作者: Chun-Hao Chen , Cheng-Yu Lu , Chih-Hung Yu
DOI: 10.1109/NBIS.2015.44
关键词:
摘要: In this paper, symbolic aggregate approximation which is the well-known dimensionality reduction for time series utilized enhancing previous approach to mine more useful group stock portfolio by grouping genetic algorithm. Each chromosome consists of three part that are grouping, stock, and parts. Grouping parts represent how divide stocks into groups. Stock means purchased units. individual evaluated balance, satisfaction SAX distance. Experiments on a real data conducted show merits proposed approach.