A Novel Particle Swarm Algorithm for Online Trading Customer Classification

Abstract:

Particle swarm algorithm is an efficient evolutionary computation method and wildly used in various disciplines. But as a random global search algorithm, particle swarm algorithm easily falls into the local optimal solution for its rapid propagation in populations and in order to overcome these shortcomings, a novel particle swarm algorithm is presented and used in classifying online trading customers. The corresponding improvements include improving the speed update formula of particles and improving the balance between the development and detection capability of original algorithm and redesigning the calculation flow of the improved algorithm. Finally after designing 21 customer classification indicators, the improved algorithm is realized for customer classification of a certain E-commerce enterprise and experimental results show that the algorithm can improve classification accuracy and decreases the square errors.

• Periodical: Applied Mechanics and Materials (Volumes 644-650)
• Pages: 2181-2184
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.644-650.2181
• Online since: September 2014
• Authors: Chen Chen*
• Keywords: Customer Classification, Detection Capability, Particle Swarm Algorithm, Update Speed

References

[1] Z. H. Zhang, S. K. Lv, Study on model of customer classification based on the customer value, J. Mana. Sci. 23 (2013) 64-71.

[2] P. S. Bradly, Application of particle swarm optimization algorithm, J. Glob. Opti., Commun. 16 (2012) 23-32.

[3] K. L. Managasarian, An improved particle swarm algorithm and its application, J. Comp. Simu. 77 (2010) 659-671.

[4] G. H. Amander, K. S. Drogger, Application of particle swarm algorithm based on commercial bank customer subdivision, J. Comp. Engin. 32 (2011) 668-679.

[5] Y. F. Zhang, L. J. Mao, An improved K-means Algorithm, J. Comp. 36 (2010) 87-94.

[6] W. B. Deng, Improvement and application of BP Algorithm, J. Soft. 27 (2011) 89-97.