US 12,118,614 B1
Systems and methods for electronic trade order routing
Shawn Simpson, New York, NY (US); Jingxin Xi, Jersey City, NJ (US); Donald Weidner, New York, NY (US); Trevor Hastie, Palo Alto, CA (US); and Robert Tibshirani, Stanford, CA (US)
Assigned to BlackRock, Inc., New York, NY (US)
Filed by BlackRock, Inc., New York, NY (US)
Filed on Jun. 22, 2022, as Appl. No. 17/847,055.
Claims priority of provisional application 63/256,378, filed on Oct. 15, 2021.
Claims priority of provisional application 63/256,354, filed on Oct. 15, 2021.
Claims priority of provisional application 63/256,316, filed on Oct. 15, 2021.
Int. Cl. G06Q 40/04 (2012.01); G06F 18/2415 (2023.01)
CPC G06Q 40/04 (2013.01) [G06F 18/2415 (2023.01)] 20 Claims
OG exemplary drawing
 
1. A method of electronically routing an incoming electronic trade order, the method comprising:
receiving, at a communication interface of a routing server, information of incoming electronic trade orders and a training dataset of historical trade data;
training a machine learning model implemented at the routing server using historical patterns of trade costs from the training dataset of historical trade data;
randomly dividing, at the routing server, the incoming electronic trade orders into a first set and a second set;
routing, via the communication interface of the routing server, the first set of trade orders to one or more trade execution entities each corresponding to a different execution style in an ad hoc manner;
generating, by the machine learning model implemented at the routing server, execution style recommendations in a form of a lookup table for the second set of trade orders according to a testing routing strategy;
routing, via the communication interface of the routing server, the second set of trade orders to corresponding trade execution entities based on the execution style recommendations;
computing a difference between performance metrics among the first set of trade orders and the second set of trade orders;
generating a decision on whether to adopt the machine learning model generated execution style recommendations based at least in part on the computed difference; and
routing, via the communication interface of the routing server, a new incoming electronic trade order to a particular trade execution entity based on a recommended execution style predicted by the machine learning model causing an execution of the new incoming electronic trade order using the recommended execution style, when the decision indicates to adopt the machine learning model generated execution style recommendations.