This is derivative work from literature review of a paper, intending to serve as main alpha for the research project developed under ETC Investment Group, Academy Division. The underlying logic and technique follows through with the abstract: "This paper presents an integrated approach for portfolio selection in a multicriteria decision making framework. Firstly, we use Support Vector Machines for classifying financial assets in three pre-defined classes, based on their performance on some key financial criteria. Next, we employ Real-Coded Genetic Algorithm to solve a mathematical model of the multicriteria portfolio selection problem in the respective classes incorporating investorpreferences." Model: -Multicriteria portfolio selection model developed by Gupta et al. can yield positive results despite a deficit in areas of return and risk -Traditional Markowitz model Multiobjective programming model for asset portfolio allocation Tools and algorithms: Support Vector Machine Real Coded Genetic Algorithm Parameters: Short-term returns (12-month period) Long-term returns(36-month period) Risk Liquidity.
