نوع مقاله : مقاله پژوهشی
عنوان مقاله English
نویسندگان English
Due to the dynamic trend of stock prices and the volatile nature of the market, asset price forecasting plays a key role in creating an efficient strategy, and the results of price forecasting are a prerequisite for creating an optimal stock portfolio. The purpose of this study is to provide a hybrid model to help investors in selecting the optimal portfolio. Therefore, ten top industries have been selected among the active industries of the Tehran Stock Exchange using IAHP method, Then, the stock price of companies listed on the Tehran Stock Exchange from 2016 to 2021 are forecast at the considered time horizons using LSTM. In the next step, three portfolios with different time horizons are selected by using the CoCoSo method, and finally, optimal weights have been determined and an efficient frontier has been drawn using Mixed-Integer Quadratic Program and Branch and Cut Algorithm based on LAM Model. According to the results of this research, the proposed model gives higher returns to investors due to the risk of constituting portfolios with specified time horizons in contrast to traditional approaches
کلیدواژهها English
Freitas, F. D., De Souza, A. F., & de Almeida, A. R. (2009). Prediction-based 12. portfolio optimization model using neural networks. Neurocomputing, 72(10), 2155-2170.