US 12,462,152 B2
Applied artificial intelligence technology for processing trade data to detect patterns indicative of potential trade spoofing
David I. Widerhorn, Phoenix, AZ (US); Paul Giedraitis, Chicago, IL (US); Melanie Rubino, Indianapolis, IN (US); and Carolyn Phillips, Chicago, IL (US)
Assigned to Trading Technologies International, Inc., Chicago, IL (US)
Filed by TRADING TECHNOLOGIES INTERNATIONAL INC., Chicago, IL (US)
Filed on Dec. 31, 2019, as Appl. No. 16/731,421.
Application 16/731,421 is a continuation of application No. 15/294,044, filed on Oct. 14, 2016, granted, now 10,552,735.
Claims priority of provisional application 62/307,108, filed on Mar. 11, 2016.
Claims priority of provisional application 62/250,470, filed on Nov. 3, 2015.
Claims priority of provisional application 62/241,751, filed on Oct. 14, 2015.
Prior Publication US 2020/0151565 A1, May 14, 2020
This patent is subject to a terminal disclaimer.
Int. Cl. G06N 3/08 (2023.01); G06N 3/004 (2023.01); G06N 3/04 (2023.01)
CPC G06N 3/08 (2013.01) [G06N 3/004 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method including:
receiving, by a computer system, trading data, wherein the trading data includes a plurality of time-stamped trade events with respect to a financial instrument in a financial market;
grouping, by the computer system, trade events in the trading data into a plurality of trading clusters by time proximity according to a burst interval time parameter such that consecutive trade events that differ in time by less than the burst interval time parameter are grouped in the same trading cluster and further such that consecutive trade events that differ in time by more than the burst interval time parameter are grouped in different trading clusters;
applying, by the computer system, data that represents each trading cluster of the plurality of the trading clusters to a trained classification model data structure to determine a spoofing classification status for each applied trading cluster, wherein the trained classification model data structure was created in response to the application of a machine-learning artificial intelligence to training data, wherein the spoofing classification status indicates a likelihood that the applied trading cluster describes trade spoofing in the financial market;
computing, by the computer system, a spoofing risk score for each trading cluster of the plurality of the trading clusters based on the determined spoofing classification status for each respective trading cluster;
determining, by the computer system, the computed spoofing risk score exceeds a threshold; and
automatically triggering, by the computer system, in response to determining the computed spoofing risk score exceeds the threshold, a kill switch in a trading platform used by a trader associated with the trade events of the corresponding trading cluster, wherein the kill switch halts trading by the trader in the trading platform.