Solving constrained portfolio optimization model using stochastic fractal search approach

Abstract

PurposeOptimum utilization of investments has always been considered one of the most crucial aspects of capital markets. Investment into various securities is the subject of portfolio optimization intent to maximize return at minimum risk. In this series, a population-based evolutionary approach, stochastic fractal search (SFS), is derived from the natural growth phenomenon. This study aims to develop portfolio selection model using SFS approach to construct an efficient portfolio by optimizing the Sharpe ratio with risk budgeting constraints.Design/methodology/approachThis paper proposes a constrained portfolio optimization model using the SFS approach with risk-budgeting constraints. SFS is an evolutionary method inspired by the natural growth process which has been modeled using the fractal theory. Experimental analysis has been conducted to determine the effectiveness of the proposed model by making comparisons with state-of-the-art from domain such as genetic algorithm, particle swarm optimization, simulated annealing and differential evolution. The real datasets of the Indian stock exchanges and datasets of global stock exchanges such as Nikkei 225, DAX 100, FTSE 100, Hang Seng31 and S&P 100 have been taken in the study.FindingsThe study confirms the better performance of the SFS model among its peers. Also, statistical analysis has been done using SPSS 20 to confirm the hypothesis developed in the experimental analysis.Originality/valueIn the recent past, researchers have already proposed a significant number of models to solve portfolio selection problems using the meta-heuristic approach. However, this is the first attempt to apply the SFS optimization approach to the problem.

Monte carlo simulation with bilstm for day-ahead stock portfolio management

“…This research is motivated by the desire to address the constraints of conventional portfolio management techniques and leverage the The novel stochastic fractal search (SFS) method, incorporating risk-budgeting constraints, aims to assess its effectiveness by comparing it with particle swarm optimization, simulated annealing, and differential evaluation. The study confirms the superior performance of the SFS model among its peers [1]. The utilization of support vector machine (SVM) over random forest proves to yield lower correlation errors, making it a suitable choice for stock price prediction.…”

Portfolio selection model using teaching learning-based optimization approach

“…The topper among all learners in the specific class is taken as a teacher (𝑇 𝑔 ) for the g th generation according to the (6). Then, the difference mean for each subject is calculated by the (7),…”

“…Where Lnew is a new weight, Lold is the old weight, DMk is the difference mean of the particular subjects, and it is calculated as per (7). Now, apply the repairing procedure discussed in section 2.1 to satisfy the constraints given in (4) and (5).…”

“…Li [5] studied the optimal portfolio by genetic algorithm (GA). Shahid et al [6] presented a PSP optimizing the Sharpe ratio by applying the stochastic fractal search (SFS) method motivated by the natural growth process based on the principle of the fractal theory; they have also applied the SFS method to solve the constrained risk-budgeted portfolio optimization model [7]. Wang et al [8] solved the credit portfolio optimization problem with a multiobjective GA model.…”