Journal of Optimization in Industrial Engineering Vol.14, Issue 2, Summer & Autumn 2021, 73-81 DOI:10.22094/JOIE.2020.677889 73 Optimizing the Prediction Model of Stock Price in Pharmaceutical Companies Using Multiple Objective Particle Swarm Optimization Algorithm (MOPSO) Ali Khazaei a , Babak Hajikarimi a,* , Mohammad Mahdi Mozafari b a Department of Management Science,Abhar branch, Islamic Azad University, Abhar, Iran b Faculty of Social Science, Imam Khomeini International University,Qazvin,Iran Received 15 December 2019 ; Revised 17 September 2020 ; Accepted 15 November 2020 Abstract The purpose of the research was to optimize the prediction model of stock price in pharmaceutical companies using meta-heuristic algorithm. In this research, optimizing the stock portfolio has been done in two separate phases. The first phase is related to predicting the stock future price based on the past stock information, in which predicting the stock price was done using an artificial neural network. The neural network used in the research was Multilayer Perceptron (MLP) using the back propagation of error algorithm. After predicting the stock price with a neural network, the predicted price data was used to optimize the stock portfolio in the second phase. In the second phase, a multi-objective genetic algorithm was used to optimize the portfolio so the optimal weights are assigned to the stock and the optimal stock portfolio was developed. Having a regression model, the relevant genetic algorithm was designed using MATLAB software. The results showed that the stock portfolio developed by MOPSO algorithm has a better performance under all four risks criteria except the conditional value-at-risk criterion than the algorithms used in the compared article. In all models except the mean-conditional value-at-risk model, the stock portfolios developed by the MOPSO algorithm used in the research have more and more appropriate efficiency. In addition, the results showed that MOPSO algorithm is of good performance at developing and optimizing the stock portfolio and better than other algorithms. Therefore, it can be said that using meta- heuristic MOPSO algorithm used in the research is effective for optimizing stock portfolio. Keywords: Predicting the Price; Multiple Objective Particle Swarm Optimization Algorithm (MOPSO); Meta-Heuristic. 1.Introduction Financial markets have become one of the most popular areas of investment in the recent eras because of their unique characteristics such as no need for macro capital, transparency and low cost of transactions, and the absence of default risk (Chang, 2010). In fact, an important part of any country's economy is formed by investing in the stock exchange. Undoubtedly, most of the capital is exchanged through stock markets all over the world and the national economy is strongly influenced by the performance of the stock market. Therefore, we need to learn mechanism and behavior of these markets using different and useful tools. An investor must have a clear insight about the future of market in order to achieve maximum profitability (Bajelan et al., 2016). Predicting stock prices is one of the attractive and challenging tasks, which has attracted many researchers’ interest and involved many scientific disciplines (Zhang et al., 2018). Predicting trends and improving the predictive power is of great value for reducing risk (Basak et al., 2018). However, there are many ways for predicting nowadays, it is not easy to predict stock prices clearly and even predict the direction of prices (Zhang et al., 2018). The predictive power of different models varies in different systems (Basak et al., 2018). The trend of predicting prices in the stock market has been of interest to researchers for many years due to its complex and dynamic nature. It is also a very debatable task due to the ambiguities and variables affecting the change of market index on a certain day. Stock markets are sensitive to rapid changes so random fluctuations may be occurred in their prices. Due to high disorder and instability nature of stock behavior, investing in this market is going along with high risk. Thus, knowledge is needed to clearly predict stock price movements in the future in order to minimize these risks (Khaidem et al., 2016). Weapon-target assignment (WTA) is critical to operational command and directly affects the progression and outcome of operations. WTA is an important military problem studied by numerous military powers. The core concept of WTA is to rapidly and accurately assign weapons to targets and to obtain better solutions to satisfy operational goals (i.e., optimization objectives). These optimization objectives mainly include maximum combat effectiveness, minimum weapon consumption, minimum potential threat of target, minimum target surplus, and minimum incidental damage. According to the number of optimization objectives in the problem, WTA problems can be divided into single-objective WTA (SOWTA) problems, with only one optimization objective, and MOWTA problems, with at least two optimization objectives. Currently, research on the SOWTA problem is more in-depth, and respective *Corresponding author Email address: babakhajikarimi@abhariau.ac.ir