US 12,282,803 B2
Systems and methods of optimizing resource allocation using machine learning and predictive control
Shihui Chen, Boston, MA (US); Keon Shik Kim, Cambridge, MA (US); and Douglas Hamilton, Boston, MA (US)
Assigned to Nasdaq, Inc., New York, NY (US)
Filed by Nasdaq, Inc., New York, NY (US)
Filed on Jan. 30, 2024, as Appl. No. 18/426,679.
Application 18/426,679 is a continuation of application No. 17/097,178, filed on Nov. 13, 2020, granted, now 11,922,217.
Prior Publication US 2024/0168808 A1, May 23, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 9/50 (2006.01); G06N 20/00 (2019.01); G06N 20/20 (2019.01)
CPC G06F 9/5027 (2013.01) [G06F 9/50 (2013.01); G06N 20/00 (2019.01); G06N 20/20 (2019.01)] 21 Claims
OG exemplary drawing
 
11. A method, comprising a computer system that includes at least one memory and at least one hardware processor:
receiving by a transceiver input data received by the transceiver from source nodes;
executing, by a processing system that includes at least one processor, instructions stored in memory as follows:
(a) defining for each of multiple data categories, a set of groups of data objects for the data category based on the input data;
(b) predicting, using one or more predictive machine learning models, transaction information for each group of data objects in the set of groups of data objects for the data category for a predetermined time period in the future;
(c) determining, using one or more control machine learning models, a quota for a particular group of data objects indicating how many data objects are permitted for the particular group of data objects, wherein the quota for the particular group of data objects is less than or equal to an initial number of data objects in the particular group based on the predicted transaction information for the particular group of data object;
(d) prioritizing, using one or more decision-making machine learning modelss, the quota of permitted data objects for the particular group of data objects based on one or more predetermined priority criteria, wherein prioritized permitted data objects are listed by the computer system for possible transactions;
(e) monitoring activities of the computer system for transactions of data objects during the predetermined time period;
(f) calculating performance metrics based on a difference between the predicted transaction information for the particular group of data objects and transactions of data objects for the particular group of data objects during the predetermined time period; and
(g) adjusting the one or more predictive machine learning models, the one or more control machine learning models, and the one or more decision-making machine learning models based on the performance metrics to improve their respective performances.