CPC G06Q 40/04 (2013.01) | 20 Claims |
1. A method of routing an incoming trade order electronically received by a trade order routing pipeline at an electronic trading server, the method comprising:
receiving, at a communication interface of the electronic trading server, information of the incoming trade order and a training dataset of historical trade data;
training a neural network based classification model implemented at the electronic trading server using historical patterns of trade costs from the training dataset of historical trade data to predict an execution style based on a trade cost;
transforming, by a processor at the electronic trading server, the received information of the incoming trade order into a vector of attributes;
generating, by the trained neural network based classification model implemented on one or more hardware processors of the electronic trading server, based on the vector of attributes, a respective probability indicating a likelihood that the incoming trade order is to be executed under each execution style from a set of execution styles;
determining, for each execution style, an estimate of an implementation shortfall metric for the incoming trade order being executed under the respective execution style;
selecting, from the set of execution styles, a recommended execution style from the set of execution styles that minimizes a combined metric computed based on the estimate of implementation shortfall metric subject to a threshold requirement placed on respective probabilities; and
routing the incoming trade order to a destination trade execution system based on the recommended execution style, wherein the routing comprises transmitting, via the communication interface, an electronic message comprising the incoming trade order to the destination trade execution system from the electronic trading server causing the incoming trade order to be executed under the recommended execution style.
|