Memetic algorithm for real estate portfolio based on risk preference coefficient

Optimization of real estate portfolio is to select two or more different types of real estate for investment, and the previous models based on expected return-variance cannot meet the needs of the investor´s. Furthermore, the investor changes their risk preference with the risk level. In this study, firstly, the real estate investment portfolio semi-variance model based on risk preference coefficient is constructed. The return per unit of risk is the key factor to determine an investment decision. Secondly memetic algorithm has been employed to solve the constructed model. Finally, a real-world case study is carried out to verify the performance of memetic algorithm, and indicates that memetic algorithm approach can generate better solution than GA. The memetic algorithm approach can be regarded as a useful approach for solving real estate portfolio problem.