ANALYSIS OF STOCK PORTFOLIO OPTIMIZATION USING THE COMBINATION OF GENETIC ALGORITHM AND SIMULATED ANNEALING METHODS WITH THE PERFORMANCE COMPARISON OF PORTFOLIO TOWARDS EQUITY FUNDS (CASE STUDIES OF LQ45 INDEX AND JII)

• Main Author: Rizki Utami, Adela
• Format: Final Project
• Language: Indonesia
• Subjects: Fisika
• Online Access: https://digilib.itb.ac.id/gdl/view/47444
• Institution: Institut Teknologi Bandung

Stock investment is a type of investment that is popular among investors related to the return value it offers. A portfolio in stock investment is a collection of several stocks with varying degrees of return and risk. This study aims to form an optimal stock portfolio whose risk level will be expressed as a Value at Risk (VaR) value. The stocks used are listed in the LQ45 index and JII from January 2015 to December 2019 period. The Markowitz model is chosen in this study due to its application to the diversification principle. To optimize the weight of selected stock, the author used the combination of a genetic algorithm and simulated annealing method to provide a minimum VaR of the portfolio. The optimized conventional and sharia stock portfolio will be compared to the performance of several mutual fund products using the Sharpe ratio, Treynor ratio, and Jensen ratio. The equity fund data used are equity funds that have been active before 2015 until December 2019. A comparison of performance will be carried out for each year and a period of 5 years from 2015 to 2019. The result of the study shows that the conventional stock portfolio relatively has a better performance than sharia. The conventional stock portfolio also has a better performance compared to conventional equity funds, and the sharia stock portfolio has a better performance compared to sharia equity funds (RDSS). The RDS product with the best and most stable performance is SUCMAXI, while the best RDSS product is SUCORSE. Through this research, the author can conclude that the portfolio formed using the combined methods of genetic algorithms and simulated annealing can provide good optimization results.