| 主权项 |
1. A system, comprising:
one or more computing devices configured to:
train a machine learning model to generate values of one or more output variables corresponding to respective observation records at a machine learning service of a provider network, wherein the one or more output variables include a particular output variable;generate, corresponding to one or more evaluation runs of the machine learning model performed using respective evaluation data sets, a first set of data to be displayed via an interactive graphical interface, wherein the first set of data comprises at least (a) a statistical distribution of the particular output variable, and (b) a first prediction quality metric of the machine learning model, wherein the interactive graphical interface includes a first graphical control to modify a first prediction interpretation threshold associated with the machine learning model;determine, based at least in part on a detection of a particular client's use of the first graphical control, a target value of the first prediction interpretation threshold;initiate a display, via the interactive graphical interface, of a change to the first prediction quality metric resulting from a selection of the target value;in response to a request transmitted by a client via the interactive graphical interface, save the target value in a persistent repository of the machine learning service; andutilize the saved target value to generate one or more results of a subsequent run of the machine learning model. |
