Class-based distributed evolutionary algorithm for asset management and trading

• US 8,768,811 B2
• Filed: 04/28/2010
• Issued: 07/01/2014
• Est. Priority Date: 04/28/2009
• Status: Active Grant

• Current Assignee: Cognizant Technology Solutions U.S. Corporation (Cognizant Technology Solutions Corp.)
• Original Assignee: Genetic Finance (Barbados) Limited
• Inventors: Hodjat, Babak, Shahrzad, Hormoz
• Primary Examiner(s): Khattar, Rajesh
• Application Number:
  US12/769,605
• Publication Number:
  US 20100274736A1
• Time in Patent Office: 1,525 Days
• Field of Search: 705 35- 40
• US Class Current: 705/36.R
• CPC Class Codes: G06N 3/126 Evolutionary algorithms, e.g. genetic algorithms or genetic programming
• CPC Class Codes: G06Q 40/04 Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
• CPC Class Codes: G06Q 40/06 Asset management; Financial planning or analysis

Abstract

A server computer and a multitude of client computers form a network computing system that is scalable and adapted to continue to evaluate the performance characteristics of a number of genes generated using a software application. Each client computer continues to periodically receive data associated with the stored genes stored in its memory. Using this data, the client computers evaluate the performance characteristic of their genes by comparing a solution provided by the gene with the periodically received data associated with that gene. Accordingly, the performance characteristic of each gene may be updated and varied with each periodically received data. The performance characteristic of a gene defines its fitness. The genes may be virtual asset traders that recommend trading options. The genes may be assigned initially to different classes to improve convergence but may later be decided to merge with genes of other classes to improve diversity.

Claims

1. A server computer system comprising:

a memory accessible to the server computer system and storing a server gene pool having some of the individuals in a plurality of individuals, each individual in the plurality of individuals identifying a corresponding subset of indicators in a plurality of indicators and further identifying at least one action in dependence upon the subset of indicators, not all of the subsets of indicators being the same;

a communications port through which the server computer system receives individuals from client computers in a plurality of client computers, each client computer in the plurality of client computers being assigned to a class, each of the classes being associated with a respective subset of indicators in a plurality of indicators, and at least one of the classes including more than one of the client computers, each received individual being one of the plurality of individuals and being received in conjunction with an associated received fitness value; and

a processor configured to;

accept at least some of the received individuals, and

transmit for further evaluation, each given individual in a first subset of the accepted individuals, to a given client computer which is a member of the class from which the server computer received the given individual.

2. A server computer system according to claim 1, wherein each of the individuals that the server computer system receives from the client computers have previously been evaluated on a first quantity of historical trading data and found to have had a fitness which exceeds a predetermined threshold fitness.

3. A server computer system according to claim 2, wherein the processor, in accepting at least some of the received individuals:

determines whether each of the received individuals is already stored in the server gene pool; and

discards all of the received individuals having an updated fitness value which is below a predetermined server minimum fitness,

wherein the updated fitness value for each received individual is the received fitness value of the individual for individuals which are not already stored in the server gene pool,

and wherein for individuals which are already stored in the server gene pool, the updated fitness value for each received individual is a combination of the received fitness value of the individual and a fitness value previously stored for the individual in the server gene pool.

4. A server computer system according to claim 3, wherein the predetermined server minimum fitness is dependent upon a fitness of the least fit individual in the server gene pool.

5. A server computer system according to claim 3, wherein the processor is further configured to store in the server gene pool at least some of the accepted individuals.

6. A server computer system according to claim 1, wherein the processor is further configured to determine whether a first one of the classes satisfies a predetermined convergence condition, and if so:

merge the first class with a second one of the classes to form a merged class, at least some of the client computers that were assigned to the first class being re-assigned to the merged class; and

transmit for further evaluation, to a client computer which is a member of the merged class, individuals which have been accepted and which were received from a client computer that was a member of the first class.

7. A server computer system according to claim 6, wherein the second class is also determined by the server computer system to satisfy a predetermined convergence condition,

wherein the merging of the first class with the second class further includes re-assigning to the merged class at least some of the client computers that were assigned to the second class being re-assigned,

and wherein the processor is further configured to transmit for further evaluation, to a client computer which is a member of the merged class, individuals which have been accepted and which were received from a client computer that was a member of the second class.

8. A server computer according to claim 6, wherein the merged class is associated with a union of the subset of indicators previously associated with the first class and the subset of indicators previously associated with the second class.

21. A server computer system according to claim 1, wherein through the communications port, in receiving individuals, the server computer system receives more than one of the individuals from a particular one of the client computers.

22. A server computer system according to claim 1, wherein the processor, in transmitting for further evaluation, transmits more than one individual to particular one of the client computers.

23. A server computer system according to claim 1, wherein the given client computer to which the processor transmits the given individual for further evaluation, is different than the client computer from which the server computer received the given individual.

9. A server computer system comprising:

a memory accessible to the server computer system and storing a server gene pool having some of the individuals in a plurality of individuals, each individual in the plurality of individuals identifying a corresponding subset of indicators in a plurality of indicators and further identifying at least one action in dependence upon the subset of indicators, not all of the subsets of indicators being the same;

a communications port through which the server computer system receives individuals from client computers in a plurality of client computers, each client computer in the plurality of client computers being assigned to a class, each of the classes being associated with a respective subset of indicators in a plurality of indicators, and at least one of the classes including more than one of the client computers; and

a processor configured to;

accept at least some of the received individuals, and

transmit to the client computers for further evaluation, each individual in a first subset of the accepted individuals,

wherein each given individual transmitted for further evaluation is transmitted for further evaluation to a member of the group consisting of;

a client computer which is a member of the same class from which the given individual was received by the server computer system; and

a client computer which is a member of a class which was derived at least in part from the class from which the given individual was received by the server computer system.

10. A server computer system according to claim 9, wherein the processor, in accepting at least some of the received individuals:

determines whether each of the received individuals is already stored in the server gene pool; and

discards all of the received individuals having an updated fitness value which is below a predetermined server minimum fitness, wherein the updated fitness value for each received individual is,

for individuals which are not already present in the server gene pool, a fitness value received by the server computer system in conjunction with the received individual; and

for individuals which are already present in the server gene pool, a combination of a fitness value received by the server computer system in conjunction with the received individual and a fitness value previously associated with the individual in the server gene pool.

11. A server computer system according to claim 10, wherein the predetermined server minimum fitness is dependent upon a fitness of the least fit individual in the server gene pool.

12. A server computer system according to claim 10, wherein the processor is further configured to store in the server gene pool at least some of the accepted individuals.

13. A server computer system according to claim 9, wherein the processor is further configured to determine whether a first one of the classes satisfies a predetermined convergence condition, and if so then to merge the first class with a second one of the classes to derive a merged class, at least some of the client computers that were assigned to the first class being re-assigned to the merged class,

wherein a first one of the individuals transmitted for further evaluation was received by the server computer system from the first class,

and wherein the first individual is transmitted for further evaluation to a first client computer in the merged class.

14. A server computer according to claim 13, wherein the first client computer was, prior to the merger, a member of the first class.

15. A server computer according to claim 13, wherein the first client computer was, prior to the merger, a member of the second class.

16. A server computer system according to claim 13, wherein the second class is also determined by the server computer system to satisfy a predetermined convergence condition,

wherein the merging of the first class with the second class further includes re-assigning to the merged class at least some of the client computers that were assigned to the second class,

wherein a second one of the individuals transmitted for further evaluation was received by the server computer system from the second class,

and wherein the second individual is transmitted for further evaluation to a second client computer in the merged class.

17. A server computer according to claim 13, wherein the merged class is associated with a union of the subset of indicators previously associated with the first class and the subset of indicators previously associated with the second class.

18. A server computer system according to claim 9, wherein one of the individuals transmitted for further evaluation is transmitted for further evaluation also to an additional member of the group.

19. A server computer system according to claim 9, wherein each of the individuals that the server computer system receives from the client computers has previously been evaluated on a first quantity of historical trading data and found to have had a fitness which exceeds a predetermined threshold fitness.

20. A server computer system according to claim 19, wherein a particular client computer, to which a particular one of the individuals is transmitted for further evaluation:

further evaluates the particular individual on a second quantity of historical trading data;

determines after the further evaluation whether the particular individual has a fitness which exceeds a predetermined threshold fitness; and

only if so, then

transmits the particular individual back to the server computer system.

24. A server computer system according to claim 9, wherein through the communications port, in receiving individuals, the server computer system receives more than one of the individuals from a particular one of the client computers.

25. A server computer system according to claim 9, wherein the processor, in transmitting for further evaluation, transmits more than one individual to particular one of the client computers.

26. A server computer system according to claim 9, wherein the given client computer to which the processor transmits the given individual for further evaluation, is different than the client computer from which the server computer received the given individual.