Journal of
Marketing Development and Competitiveness






Scholar Gateway


Abstracts prior to volume 5(1) have been archived!

Issue 5(1), October 2010 -- Paper Abstracts
Girard  (p. 9-22)
Cooper (p. 23-32)
Kunz-Osborne (p. 33-41)
Coulmas-Law (p.42-46)
Stasio (p. 47-56)
Albert-Valette-Florence (p.57-63)
Zhang-Rauch (p. 64-70)
Alam-Yasin (p. 71-78)
Mattare-Monahan-Shah (p. 79-94)
Nonis-Hudson-Hunt (p. 95-106)



JOURNAL OF ACCOUNTING AND FINANCE

Quantum Particle Swarm Optimization for Short-Team Portfolios


Author(s): Moustafa Abuelfadl

Citation: Moustafa Abuelfadl, (2017) "Quantum Particle Swarm Optimization for Short-Team Portfolios",  Journal of Accounting and Finance, Vol. 17, ss. 8, pp. 121-137

Article Type: Research paper

Publisher: North American Business Press

Abstract:

This study examines proprietary transaction data for 2,726 accounts and 256,674 roundtrip transactions from November 2004 to January 2015. This study finds that the average individual investor in this sampleearns $23.87 per trade. The results show that individual investors exhibit the disposition effect in their trades. Additionally, the study uses the Quantum Particle Swarm Optimization (QPSO) to form optimal short-term portfolios using individual investors trading data as the training points for the QPSO algorithm.

The results show that QPSO yields better in sample optimized portfolios with respects to measures of risk and return than do optimized portfolios using Markowitz or Genetic Algorithm techniques (GA). The results also show that using individual investors trading data as the training points for the QPSO algorithm, yield more superior out of sample optimized portfolios than using historical data as the training points for QPSO. The optimization is carried out by minimizing these three risk measures Variance, Value at Risk (VaR) and the Conditional Value at Risk (CVaR) for the portfolios.