Back end server modification and model visualization
Product recommendations are selected according to a model. Product recommendations may be annotated with rules of the model used to select the products. A user may modify the model and be provided with a URL and a cookie associated with the modified model. Subsequent requests or the URL and presenting the cookie are processed using the modified model. A context may be associated with the cookie and modified by the user to observe performance of the model for the context. An interface may permit a user to specify rules for the model or otherwise model its behavior. User interactions with a website result in recommendations according to the model. A journey is recorded that records content, recommendations, and parameters of the model corresponding to the recommendations. The journeys of users may be filtered and visually presented to a user.
1. A method comprising, for each user of a plurality of users:
receiving, by a server system, a plurality of actions from the each user with respect to a website;
for each action of the plurality of actions:
transmitting, by the server system, content requested by the each action;
generating, by the server system, product recommendations using a model according to the each action and a profile of the each user; and
storing, by the server system, a record for the each action in a journey of the each user, the record including a descriptor of the each action and the product recommendations, wherein the journey is:
(a) a new journey if the each action is not a result of any preceding action of the plurality of actions and
(b) an existing journey if the each action is a result of an other action of the plurality of actions recorded in the existing journey;
determining, by the server system, that the each action is not the result of any action of the plurality of actions if it is entry to the web site from a referrer, not a result of interaction with another webpage of the website, and is not a result of interaction with a product recommendation of the product recommendations of any preceding action of the plurality of actions; and
determining that the each action is the result of the other action of the plurality of actions if the each action is any of: a result of user action with respect to a webpage or search result returned to the each user in response to the other action, a result of user action with respect to the product recommendations generated for the other action, or purchase of a product added to an electronic shopping cart by the other action.
2. The method of claim 1 , further comprising:
storing, by the server system, in the record for the each action, one or more parameters from the model describing generation of the product recommendations.
3. The method of claim 2 , wherein the one or more parameters include a confidence value according to the model for each product in the product recommendations.
4. The method of claim 1 , wherein the plurality of actions includes at least one of:
navigating to the web site from a referrer web site;
entering one or more search terms;
selecting a product from a set of the product recommendations for another action of the plurality of actions; and
selecting an advertisement on a different website.
5. The method of claim 4 , wherein the plurality of actions includes at least one of:
adding a product to an electronic shopping cart; and
purchasing contents of the electronic shopping cart.
6. The method of claim 1 , further comprising:
providing, by the server system, a graphical representation of the journey by rendering data from the record for at least one action of the plurality of actions.
7. The method of claim 1 , further comprising:
receiving, by the server system, an attribute criteria;
identifying, by the server system, a set of users of the plurality of users corresponding to the attribute criteria; and
providing, by the server system, a graphical representation of the journeys of the set of users by rendering data from the records for at least one action of the plurality of actions of each user of the set of users.
8. The method of claim 1 , further comprising:
receiving, by the server system, a journey filter criteria;
identifying, by the server system, a set of users of the plurality of users, the journeys of the set of users satisfying the journey filter criteria; and
providing, by the server system, a graphical representation of the journeys of the set of users by rendering data from the records for at least one action of the plurality of actions of each user of the set of users.
9. The method of claim 8 , wherein the filter criteria includes each journey of the journeys of the set of users including purchase of a product as one of the plurality of actions thereof.
10. The method of claim 8 , wherein the filter criteria includes each journey of the journeys of the set of users beginning with referral from a social media platform as one of the plurality of actions thereof.
11. The method of claim 1 , further comprising:
selecting, by the server system, a set of journeys from among the journeys of the plurality of users by applying filter criteria to each journey of the journeys of the plurality of users, the applying filter criteria including performing pattern analysis with respect to each journey.