A Series-based group stock portfolio optimization approach using the grouping genetic algorithm with symbolic aggregate Approximations

摘要: Stock portfolio optimization is both an attractive research topic and a complex problem due to the rapidly changing economy. Based on techniques, many algorithms have been proposed mine different portfolios. In previous approach, group stock (GSP) was derived based investors' objective subjective requests by grouping genetic algorithm. Stocks were divided into groups, with those in same being similar. The benefit of using GSP that investors can replace any they do not like substitute stocks group. To increase similarity price series are taken consideration, enhanced approach derive series-based be used provide more actionable portfolios making decisions. chromosome representation, grouping, parts represent as did approach. return GSP, stability factor designed cash dividends, unit balances utilized well. Because dimension high, symbolic aggregate approximation (SAX) extended (ESAX) selected transform data points symbols. Then, distance presented evaluate groups GSP. By new factors existing two fitness functions developed quality chromosomes. Experiments real-world dataset conducted show merits SAX ESAX. results investment (ROI) approximately 16% 18% better than ROI obtained However, ESAX achieves does SAX.