US 10,891,327 B1
Computer-based systems and methods configured to utilize automating deployment of predictive models for machine learning tasks
Chen Wu, Vienna, VA (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Jul. 15, 2019, as Appl. No. 16/511,671.
Application 16/511,671 is a continuation of application No. 16/510,368, filed on Jul. 12, 2019, granted, now 10,614,382.
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 15/18 (2006.01); G06F 16/38 (2019.01); G06N 5/04 (2006.01); G06N 20/00 (2019.01); G06K 9/62 (2006.01); G06N 3/08 (2006.01); G06F 16/84 (2019.01); G06F 3/0484 (2013.01); G06F 8/60 (2018.01); G06F 8/36 (2018.01)
CPC G06F 16/38 (2019.01) [G06F 3/0484 (2013.01); G06F 16/86 (2019.01); G06K 9/6256 (2013.01); G06K 9/6263 (2013.01); G06N 3/08 (2013.01); G06N 5/04 (2013.01); G06N 20/00 (2019.01); G06F 8/36 (2013.01); G06F 8/60 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving, by one or more processors, a first application program interface (API) call comprising an input data value;
determining, by the one or more processors using a model wrapper, a score relating to the input data value, wherein the model wrapper is generated by applying a model wrapper code to a feature generation, a data grouping code, and a modeling code, wherein:
the feature generation code is configured to determine features relating to input data,
the data grouping code is configured to generate training data by determining a plurality of data groupings for the features relating to the input data, and
the modeling code is derived at least in part by applying one or more machine learning algorithms to the training data; and
sending, by the one or more processors, in response to the first API call, a second API call comprising the score.