Implementation of particle swarm optimization in construction of optimal risky portfolios

Dashti, M.A.; Farjami, Y.; Vedadi, Ahmad; Anisseh, Mohammad

doi:10.1109/ieem.2007.4419303

Cited by 23 publications

(13 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both algorithms are converged using the minimum error criteria. For the correct accuracy percentage, it shows that FNNPSO result is better than FNNBP with 100% compared to 85.5% but FNNBP convergence time is faster at 1000 iterations compared with 1800 iterations in FNNPSO as show in figure (10) and (11).…”

Section: Simulation Results Of the 2nd Images Skin Diseases Using Fnn...mentioning

confidence: 91%

See 1 more Smart Citation

Training Artificial Neural Network Using Back-Propagation & Particle Swarm Optimization for Image Skin Diseases

A. R. Akkar,

Abass Salman

2011

ETJ

View full text Add to dashboard Cite

This work is devoted to compression Image Skin Diseases by using Discrete Wavelet Transform (DWT) and training Feed-Forward Neural Networks (FFNN) by using Particle Swarm Optimization(PSO) and compares it with Back-Propagation (BP) neural networks in terms of convergence rate and accuracy of results .The comparison between the two techniques will be mentioned. A MATLAB 6.5 program is used in simulation. The structure Artificial Neural Network (ANN) of training image skin diseases is proposed as follows: 1-The proposed structure of NN that performs three compressions Images Skin training by BP algorithms with log sigmoid activation function, and three neurons in output layer. 2-The proposed structure of FFNN using PSO that performs three compressions Images Skin with hardlim activation function, and three neurons in output layer. The results obtained using PSO are compared to those obtained using BP. Learning iterations (602-4700 epoch), convergence time (1sec.-100 sec.), number of initial weights (1set -75set), number of derivatives (0 -38 derivatives) and accuracy (60% -100%) are used as performance measurements. The obtained Mean Square Error (MSE) is 7 10 − to check the performance of algorithms. The results of the proposed neural networks performed indicate that PSO can be a superior training algorithm for neural networks, which is consistent with other research in the area.

show abstract

Section: Simulation Results Of the 2nd Images Skin Diseases Using Fnn...mentioning

confidence: 91%

“…During the past few years PSO has been shown successful for many applications [10][11][12] several papers discuss how to apply PSO in training NNs and their advantages [13][14][15].…”

Section: Particle Swarm Optimizationmentioning

confidence: 99%

Training Artificial Neural Network Using Back-Propagation & Particle Swarm Optimization for Image Skin Diseases

A. R. Akkar,

Abass Salman

2011

ETJ

View full text Add to dashboard Cite

show abstract

“…The main cycle stops when the termination condition is reached, and the algorithm return the solution. Considering the use of PSO in the problem of portfolio optimization, as is the case of this work, we can find these applications also in [16,21,45,46,53,[55][56][57]; most of these applications belong to the economy domain. The classic portfolio problem in economy is used to determine what are the best investment options on the stock exchanges.…”

Section: Swarm Intelligence Metaheuristicsmentioning

confidence: 99%

Portfolio optimization of electricity markets participation using forecasting error in risk formulation

Faia

Pinto

Vale

et al. 2021

International Journal of Electrical Power & Energy Systems

View full text Add to dashboard Cite

“…The risk definition in the Sharpe ratio is based on the MPT, which uses the variance and covariance to calculate the risk between two stocks in the portfolio. Many studies [8]- [14] have used the Sharpe ratio to assess portfolio performance. However, the Sharpe ratio only calculates the risk between two stocks in the portfolio, thus, when the portfolio contains more than two stocks, the Sharpe ratio cannot completely consider the portfolio risk.…”

Section: Related Studiesmentioning

confidence: 99%

Using Trend Ratio and GNQTS to Assess Portfolio Performance in the U.S. Stock Market

et al. 2021

View full text Add to dashboard Cite

Stock selection is an important issue in the stock market, and when assessing portfolio performance, return and risk are important conditions. The Sharpe ratio is a well-known assessment strategy that simultaneously considers portfolio return and risk. However, as the Sharpe ratio uses the average line to assess portfolio risk, it can easily assess a portfolio with stable uptrend as high risk, thus, this paper uses the trend ratio to address this problem. The trend ratio can assess a stable uptrend portfolio with low risk and identify a portfolio that has a higher daily expected return per unit daily risk. As the solution space in stock solution is huge, it is hard to use brute-force method to exhaust selections within a limited time. Thus, this paper uses the Global-best guided Quantum-inspired Tabu Search algorithm with Not-gate (GNQTS) to effectively optimize a portfolio given limited time. In addition, this paper uses 13 different kinds of sliding windows to train and test data, and identify a suitable period with a high trend ratio. The experimental results show that the proposed method can identify a portfolio with stable uptrend in the U.S. stock market. This paper does not exclude any stocks in the solution space; therefore, our method can comprehensively consider all the possible combinations of a portfolio. Moreover, we find some interesting phenomenon: the best single stock may not be contained in a portfolio and the stock with negative return cannot be excluded in the solution space. In addition, this study compares our portfolio performance with the portfolio guided by the Sharpe ratio; according to the experimental results, a portfolio guided by the trend ratio has more stable uptrend and lower risk than the Sharpe ratio. Thus, our method can outperform other assessment strategies.INDEX TERMS Stock selection, portfolio optimization, metaheuristic algorithm, trend ratio, quantuminspired tabu Search algorithm (QTS), the U.S. Stock Market.

show abstract

Implementation of particle swarm optimization in construction of optimal risky portfolios

Cited by 23 publications

References 10 publications

Training Artificial Neural Network Using Back-Propagation & Particle Swarm Optimization for Image Skin Diseases

Training Artificial Neural Network Using Back-Propagation & Particle Swarm Optimization for Image Skin Diseases

Portfolio optimization of electricity markets participation using forecasting error in risk formulation

Using Trend Ratio and GNQTS to Assess Portfolio Performance in the U.S. Stock Market

Contact Info

Product

Resources

About