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 system comprising:
a back end server including one or more processing devices and one or more memory devices operably coupled to the one or more processing devices, the one or more memory devices storing executable code effective to cause the one or more processing devices to:
receive a first request from a user device, the first request associated with first context parameters describing the user device and a user of the user device;
process the first request by applying a selection model to the first context parameters to obtain a first response;
transmit the first response to the user device;
receive, from the user device, a specification of second context parameters that do not correspond to the user device and the user of the user device;
associate the second context parameters with an identifier;
transmit the identifier to the user device;
receive a second request from the user device, the second request associated with the first context parameters and including the identifier;
determine that the second request includes the identifier;
in response to determining that the second request includes the identifier, process, the second request by applying the selection model to the second context parameters instead of the first context parameters to obtain a second response; and
return the second response to the user device.
2. The system of claim 1 , further comprising a front end server programmed to receive the first request from the user device and forward the first request to the first server.
3. The system of claim 1 , wherein the first context parameters include at least one of: attributes of a user, a user browsing history, a user search history, a user purchase history, browser parameters for a browser generating the first request on the user device, and device parameters describing the user device.
4. The system of claim 1 , wherein the executable code is further effective to cause the one or more processing devices to:
receive, from the user device, an instruction to pin a selected result of the second response;
in response to the instruction to pin the selected result, modify the selection model to return the selected result in response to all requests.
5. The system of claim 1 , wherein the executable code is further effective to cause the one or more processing devices to:
receive, from the user device, an instruction to pin a selected result of the second response to the second context parameters; and
in response to the instruction to pin the selected result, modify the selection model to return the selected result in response to all requests having the second context parameters.
6. The system of claim 1 , further comprising:
receive, from the user device, an instruction to black list a selected result of the second response; and
in response to the instruction to blacklist the selected result, modify the selection model to refrain from returning the selected result.
7. The system of claim 1 , wherein the selection model is an artificial intelligence model.
8. A method comprising:
receiving, by a first server, a first request from a user device, the first request associated with first context parameters describing the user device and a user of the user device;
processing, by the first server, the first request by applying a selection model to the first context parameters to obtain a first response;
transmitting, by the first server, the first response to the user device;
receiving, by the first server, from the user device, a specification of second context parameters that do not correspond to the user device and the user of the user device;
associating, by the first server, the second context parameters with an identifier;
transmitting, by the first server, the identifier to the user device;
receiving, by the first server, a second request from the user device, the second request associated with the first context parameters and including the identifier;
determining, by the first server, that the second request includes the identifier;
in response to determining that the second request includes the identifier, processing, by the first server, the second request by applying the selection model to the second context parameters instead of the first context parameters to obtain a second response; and
returning, by the first server, the second response to the user device.
9. The method of claim 8 , further comprising
receiving, by a front end server, the first request from the user device and forwarding the first request to the first server.
10. The method of claim 8 , wherein the first context parameters include at least one of: attributes of a user, a user browsing history, a user search history, a user purchase history, browser parameters for a browser generating the first request on the user device, and device parameters describing the user device.
11. The method of claim 8 , further comprising:
receiving, by the first server from the user device, an instruction to pin a selected result of the second response;
in response to the instruction to pin the selected result, modifying, by the first server, the selection model to return the selected result in response to all requests.
12. The method of claim 8 , further comprising:
receiving, by the first server from the user device, an instruction to pin a selected result of the second response to the second context parameters;
in response to the instruction to pin the selected result, modifying, by the first server, the selection model to return the selected result in response to all requests having the second context parameters.
13. The method of claim 8 , further comprising:
receiving, by the first server from the user device, an instruction to black list a selected result of the second response;
in response to the instruction to blacklist the selected result, modifying, by the first server, the selection model to refrain from returning the selected result.
14. The method of claim 8 , wherein the selection model is an artificial intelligence model.