Kete Charles Chalermkraivuth

Multiobjective financial portfolio design: a hybrid evolutionary approach

A principal challenge in modern computational finance is efficient portfolio design - portfolio optimization followed by decision-making. Optimization based on even the widely used Markowitz two-objective mean-variance approach becomes computationally challenging for real-life portfolios. Practical portfolio design introduces further complexity as it requires the optimization of multiple return and risk measures subject to a variety of risk and regulatory constraints. Further, some of these measures may be nonlinear and nonconvex, presenting a daunting challenge to conventional optimization approaches. We introduce a powerful hybrid multiobjective optimization approach that combines evolutionary computation with linear programming to simultaneously maximize these return measures, minimize these risk measures, and identify the efficient frontier of portfolios that satisfy all constraints. We also present a novel interactive graphical decision-making method that allows the decision-maker to quickly down-select to a small subset of efficient portfolios. The approach has been tested on real-life portfolios with hundreds to thousands of assets, and is currently being used for investment decision-making in industry.

A Review of Two Industrial Deployments of Multi-criteria Decision-making Systems at General Electric

Two industrial deployments of multi-criteria decision-making systems at General Electric are reviewed from the perspective of their multi-criteria decision-making component similarities and differences. The motivation is to present a framework for multi-criteria decision-making system development and deployment. The first deployment is a financial portfolio management system that integrates hybrid multi-objective optimization and interactive Pareto frontier decision-making techniques to optimally allocate financial assets while considering multiple measures of return and risk, and numerous regulatory constraints. The second deployment is a power plant management system that integrates predictive modeling based on neural networks, optimization based on multi-objective evolutionary algorithms, and automated decision-making based on Pareto frontier techniques. The integrated approach, embedded in a real-time plant optimization and control software environment dynamically optimizes emissions and efficiency while simultaneously meeting load demands and other operational constraints in a complex real-world power plant

GE Asset Management, Genworth Financial, and GE Insurance Use a Sequential-Linear-Programming Algorithm to Optimize Portfolios

GE Asset Management Incorporated (GEAM), a wholly owned subsidiary of General Electric Company (GE), manages investment portfolios on behalf of various GE units and over 200 unaffiliated clients worldwide, including Genworth Financial (Genworth) and GE Insurance (GEI) portfolios worth billions of dollars. GEAM invests portfolios of assets—derived from cash flows for various insurance, reinsurance, and financial products—primarily in corporate and government bonds in accordance with risk and regulatory constraints. In asset-liability management (ALM) applications, portfolio managers try to maximize return or minimize risk and match the characteristics of asset portfolios with corresponding liabilities. While risk is widely represented by variance or volatility, it is usually a nonlinear measure; ALM portfolio managers traditionally need to use linear risk sensitivities for computational tractability. We developed a novel, sequential-linear-programming algorithm that handles the nonlinearity iteratively but efficiently. Patented and implemented on a limited basis since 2003, GE used it to optimize more than 30 portfolios valued at over

Multi-criteria Set Partitioning for Portfolio Management: A Visual Interactive Method

30 billion. It is now in broader use at GEAM, GEI, and Genworth. Hypothetically, based on

Methods and systems for analytical-based multifactor multiobjective portfolio risk optimization

100 billion of assets, the present value of potential benefits could approximate

Systems and methods for multi-objective portfolio optimization

75 million over five years.

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

A visual interactive multi-criteria decision-making method for partitioning a portfolio of assets into mutually exclusive categories is presented. The two principal decision categories are hold and sell - portfolio assets in the sell category are considered as potential sale prospects, and the other assets in the portfolio are considered as potential retention prospects. The problem may be mathematically formulated as a multi-criteria 0/1 knapsack problem with multiple constraints. The decision-making method centers on the utilization of several coupled 2D projections of the portfolio in the multi-dimensional criterion space. The decision-maker interacts with these projections in a variety of ways to express and record multi-category (hold, hold-bias, sell-bias, and sell) set partitioning preferences. The decision-maker may also set an aggregated preference threshold that is utilized for partitioning the portfolio into the two principal hold and sell categories. The decision-maker may further fine-tune their preferences and threshold settings so as to achieve a multitude of financial targets.