The comparison of neural network, ANFIS and AR model in expected return prediction and comparison of memetic and symbiotic organism search in constrained portfolio optimization

In this paper, Symbiotic organism search and memetic algorithms are used to solve constrained mean-semi variance portfolio problem. Then AR model, Neural network and ANFIS are compared to predict expected return of stocks. 23 active stocks from June 22, 2014 to Jan 21, 2016 are used as our sample. The results indicate that, memetic algorithm despite its longer time consuming has better performance than SOS algorithm. And ANFIS has more accurate prediction than others in predicting expected rate of return. Finally, we compare expected and real efficient frontier, the results indicate that, in lower risk, ANFIS has better prediction accuracy. So in that area, we can allocate our asset with higher certainty.