Systems and methods for efficient frontier supplementation in multi-objective portfolio analysis

• US 7,469,228 B2
• Filed: 02/20/2004
• Issued: 12/23/2008
• Est. Priority Date: 02/20/2004
• Status: Expired due to Fees

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Bonissone, Piero Patrone, Subbu, Rajesh Venkat, Bollapragada, Srinivas, Eklund, Neil Holger White, Iyer, Naresh Sundaram, Chalermkraivuth, Kete Charles
• Primary Examiner(s): Kramer; James A
• Assistant Examiner(s): WONG, ERIC TAK WAI
• Application Number:
  US10/781,897
• Publication Number:
  US 20050187848A1
• Time in Patent Office: 1,768 Days
• Field of Search: 705/36.R
• US Class Current: 705/36.00R
• CPC Class Codes: G06Q 40/06 Asset management; Financial planning or analysis

Abstract

The systems and methods of the invention are directed to portfolio optimization and related techniques. For example, the invention provides a method for multi-objective portfolio optimization for use in investment decisions based on competing objectives and a plurality of constraints constituting a portfolio problem, the method comprising: performing a first multi-objective optimization process, based on competing objectives, to generate an efficient frontier of possible solutions; observing the generated efficient frontier; based on the observing, identifying an area of the efficient frontier in which there is a gap; and effecting a gap filling process by which the efficient frontier is supplemented in the area of the gap, the efficient frontier being used in investment decisioning.

Claims

1. A method for efficient frontier supplementation in multi-objective portfolio analysis, the method comprising:

generating an initial population of feasible solutions of portfolio allocations in a computing device;

generating a non-dominated solution set comprising a first efficient frontier in a portfolio performance space having at least three-dimensions using one of an evolutionary algorithm and optimization processing by using the computing device;

identifying at least one region having a gap in the at least three-dimensions of the first efficient frontier using a visualization tool;

interactively placing at least one target in the at least one region of the first efficient frontier using the visualization tool; and

providing the initial population of feasible solutions to a Target Objectives Genetic Algorithm (TOGA); and

performing TOGA processing in the at least one region of the first efficient frontier to generate supplemental solutions to the first efficient frontier and to create a second efficient frontier, the second efficient frontier being used in investment decisions.

2. The method of claim 1, further including the step of selecting at least one portfolio from the second efficient frontier.

3. The method of claim 1, wherein the TOGA further includes the steps of:

accepting a set of target vectors; and

generating a series of chromosomes, evaluated on the basis of the accepted target vectors, over multiple generations.

4. The method of claim 3, wherein the TOGA further includes the step of evaluating a fitness of each chromosome until a population with an acceptable fitness is determined so as to fill in the gap.

5. The method of claim 1, wherein the gap is a region that is sparsely populated by possible solutions.

6. A program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine to perform method steps for efficient frontier supplementation in multi-objective portfolio analysis, said method steps comprising:

generating an initial population of feasible solutions of portfolio allocations in a computing device;

generating a non-dominated solution set comprising a first efficient frontier in a portfolio performance space having at least three-dimensions using one of an evolutionary algorithm and optimization processing by using the computing device;

identifying at least one region having a gap in the at least three-dimensions of the first efficient frontier using a visualization tool;

interactively placing at least one target in the at least one region of the first efficient frontier using the visualization tool; and

providing the initial population of feasible solutions to a Target Objectives Genetic Algorithm (TOGA); and

performing TOGA processing in the at least one region of the first efficient frontier to generate supplemental solutions to the first efficient frontier and create a second efficient frontier, the second efficient frontier being used in investment decisions.