Message transmission timing optimization

Patent metadata

Field	Value
Publication number	US-11023969-B2
Application number	US-201815889751-A
Country	US
Kind code	B2
Filing date	Feb 6, 2018
Priority date	Feb 6, 2018
Publication date	Jun 1, 2021
Grant date	Jun 1, 2021

Abstract

Systems and methods are provided for message transmission timing optimization. The system receives a large market disrupting transaction and provides a transaction placement strategy that splits up the transaction to maximizes favorable execution value and minimizes time required to execute the entire transaction.

First claim

What is claimed is:

1. A computer implemented method for preventing a disruption in an electronic data transaction processing system in which a plurality of data items are transacted by a hardware matching processor associated therewith that match, as they are received, incoming electronic data transaction request messages, for one of the plurality of data items received over a data communication network with at least one other previously received but unsatisfied electronic data transaction request message counter thereto stored in a memory associated with the plurality of data items coupled with the hardware matching processor, to at least partially satisfy one or both of the incoming electronic data transaction request messages or the at least one other previously received electronic data transaction request message, the method comprising:
determining that an incoming electronic data transaction request message would cause a change in the electronic data transaction processing system that would exceed a predefined threshold resulting in the disruption;
identifying a first state of the electronic data transaction processing system for the plurality of data items;
predicting, using a machine learnt network, based on the first state, an expected change in the state as a result of one or more potential electronic data transaction request messages with one or more different parameters, wherein the machine learnt network is a structured neural network and wherein the structured neural network is trained by identifying one or more patterns in historical transaction data and historical state data, the structured neural network comprising a layered plurality of interconnected processing nodes, wherein each connection of the plurality of interconnected processing nodes to another may be dynamically weighted, the one or more patterns indicative of expected changes in the historical state data as a result of the historical transaction data;
generating using the prediction, a transaction execution strategy that minimizes the disruption while maximizing a first parameter of the one or more different parameters and minimizing a second parameter, different from the first parameter, of the one or more different parameters;
generating one or more electronic data transaction request messages from the incoming electronic data transaction request message as a function of the transaction execution strategy based on the prediction by the machine learnt network; and
providing, according to the transaction execution strategy, the one or more electronic data transaction request messages to the electronic data transaction processing system.

2. The computer implemented method of claim 1 , further comprising:
identifying a second state of the electronic data transaction processing system for the plurality of data items as a result of providing a second incoming electronic data transaction request message to the electronic data transaction processing system;
predicting, using the machine learnt network, based on the second state, expected second changes in the state as a result of the one or more potential electronic data transaction request messages with the one or more different parameters;
updating using the prediction of the second expected changes, the transaction execution strategy that minimizes the disruption while maximizing the first parameter of the one or more different parameters and minimizing the second parameter of the one or more different parameters;
generating a second electronic data transaction request message as a function of the updated transaction execution strategy; and
providing according to the updated transaction execution strategy, the second electronic data transaction request message to the electronic data transaction processing system.

3. The computer implemented method of claim 1 , wherein determining comprises:
comparing a quantity value of the incoming electronic data transaction request message with a predefined threshold; and
determining that the incoming electronic data transaction request message is disruptive based on the comparison.

4. The computer implemented method of claim 1 , wherein the historical transaction data comprises at least a value and a quantity for each transaction in the historical transaction data.

5. The computer implemented method of claim 1 , wherein the historical state data comprises at least an inside market width, a volume at a top of a market, a liquidity in the market, and a time window of observation.

6. The computer implemented method of claim 1 , wherein the one or more different parameters include at least a value and a timing.

7. The computer implemented method of claim 6 , wherein generating the transaction execution strategy comprises:
identifying a plurality of potential electronic data transaction request messages to be transacted sequentially within a time window; wherein the plurality of potential electronic data request messages together comprises a total quantity equal to a quantity stored in the incoming electronic data transaction request message; wherein the plurality of electronic data transactions are identified based on the predictions to be transacted to maximize the value.

8. The computer implemented method of claim 7 , wherein the plurality of electronic data transactions are further identified based on the predictions to minimize the timing.

9. A system for executing an electronic data transaction request message exceeding a first predefined threshold in multiple parts, each of the multiple parts not exceeding the first predefined threshold, in an electronic data transaction processing system maximizing a first parameter and minimizing a second parameter, different from the first parameter, the electronic data transaction processing system comprising a plurality of data items transacted by a hardware matching processor associated therewith that match, as they are received, incoming electronic data transaction request messages, for one of the plurality of data items received over a data communication network with at least one other previously received but unsatisfied electronic data transaction request message counter thereto stored in a memory associated with the plurality of data items coupled with the hardware matching processor, to at least partially satisfy one or both of the incoming electronic data transaction request messages or the at least one other previously received electronic data transaction request message, with the execution of the multiple parts maximizing the first parameter and minimizing the second parameter, the system comprising:
a database configured to store historical data relating to historical states in the electronic data transaction processing system;
a disruption filter configured to identify that the electronic data transaction request message would cause a change in the electronic data transaction processing system that would exceed a second predefined threshold;
a machine learnt network configured to predict a future state of the electronic data transaction processing system as a function of a current state of the electronic data transaction processing system and one or more potential electronic data transaction request messages of different parameters;
wherein the machine learnt network is a structured neural network, wherein the machine learnt network is trained with the historical data stored in the database, and wherein the structured neural network is trained by identifying one or more patterns in the historical data; the structured neural network comprising a layered plurality of interconnected processing nodes, wherein each connection of the plurality of interconnected processing nodes to another may be dynamically weighted, the on

Assignees

• Chicago Mercantile Exchange Inc

Inventors

• Singh Inderdeep
• Malabre Frederic Cedric
• Studnitzer Ari L
• Geddes David John

Classifications

• G06Q40/04 Primary

  Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange · CPC title

• G06N20/00

  Machine learning · CPC title