首頁 > 網路資源 > 大同大學數位論文系統

Title page for etd-0910115-124515


URN etd-0910115-124515 Statistics This thesis had been viewed 765 times. Download 2 times.
Author Feng Hsueh
Author's Email Address No Public.
Department Information Management
Year 2014 Semester 2
Degree Master Type of Document Master's Thesis
Language zh-TW.Big5 Chinese Page Count 53
Title MapReduce-based Discrete Differential Evolution for Portfolio Optimization
Keyword
  • Differential evolution
  • MapReduce
  • Hadoop
  • Portfolio optimization
  • Portfolio optimization
  • Hadoop
  • MapReduce
  • Differential evolution
  • Abstract The portfolio optimization (PO) problem is a multi-objective combinatorial optimization which needs to consider expected return and risk at the same time. Thus it needs an efficient computing way to find optimal solutions. Differential Evolution is a meta-heuristic algorithm and can be applied to the PO problem for finding optimal solutions. When we think of the PO problem, the more choices of stocks are, the more complicated the problem is. Therefore, the computation time on a single machine surprisingly increases. The solution to this computational problem is to use Hadoop. MapReduce is a key component of Hadoop and can be applied to solving many optimization problems. This study proposes a discrete differential evolution algorithm for solving the PO problem, and the proposed algorithm is implemented by using the MapReduce framework run on multiple machines in order to obtain optimal solutions within a shorter time. Experimental results show that using the MapReduce framework to implement the discrete differential algorithm can solve larger PO problems more quickly than on a single machine.
    Advisor Committee
  • Yu-cheng Kao - advisor
  • Wen-Hwa Liao - co-chair
  • Yun-Chia Liang - co-chair
  • Files indicate in-campus access at one year and off-campus not accessible
    Date of Defense 2015-07-23 Date of Submission 2015-09-10


    Browse | Search All Available ETDs