Mohammadreza Ghadimpour; Seyed babak Ebrahimi
Abstract
The ability to predict the stock market and analyze market trends is invaluable to researchers and anyone interested in investing. However, this task is a challenging problem due to a large number of parameters and unpredictable noise that may affect the stock price. To overcome this issue, researchers ...
Read More
The ability to predict the stock market and analyze market trends is invaluable to researchers and anyone interested in investing. However, this task is a challenging problem due to a large number of parameters and unpredictable noise that may affect the stock price. To overcome this issue, researchers have employed numerous approaches such as Moving Average (MA), Support Vector Machine (SVM), and Neural Networks. With technological advances, deep learning methods have become popular in processing time-series data. In this paper, we compare two recently introduced deep learning models, namely a Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), in forecasting daily movements of the Standard & Poor (S&P 500) index using the daily closing price of this index from 14/5/1991 to 14/5/2021. Results show that both models are effective and accurate in stock market prediction. In this case study, the mean squared error (MSE) and mean absolute error (MAE) for the GRU model are slightly lower than the LSTM model; hence, GRU outperformed the LSTM model despite its simpler structure. The results of this study are applicable in various instances where it is challenging to identify patterns among large volumes of unstructured data, such as medical data analysis, text mining, and financial time series modeling.
Seyed Babak Ebrahimi; Mostafa Abdollahi Moghadam; Nasser Safaie
Abstract
The primary purpose of investors is maximizing the utility that is characterized by two essential criteria include risk and return. Regarding investors' uncertainty about the future, one of the main ways to reduce risk is to diversify the investment portfolio. In this research, we proposed an index conducted ...
Read More
The primary purpose of investors is maximizing the utility that is characterized by two essential criteria include risk and return. Regarding investors' uncertainty about the future, one of the main ways to reduce risk is to diversify the investment portfolio. In this research, we proposed an index conducted by Euclidean distance for assessing portfolio diversity. Besides, we designed a multi-objective model to select optimal stock portfolios with considering value at risk (VaR), which is one of the critical indicators of unacceptable risk, portfolio Beta as systematic risk, and portfolio variance as unsystematic risk simultaneously. The model presented in this paper aims to maximize diversification while minimizing value at risk and stock risks. Furthermore, maximizing returns are considered as a limitation of this model. Since the proposed model is nonlinear and concerning computational complexity, it is NP-hard; therefore, we utilized the PSO and the GE metaheuristic algorithms that are improved for solving multi-objective problems to solve the model. The results of the model implementation in multiple iterations showed that the average yield of selected portfolios by the model is higher than the desirable condition. The evaluation of stock performance indicators also shows the satisfactory performance of the multi-objective model.