Recommender evaluation based on tokenized messages

摘要

A machine may implement a recommender that provides recommendations to users. The machine may be configured to present a first version of the recommender configured by various parameters. A user may submit a message to the machine, and the machine may identify a parameter among the various parameters by tokenizing the message and identifying the parameter among the tokens. The machine may then generate a second version of the recommender by modifying the parameter and configuring the second version according to the modified parameter. The machine may then present the first and second versions of the recommender contemporaneously two different portions of the users. By tokenizing a further message received from the users, the machine may evaluate the first and second versions and determine whether the second version is a replacement of the first version.

主权项

1. A method comprising:
by a presentation module comprising one or more processors of a machine, presenting a recommender in a first configuration specified by parameters to provide users with recommendations; by a feedback module comprising one or more processors of the machine, identifying a parameter among the parameters by tokenizing a message that corresponds to a user among the users and identifying a token in the message as the parameter; by a modification module comprising one or more processors of the machine, determining a second configuration of the recommender by modifying the parameter; and by an evaluation module comprising one or more processors of the machine, presenting a first subset of the users with the recommender in the first configuration and a second subset of the users with the recommender in the second configuration.