| CPC G06N 20/00 (2019.01) [G06F 3/0482 (2013.01); G06F 3/04847 (2013.01); G06F 40/169 (2020.01); G06N 5/04 (2013.01)] | 20 Claims |

|
1. A system for deploying machine-learning services, the system comprising:
a display;
a processor operably connected to the display;
a memory operably connected to the processor, the memory storing:
a plurality of datastore objects, each datastore object storing data instances accessible to the processor,
a plurality of machine-learning (ML) model objects, each representing a different trained ML model, and
a set of instructions that, when executed, cause the processor to:
display, via the display, a graphical user interface (GUI) including a first set of icons representing the plurality of datastore objects, and a second set of icons representing the plurality of ML model objects;
detect selection of:
a first icon, from the first set of icons, identifying a first datastore object indicative of an input data source,
a second icon, from the second set of icons, indicative of a particular ML model object, and
a third icon, from the first set of icons, identifying a second datastore object indicative of a data destination;
instantiate a workflow object, wherein the workflow object includes (i) the first datastore object as the input data source, (ii) the particular ML model object, and (iii) the second datastore object as the data destination; and
execute the workflow object, wherein executing the workflow object causes the processor to:
access, from the first datastore object, a plurality of data instances, each data instance of the plurality of data instances comprising a set of features,
generate, using the particular ML model object, a plurality of predicted data instances, wherein generating each predicted data instance of the plurality of predicted data instances comprises:
inputting, to the particular ML model object, the set of features corresponding to an individual data instance of the plurality of data instances, wherein the individual data instance is processed by the ML model without use, by the ML model, of a remainder of data instances of the plurality of data instances, and
receiving, as output of the particular ML model, a predicted data instance corresponding to the individual data instance; and
store the plurality of predicted data instances to the second datastore object.
|