Mehdi Rezaei; Najmeh Neshat; Abbasali Jafari Nodoushan; Amirmohammad Ahmadzadeh
Abstract
In this research, we investigated the interactive effects between the macroeconomic variables of currency, gold, and oil on two indicators of total and equal weighted indices considering the importance of correlation between economic variables and stock market indices. ...
Read More
In this research, we investigated the interactive effects between the macroeconomic variables of currency, gold, and oil on two indicators of total and equal weighted indices considering the importance of correlation between economic variables and stock market indices. In this regard, the analysis of Pearson correlation and regression coefficients have been used to investigate the existence of an interactive effect among them, and a Multi-Layer Perceptron Neural Network (MLP NN) model has been used to simulate this effect. The models have been fitted as a time series based on the daily data related to the economic variables and the mentioned indicators during march 2016 to that of 2021. Investigating the interactive effects between variables has been done using SPSS statistical software, and Artificial Neural Network (ANN) simulation developed in MATLAB programming environment. The extracted results indicate the existence of an interactive effect among these economic variables. The simulation results show the high ability of ANN in modeling and predicting the total price and equal-weighted indices, and this model has been able to make more accurate predictions by considering these interactive effects as well.
Maryam Moradi; Najme Neshat; Amir Mohammad Ahmadzade Semeskande
Abstract
Safe investment can be experienced by incorporating human experience and modern predicting science. Artificial Intelligence (AI) plays a vital role in reducing errors in this winning layout. This study aims at performance analysis of Deep Learning (DL) and Machine Learning (ML) methods in modellingand ...
Read More
Safe investment can be experienced by incorporating human experience and modern predicting science. Artificial Intelligence (AI) plays a vital role in reducing errors in this winning layout. This study aims at performance analysis of Deep Learning (DL) and Machine Learning (ML) methods in modellingand predicting the stock returns time series based on the return rate of previous periods and a set of exogenous variables. The data used includes the weekly data of the stock return index of 200 companies included in the Tehran Stock Exchange market from 2016 to 2021. Two Long Short-Term Memory (LSTM)and Deep Q-Network (DQN) models as DL processes and two Random Forest (RF) and Support Vector Machine (SVM) models as ML algorithms were selected. The results showed the superiority of DLalgorithms over ML, which can indicate the existence of strong dependence patterns in these time series, as well as relatively complex nonlinear relationships with uncertainty between the determinant variables. Meanwhile, LSTM with R-squared equals to 87 percent and the analysis of the results of five other evaluation models have shown the highest accuracy and the least error of prediction. On the other hand, the RF model results in the least prediction accuracy by including the highest amount of error.