Optimizing the Prediction Model of Stock Price in Pharmaceutical Companies Using Multiple Objective Particle Swarm Optimization Algorithm (MOPSO)

The purpose of this study is to optimize the stock price forecasting model with meta-innovation method in pharmaceutical companies.In this research, stock portfolio optimization has been done in two separate phases.The first phase is related to forecasting stock futures based on past stock information, which is forecasting the stock price using artificial neural network.The neural network used was a multilayer perceptron network using the error propagation learning algorithm.After predicting the stock price with the neural network, the forecast price data in the second phase has been used to optimize the stock portfolio.In this phase, a multi-objective genetic algorithm is used to optimize the portfolio, and the optimal weights are assigned to the stock and the optimal stock portfolio is created.Having a regression model, the design of the relevant genetic algorithm has been done using MATLAB software.The results show that the stock portfolio created by MOPSO algorithm has a better performance compared to the algorithms used in the article under comparison under all four risk criteria except the criterion of conditional risk exposure. In all models, except the conditional risk-averaged value model, the stock portfolios created by the MOPSO algorithm used in the research have more and more appropriate performance.