-transitory machine-readable storage medium of claim 9 , wherein each request type is one of a top-level page request or a child request.
12. The non-transitory machine-readable storage medium of claim 9 , wherein each relative time is one of early, middle, or late.
13. The non-transitory machine-readable storage medium of claim 9 , wherein each relative time distribution is one of early, middle, late, or uniform.
14. The non-transitory machine-readable storage medium of claim 9 , wherein the machine learning model comprises a decision tree or a random forest.
15. The non-transitory machine-readable storage medium of claim 9 , further comprising creating, for the plurality of requests, a conversion funnel based on a tag of each of the plurality of requests.
16. An apparatus for improving the efficiency of an e-commerce hosting system having a machine learning model, to streamline and enhance user experience, comprising:
a processor; and
a non-transitory machine-readable storage medium that provides instructions that, if executed by a processor, are configurable to cause the processor to perform operations
comprising:
retrieving a plurality of requests previously grouped into a user session, wherein:
each request comprises a uniform resource locator (URL), a timestamp, a request method, a referrer, and a session identifier; and
the user session comprises a session start time, a session end time, and a session length;
generating preprocessed request information related to a plurality of conversion funnel metrics by:
determining a request type for each of the plurality of requests;
determining a relative time for each of the plurality of requests, the relative time being relative to the session length;
determining, for each of the plurality of requests, a keyword count for each of a plurality of keywords, wherein:
each of the plurality of keywords belongs to one or more keyword lists; and
each keyword list corresponds to one of a plurality of conversion classifications; and
determining a relative time distribution for each of the plurality of keywords, the relative time distribution being relative to the session length;
applying the machine learning model to the plurality of requests and the preprocessed request information to tag each of the plurality of requests as being associated with one of the plurality of conversion classifications;
creating a conversion funnel for the user session based on the preprocessed request information and the plurality of conversion funnel metrics, the conversion funnel comprising a plurality of conversion stages through a website; and
determining whether the user session results in a purchase based upon the conversion funnel.
17. The apparatus of claim 16 , wherein the plurality of requests comprises requests made by a user to a website.
18. The apparatus of claim 16 , wherein each request type is one of a top-level page request or a child request.
19. The apparatus of claim 16 , wherein the machine learning model comprises a decision tree or a random forest.
20. The apparatus of claim 16 , wherein the operations further comprise creating, for the plurality of requests, a conversion funnel based on a tag of each of the plurality of requests.