Chicago Mercantile Exchange Inc.

Ari L Studnitzer

Frank Kmiec

Zachary Bonig

Ryan Eavy

Paul J Callaway

Barry Galster

Pearce Peck-Walden

Paul Andrew Bauerschmidt

James W Farrell

William J Albert

A Shanthi Thiruthuvadoss

José Antonio Acuña-Rohter

James Krause

Inderdeep Singh

David John Geddes

Seshadri Sundaram

Bernard Pieter Hosman

Kevin Kometer

Sana Fathallah-Shaykh

Dmitriy Glinberg

Edward M Gogol

Kyle Dennis Kavanagh

Eric Schuldt

Tae Seok C Yoo

Jacques Doornebos

Sunil Kiran Cutinho

Stephen M Goldman

Michael E Culhane

Paul I Lichter

Jeffrey Robert Mitchell

John Paul Scheerer

Jacob Doornebos

Brian Wolf

Giuseppe Scimeca

Matthew Coffey

Lori Flemm, Legal Representative

Christopher Reithel

Scott Henderson

Nathan Ball

Wayne G Arner, Ii

James Allen Bailey

Dileep Chakravarthi Konduru

Matthew Morano

David Alan Lariviere

Baris Mestanogullari

Brian Alvin Bourn

Suchith Vasudevan

Jake Siddall

John Curran

Manmathasivaram Nagarajan

Francis Bernard Bakalar

Jochen Mielke De Lima

Martin Stroup

Ken Silhavy

Dave Salvadori

Steven Hutt

Priteshkumar Soni

Fred Malabre

Arkadiusz Koziol

Sean Castette

Frederic Malabre

Mark Andrew Rogerson

Donald Mendelson

Mark Rogerson

Bernard Hosman

The disclosed embodiments relate to implementation, such as by a message processing system architecture, of a message handling system and/or protocol which mitigates optimistic messaging behavior. As used herein optimistic messaging behavior may at least refer to the transmission, in whole or in part, of a message, or of one or more messages of a sequence thereof, to a receiving system, such as the system implemented by the disclosed embodiments, prior to the sender determining that the message(s) is/are desired, alone or in conjunction with subsequently canceling or otherwise invalidating the message(s) once it has been determined that it is not desired. The disclosed embodiments mitigate such behavior by detecting and taking action with respect to these types of messages to deter optimizing behavior which may or may not be manipulative, while maintaining reliable message handling under increasing processing loads with minimal impact on users being able to send messages to the system.

Message processing protocol which mitigates optimistic messaging behavior

The disclosed embodiments relate to implementation of a trading system, which may also be referred to as a trading system architecture, having improved performance which further assures transactional determinism under increasing processing transaction loads while providing improved trading opportunities, fault tolerance, low latency processing, high volume capacity, risk mitigation and market protections with minimal impact, as well as improved and equitable access to information and opportunities.

Transactionally deterministic high speed financial exchange having improved, efficiency, communication, customization, performance, access, trading opportunities, credit controls, and fault tolerance

Systems and methods are provided for scoring the use of financial market messages. Uses of messages that are efficient and/or improve market liquidity receive positive scores. Traders are charge fees or receive rewards that are dependent upon message quality scores.

Message processing

Systems and methods are disclosed for ensuring execution of multiple inter-dependent transactions in an electronic data transaction processing system in which a plurality of data items are transacted by one or more hardware matching processors associated therewith that match a combined electronic data transaction request comprising a conditional execution instruction and a plurality of component electronic data transaction request messages, each for transaction of a different data item of the plurality of data items.

Execution of co-dependent transactions in a transaction processing system

Systems and methods are provided for processing and distributing market data. Critical data, such as data showing that a market price has changed is distributed without further delay. When the market data does not result in a change in a market price or does not meet another critical criteria, the market data is aggregated with market data for similar events and distributed when the aggregated market data passes a quantity threshold.

System and method for providing intelligent market data snapshots

Systems and methods for pre-processing data to facilitate efficient and accurate machine learning are provided. The data may include market data. The pre-processing may include partitioning the data into windows assigning categories to windows generate a series of vectors. The series of vectors then being input into a computer system that executes a machine learning algorithm to efficiently train a neural network used to identify structure or patterns therein.

Pre-processing financial market data prior to machine learning training

Systems and methods are provided to identify abnormal transaction activity by a participant that is inconsistent with current conditions. Historical participant and external data are identified. A recurrent neural network identifies patterns in the historical participant and external data. A new transaction by the participant is received. The new transaction is compared using the patterns to the historical participant and external data. An abnormality score is generated. An alert is generated if the abnormality score exceeds a threshold.

Deep learning for credit controls

Systems and methods for controlling use of a credit pool in connection with electronic trading in a plurality of product groups via a set of match engines are described. Credit data indicative of a current magnitude of the credit pool is obtained. A plurality of allocations of the credit pool are determined, based on the credit pool, across the plurality of product groups. For each allocation of the plurality of allocations, allocation data indicative of the allocation is provided to a respective credit controller of a set of credit controllers. The respective credit controller is disposed at a respective match engine to which a respective product group of the plurality of product groups is assigned. The use of the credit pool for an incoming order in a respective product group is thus limited in accordance with the allocation data provided to the credit controller at the respective match engine.

Distributed credit control with centralized allocation

Growing community of inventors

Northbrook, IL, United States of America

Ari L Studnitzer