Goal programming with extended factors for portfolio selection

Abstract

This paper proposes and examines the use of several stock‐related factors, called extended factors, for portfolio selection. These factors, including the traditional factors of risk and return, are represented as objectives in weighted goal programming (WGP) models. Several WGP models with passive and active target values and various weights for their unwanted deviational variables in their achievement functions have been developed. The weights and target values of the extended factors represent decision makers’ utility toward their portfolio. The resulting portfolios for the proposed models are compared against each other as well as against the Dow Jones Industrial Average index and portfolios obtained from the well‐established Markowitz and Konno and Yamazaki's models. The experimental results strongly support the use of extended factors for portfolio selection problems and the assumption of meeting decision maker's preferences and utilities better than the portfolios based entirely on risk and return.

Portfolio selection: should investors include crypto‐assets? A multiobjective approach

“…(2007) and Abdelaziz and Masmoudi (2014) proposed new deterministic formulations to multi‐objective stochastic programs, to solve each a different portfolio selection problem. Tamiz and Azmi (2017) used the weighted goal programming (WGP) method, which is a multi‐objective approach, to solve their proposed portfolio selection model, with extended factors. Salas‐Molina (2019) applied goal programming to specify a cost‐risk minimization program and to generate optimal solutions for cash management models.…”

Robust, extended goal programming with uncertainty sets: an application to a multi-objective portfolio selection problem leveraging DEA

“…However, the intrinsic multidimensionality of the portfolio selection problem has been emphasized by many scholars. Empirical evidence shows that incorporating more than two factors in order to choose the best financial portfolio mitigates reliance on any single measure that might have flaws associated with it (Almeida-Filho et al, 2021;Colapinto et al, 2019;Doumpos & Zopounidis, 2014;Kim et al, 2022;Rahiminezhad Galankashi et al, 2020;Spronk et al, 2016;Steuer et al, 2007Steuer et al, , 2008Tamiz & Azmi, 2019;Tamiz et al, 2013;Xidonas et al, 2012). Furthermore, contemplating factors beyond risk and return is not an unsound move in a financial portfolio selection problem.…”

“…Actually, the synergy resulting from simultaneously employing these two techniques has the potential to enhance the predicting power of firms' future financial performance, thus leading to the selection of superior portfolios. In the domain of financial portfolio selection, the risk and return attributes of the investment are considered as technical factors (Kuo et al, 2021;Tamiz & Azmi, 2019). On the other hand, there are various ways to implement FA, one of which is Data Envelopment Analysis (DEA) (Abad et al, 2004;Edirisinghe & Zhang, 2007, 2008Lim et al, 2014).…”

“…In this manner, they are able to benefit from the capabilities of this mathematical framework, including sensitivity analysis, to effectively achieve their desired portfolios. Portfolio selection problems centered only on risk and return optimization can be described as a GP model comprising of two principal goals (Tamiz & Azmi, 2019). Nonetheless, as previously mentioned, extra objectives illustrating other factors and attributes can readily be incorporated into the versatile GP model.…”

Portfolio Selection and Post Optimality Test Using Goal Programming

“…Portfolio selection is done using fuzzy programming problem. Stoyan and Kwon [16] addressed a complex stochastic goal mixed-integer programming model for stock and bond portfolio. Masmoudi and Abdelaziz [14] presented a bi-objective stochastic programming, portfolio optimization model, which is solved by goal programming with the objectives return and risk.…”