Optimizing Long-Term Bank Financial Products Portfolio Problems with a Multiobjective Evolutionary Approach

• Main Authors: Jian Xiong, Chao Zhang, Gang Kou, Rui Wang, Hisao Ishibuchi, Fawaz E. Alsaadi
• Format: Article
• Language: English
• Published: Hindawi-Wiley 2020-01-01
• Series: Complexity
• Online Access: http://dx.doi.org/10.1155/2020/3106097

With the development of economy, the requirement of financial planning for individuals or families is emerging. In the era of the Internet, individual investors can conveniently enter the market and purchase financial products. Traditional portfolio management models focus on risky markets such as stock markets. However, risk-averse investors, such as normal families, may concern appropriate long-term financial planning. This paper considers the problem of portfolio management of bank financial products with a long-term planning horizon. By taking into account the final return and the flexibility, a multiobjective model of long-term portfolio is proposed. A multiobjective evolutionary approach is employed for the handling of conflicting objectives. Test instances are generated to illustrate the problem. Experiment results show that the presented algorithm can efficiently find trade-off solutions. Our experimental results also show that crossover probabilities should be separately implemented for long-term portfolio problems with hybrid encoding. Performance comparison of different crossover operators suggest that, for a real-valued encoding part, the simulated binary crossover (SBX) has a better performance than BLX- operator. While for a binary encoding part, a uniform crossover operator might be appropriate for large-scale instances. The proposed multiobjective model in this paper provides risk-averse investors with an appropriate decision support model for the long-term financial planning and management.