Banks are collecting an unprecedentedly large amount of data about their customers from difference sources, considering their cyber, physical, social activities. The focus of this paper is to study the problem of information sharing and lower the communication overhead among different nodes for a specific data mining approach in distributed big data architectures. This problem can be abstracted as how to efficiently search under a specific cluster node topology. This paper proposes a new design rule for topologies including: 1) low coordination number; 2) high packing density; and 3) having a 3-D structure. According to this rule, a rhombic dodecahedron topology is proposed. A distributed banking big data mining framework based on the proposed topology is implemented. The experiments based on multioptimization benchmark functions show the excellent searching ability of the proposed topology; and a banking customer feature reduction prototype has been implemented to showcase the practicality of the data mining framework.
Bibliographical noteFunding Information:
Manuscript received January 31, 2019; revised April 12, 2019; accepted May 6, 2019. Date of publication June 19, 2019; date of current version October 7, 2019. This work was supported in part by the Fujian Fumin Foundation, in part by National Natural Science Foundation of China under Grant 61672170, in part by the Science and Technology Planning Project of Guangdong Province under Grant 2017A050501035, and in part by the Science and Technology Program of Guangzhou under Grant 201807010058. (Corresponding author: Hao Wang.) H. Wang is with the Department of Computer Science, Norwegian University of Science and Technology, 2815 Gjøvik, Norway (e-mail: firstname.lastname@example.org).
© 2014 IEEE.
- Cyber-physical-social systems
- financial big data
- rhombic dodecahedron
- swarm optimization