DISTRIBUTED EVOLUTIONARY ALGORITHM FOR ASSET MANAGEMENT AND TRADING

• US 20100274742A1
• Filed: 04/28/2010
• Published: 10/28/2010
• 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 Holdings Limited AMS Trustees Limited
• Inventors: Hodjat, Babak, Shahrzad, Hormoz
• Granted Patent: US 8,527,433 B2
• Time in Patent Office: Days
• US Class Current: 706/10
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/086 using evolutionary algorithms, e.g. genetic algorithms or genetic programming
• CPC Class Codes: G06N 3/12 using genetic models
• CPC Class Codes: G06N 3/126 Evolutionary algorithms, e.g. genetic algorithms or genetic programming
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

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 running on the client computers. Each client computer continues to periodically receive data associated with the 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, and the data associated with the genes may be historical trading data.

Claims

1. A networked computer system comprising a plurality of client computers, a first one of the plurality of client computers comprising:

a memory operative to store N genes, each gene characterized by a plurality of conditions and at least one action, wherein N is an integer greater than one;

a communication port adapted to continue to periodically receive data associated with the N genes; and

a processor operative to evaluate performance characteristic of each of the N genes by comparing a solution provided by each gene with the periodically received data associated with that gene, the performance characteristic of each gene being adjusted with each periodically received data and defining a fitness of the gene.

2. The networked computer system of claim 1 wherein the data associated with each gene is historical trading data and wherein the solution provided by each gene is a trading recommendation made by the gene.

3. The networked computer system of claim 2 wherein said first client computer is configured to discard M of the N genes after evaluating the fitness of the N genes for P days, each of the discarded genes having a fitness that falls below a first predefined threshold value, each of the remaining N−

M genes being a surviving gene, wherein M and P are integers and wherein M is smaller than N.

4. The networked computer system of claim 3 wherein said first client computer is further configured to:

evaluate, for a plurality of Q days in addition to the P days, the fitness of the remaining genes;

discard the genes whose fitness as evaluated during a sum of the P+Q days is below a second predefined threshold value; and

repeat the evaluation and the discard operations at least S times, wherein Q and S are integers, and wherein S is equal to or greater than 1, wherein genes surviving S evaluation and discard operations define a first elitist gene pool each gene being V trading days olds, wherein V is defined by the P+S*Q, wherein * represents a multiplication operation; and

transmit the first elitist pool of genes to a server computer.

5. The networked computer system of claim 4 wherein the first and second predefined threshold values are equal.

6. The networked computer system of claim 4 wherein said sever computer is adapted to:

receive the first elitist pool gene from the first client computer;

store the received genes in a server gene pool; and

transmit to each of at least a first subset of the plurality of client computers one or more genes of the server gene pool for fitness evaluation spanning W trading days.

7. The networked computer system of claim 4 wherein each of the at least a first subset of the plurality of client computers is adapted to:

receive the one or more genes of the server gene pool from the first server computer;

evaluate a fitness of the received genes by comparing trading recommendations made by each of the received genes with an associated historical trading data spanning the W trading days;

discard genes whose fitness are less than a third threshold value;

report discarded genes to the server computer; and

transmit genes that are not discarded to the server for storage in the server gene pool.

8. The networked computer system of claim 7 wherein said W trading days and V trading days do not overlap.

9. The networked computer system of claim 7 wherein said third threshold value is equal to the first and second threshold values.

10. The networked computer system of claim 7 wherein said genes are transmitted to the server computer only if their fitness is higher than the fitness of genes previously stored in the server gene pool.

11. The networked computer system of claim 2 wherein the N genes stored in the memory of the client computer are generated in accordance with computer instructions stored in the first client computer and executed by the processor of the first client computer.

12. The networked computer system of claim 7 wherein said server gene pool is configured to store a fixed number of genes.

13. The networked computer system of claim 10 wherein said sever is further adapted to combine a plurality of fitness values associated with each gene the server receives from the at least a first subset of the plurality of client computers with a corresponding fitness value stored in the server for that gene.

14. The networked computer system of claim 3 wherein said plurality of indicators are evaluated as a logical expression conjoined by logical AND and/or modified by logical NOT operations.

15. The networked computer system of claim 14 wherein the at least one action recommended by each gene is selected from a group consisting of buy, sell, hold, long exit and short exit recommendations.

16. A networked computer system comprising a server computer, said server computer configured to:

receive an elitist gene pool from a first one of a plurality of client computers;

store the received genes in a gene pool; and

transmit to each of at least a first subset of the plurality of client computers one or more genes of the server gene pool for fitness evaluation spanning W trading days, the elitist gene pool being generated by evaluating performance characteristic of each of N genes by comparing a solution provided by each gene with the periodically received data associated with the gene, the performance characteristic of each gene being adjusted with each periodically received data and defining a fitness of the gene, each gene characterized by a plurality of conditions and at least one action.

17. The networked computer system of claim 16 wherein the data associated with each gene is historical trading data and wherein the solution provided by each gene is a trading recommendation made by the gene.

18. The networked computer system of claim 17 wherein said first one of the plurality of client computers is configured to discard M of the N genes after evaluating the fitness of the N genes for P days, each of the discarded genes having a fitness that falls below a first predefined threshold value, each of the remaining N−

M genes being a surviving gene, wherein M and P are integers and wherein M is smaller than N.

19. The networked computer system of claim 18 wherein said first one of the plurality of client computers is further configured to:

evaluate, for a plurality of Q days in addition to the P days, the fitness of the remaining genes;

discard the genes whose fitness as evaluated during a sum of the P+Q days is below a second predefined threshold value; and

repeat the evaluation and the discard operations at least S times, wherein Q and S are integers, and wherein S is equal to or greater than 1, wherein genes surviving S evaluation and discard operations define the first elitist gene pool, each gene being V trading days olds, wherein V is defined by the P+S*Q, wherein * represents a multiplication operation.

20. The networked computer system of claim 17 wherein said server computer receives only genes whose fitness is higher than the fitness of genes previously stored in the server gene pool.

21. The networked computer system of claim 20 wherein said server gene pool is configured to store a fixed number of genes.

22. The networked computer system of claim 20 wherein said sever is further adapted to combine a plurality of fitness values associated with each gene the server receives with a corresponding fitness value stored in the server for that gene.

23. The networked computer system of claim 17 wherein said plurality of indicators are evaluated as a logical expression conjoined by logical AND and/or modified by logical NOT operations.

24. The networked computer system of claim 23 wherein the at least one action recommended by each gene is selected from a group consisting of buy, sell, hold, long exit and short exit recommendations.

25. A method for solving a computational problem using a plurality of client computers, the method comprising:

storing N genes, each gene characterized by a plurality of conditions and at least one action, wherein N is an integer greater than one;

continuing to periodically receive data associated with the N genes; and

evaluating performance characteristic of each of the N genes by comparing a solution provided by each gene with the periodically received data associated with that gene, the performance characteristic of each gene being adjusted with each periodically received data and defining a fitness of the gene.

26. The method of claim 25 wherein the data associated with each gene is historical trading data and wherein the solution provided by each gene is a trading recommendation made by the gene.

27. The method of claim 26 further comprising:

discarding M of the N genes after evaluating the fitness of the N genes for P days, each of the discarded genes having a fitness that falls below a first predefined threshold value, each of the remaining N−

M genes being a surviving gene, wherein M and P are integers and wherein M is smaller than N.

28. The method of claim 27 further comprising:

evaluation, for a plurality of Q days in addition to the P days, the fitness of the remaining genes;

discarding the genes whose fitness as evaluated during a sum of the P+Q days is below a second predefined threshold value; and

repeating the evaluation and the discard operations at least S times, wherein Q and S are integers, and wherein S is equal to or greater than 1, wherein genes surviving S evaluation and discard operations define a first elitist gene pool each gene being V trading days olds, wherein V is defined by the P+S*Q, wherein * represents a multiplication operation; and

transmitting the first elitist pool of genes to a server computer.

29. The method of claim 28 wherein the first and second predefined threshold values are equal.

30. The method of claim 28 further comprising:

receiving the first elitist pool gene from the first one of the plurality of client computer;

storing the received genes in a server pool gene; and

transmitting to each of at least a first subset of the plurality of client computers one or more genes of the server pool gene for fitness evaluation spanning W trading days.

31. The method of claim 28 further comprising:

receiving the first elitist pool gene from the first one of the plurality of client computer;

storing the received genes in a server pool gene; and

transmitting to each of at least a first subset of the plurality of client computers one or more genes of the server pool gene for fitness evaluation spanning W trading days.

32. The method of claim 31 wherein said W trading days and V trading days do not overlap.

33. The method of claim 31 wherein said third threshold value is equal to the first and second threshold values.

34. The method of claim 31 wherein said genes are transmitted to the server computer only if their fitness is higher than the fitness of genes previously stored in the server pool.

35. The method of claim 26 wherein the N stored genes in each client computer are generated in accordance with computer instructions stored in the first client computer and executed by the processor of the first client computer.

36. The method of claim 31 wherein said server pool is configured to store a fixed number of genes.

37. The method of claim 34 further comprising:

combining a plurality of fitness values associated with each gene the server receives from the at least a first subset of the plurality of client computers with a corresponding fitness value stored in the server for that gene.

38. The method of claim 27 wherein said plurality of indicators are evaluated as a logical expression conjoined by logical AND and/or modified by logical NOT operations.

39. The method of claim 38 wherein the at least one action recommended by each gene is selected from a group consisting of buy, sell, hold, long exit and short exit recommendations.

40. A stand alone computer comprising:

a processing core configured as a sever;

and a plurality of processing cores configured as clients, each of the plurality of clients comprising;

a memory operative to store N genes, each gene characterized by a plurality of conditions and at least one action, wherein N is an integer greater than one;

a port adapted to continue to periodically receive data associated with the N genes;

each client processing core configured to evaluate performance characteristic of each of the N genes by comparing a solution provided by each gene with the periodically received data associated with that gene, the performance characteristic of each gene being adjusted with each periodically received data and defining a fitness of the gene.

41. The stand alone computer of claim 40 wherein the data associated with each gene is historical trading data and wherein the solution provided by each gene is a trading recommendation made by the gene.

42. The stand alone computer of claim 41 wherein a first one of the plurality of client computers is configured to discard M of the N genes after evaluating the fitness of the N genes for P days, each of the discarded genes having a fitness that falls below a first predefined threshold value, each of the remaining N−

M genes being a surviving gene, wherein M and P are integers and wherein M is smaller than N.

43. The stand alone computer of claim 42 wherein said first one of the client computers is further configured to:

evaluate, for a plurality of Q days in addition to the P days, the fitness of the remaining genes;

discard the genes whose fitness as evaluated during a sum of the P+Q days is below a second predefined threshold value; and

repeat the evaluation and the discard operations at least S times, wherein Q and S are integers, and wherein S is equal to or greater than 1, wherein genes surviving S evaluation and discard operations define a first elitist gene pool each gene being V trading days olds, wherein V is defined by the P+S*Q, wherein * represents a multiplication operation; and

transmit the first elitist pool of genes to the server processing core.

44. The stand alone computer of claim 43 wherein the first and second predefined threshold values are equal.

45. The stand alone computer of claim 43 wherein said sever processing core is adapted to:

receive the first elitist pool gene from the first client processing core;

store the received genes in a server processing core pool gene; and

transmit to each of at least a first subset of the plurality of client processing cores one or more genes of the server processing core pool gene for fitness evaluation spanning W trading days.

46. The stand alone computer of claim 43 wherein each of the at least a first subset of the plurality of client processing cores is adapted to:

receive the one or more genes of the first elitist pool gene from the s processing core;

evaluate a fitness of the received genes by comparing trading recommendations made by each of the received genes with an associated historical trading data spanning the W trading days;

discard genes whose fitness are less than a third threshold value;

report discarded genes to the server processing core; and

transmit genes that are not discarded to the server processing core for storage in the server pool gene.

47. The stand alone computer of claim 46 wherein said W trading days and V trading days do not overlap.

48. The stand alone computer of claim 46 wherein said third threshold value is equal to the first and second threshold values.

49. The stand alone computer of claim 46 wherein said genes are transmitted to the server processing only if their fitness is higher than the fitness of genes previously stored in the server pool.

50. The stand alone computer of claim 41 wherein the N genes stored in each client processing core are generated in accordance with computer instructions stored in the and executed by the stand alone computer.

51. The stand alone computer of claim 46 wherein said server processing core pool is configured to store a fixed number of genes.

52. The stand alone computer of claim 49 wherein said sever processing core is further adapted to combine a plurality of fitness values associated with each gene the server processing core receives from the at least first subset of the plurality of client processing cores with a corresponding fitness value stored in the server processing core for that gene.

53. The stand alone computer of claim 42 wherein said plurality of indicators are evaluated as a logical expression conjoined by logical AND and/or modified by logical NOT operations.

54. The stand alone computer of claim 43 wherein the at least one action recommended by each gene is selected from a group consisting of buy, sell, hold, long exit and short exit operations.

55. The stand alone computer of claim 40 wherein said stand alone computer is a mainframe computer.