A PYTHON-BASED MULTICRITERIA PORTFOLIO SELECTION DSS

摘要

Our purpose in this article is to develop an integrated portfolio management decision support system, which takes into account the inherent multidimensional nature of the problem, while allowing the DM, i.e. investor, to incorporate his/her preferences in the decision process. The proposed DSS has been developed in Python programming language and consists of two components: The first component is associated with the security selection phase, while the second component is associated with the portfolio optimization phase. In the first phase, four discrete multicriteria methods are employed; the PROMETHEE II, the ELECTRE III, the MAUT and the TOPSIS. After the cumulative integration of the results, a series of mathematical programming models are applied in the second phase, that of multicriteria portfolio optimization; a mixed-integer quadratic programming model, a goal programming model, a genetic algorithm model, and a multiobjective PROMETHEE flow model. Finally, the proposed approach is tested through a large-scale illustrative application in several stock markets and various sectors, analyzing simultaneously a very large number of securities.