درخت حوزه‌های تخصصی

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.

EXTENDED ABSTRACT INTRODUCTIONIn 2019, Iran is ranked sixth among world countries and fifth among Asian countries (including Russia) in terms of CO2 emissions. Therefore, studying the CO2 emission elasticity of the production sectors of this country is significant and important for energy and environmental policymakers. What factors influence changes in CO2 emission elasticities? Which are the stimulants and which are the inhibators? The answers to these questions are useful in reducing and controlling CO2 emissions. In the present study, CO2 emission elasticities of production sectors are calculated, and then, with the aim of identifying CO2 emission elasticity stimuli, the changes in CO2 emission elasticities are broken down into different components. The methodology of this research is based on Input-Output analysis and decomposition analysis. The novelty of this paper is to determine and calculate the components of changes in CO2 emission elasticities using SAD. Guo et al. (2018) have presented a method for calculating CO2 emission elasticities based on the Input-Output analysis.METHODOLOGY Aim of this paper is to investigate the factors affecting CO2 emission elasticities, CO2 emission demand elasticity and CO2 emission production elasticity. In the first step, the elasticities are calculated and in the second step, changes of elasticities are decomposed. In this study, we have used input-output tables published in 2001 and 2011 by the Statistics Center of Iran. Due to the differences in the sector classification of the input-output tables of 2001 and 2011, we match some production sectors and finally take into account the 65 unified sectors. In order to calculate the CO2 emission of each production sector, we first obtain the total consumption of each energy for each year from the Iranian energy balance sheet, and then we allocate each energy consumption to production sectors and single household sector, according to input-output tables and the share of production sectors and the share of the household sector.                                                                                                                                                                                                                                                                   FINDINGS Findings show that the "Electricity generation, transmission, and distribution" sector has the most elasticity. The "Ghosh inverse matrix" effect is a strong stimulus to the CO2 emission elasticity of the sectors. This result indicates that the change in the share of output i, which is sold to sector j as an intermediate input, is a strong stimulus to increase the elasticity of CO2 emissions. These changes can be due to increased economic activities and the inefficiency of production structure.   CONCLUSION "Electricity generation, transmission and distribution" sector should be considered by energy and environmental policy makers due to having the highest amount and changes in CO2 emission elasticity than other sectors. Increasing the share of renewable energy in the energy consumption basket of production sectors, increasing energy efficiency (reducing energy intensity) by replacing new and advanced equipment with old and worn equipment and improving production structure can help reduce the CO2 elasticity and CO2 emission in Iran's production sectors. Finally, due to the high of CO2 emission elasticities in the "Electricity generation, transmission and distribution" sector, future research can focus on this area and suggest solutions to increase production efficiency and energy efficiency. Also, future research can focus on the production structure of production sectors and provide solutions to improve the production structure of Iran's production sectors.