Journal of System Management(JSM)

Accurate stock market prediction can assist in an efficient portfolio and risk management. However, accurately predicting stock price trends still is an elusive goal, not only because the stock market is affected by policies, market environment, and market sentiment, but also because stock price data is inherently complex, noisy, and nonlinear. Recently, the rapid development of deep learning can make the classifiers more robust, which can be used to solve nonlinear problems. This study proposes a hybrid framework using Long Short-Term Memory, Autoencoder, and Deep Neural Networks (LSTM-AE-DNNs). Specifically, LSTM-AE is responsible for extracting relevant features, and in order to predict price movement, the features are fed into two deep learning models based on a recurrent neural network (RNN) and multilayer perceptron (MLP). The dataset used for this is Dow Jones daily stock for 2008-2018, which was used in this article. Besides, to further assess the prediction performance of the proposed model, original stock features are fed to the single RNN and MLP models. The results showed that the proposed model gives the more accurate and best results compared to another. In particular, LSTM-AE+RNN shows a better performance than the LSTM-AE+MLP. In addition, hybrid models show better performance compared to a single DNN fed with the all-stock features directly.

Innovation capability refers to a complete set of characteristics of the organization that facilitates innovation strategies, and the food industry plays a pivotal role in the processing of agricultural raw materials and food supply. The aim of the present study was to Identify and Analyze of the dimensions of innovation capability, clustering and ranking indexes in Urmia food industries. The sample size of the statistical population encompassing 221 companies was equal to 143 according to Cochran's formula. Obtaining required information was based on field study method. In the applied part of the study, exploratory factor analysis, clustering with K-MEANS algorithm and cluster ranking based on AHP technique were used. The results of the exploratory factor analysis showed that the relationship of each item with the factors classified into three categories was properly expressed. Companies with similar features but different from other clusters were put into 8 clusters. Finally, according to the weights of study variables, "human", "operability" and "structural” factors ranked first, second and last respectively.

Planning for economic sections and industrial activities at a regional level requires a proper understanding of a region’s potentials. The present study applies product space theory, network science, and information on Iranian provincial production structure to outline a roadmap for industrial development of Kermanshah. Analysis of mean value added and population of Iranian provinces in 2014 to 2018 indicated that of the 32 activities examined, Kermanshah has a revealed comparative advantage in five areas (agriculture and horticulture, traditional husbandry, apiculture, sericulture, and hunting) and other agricultural areas, forestry, and chemicals, with latent comparative advantage in 11 areas, and no advantage in 16 areas. Next, greedy, majority, high degree, and low degree strategies were combined with Borda’s and Copeland’s approaches to identify 11 activities for activation prioritized as follows: poultry, fishing, food, base metal, machinery & equipment, wood industry, other non-metal minerals, pharmaceuticals, metals, appliances, and rubber and plastic products.

The arrangement of machines and how to move them is one of the most important issues in factories and production units, which always imposes a lot of costs on the collections. Although the arrangement of machines is done once over a long period of time, its effects are very widespread. Accordingly, it is necessary to pay more attention to the matter of arrangement. Today, cellular production is also one of the widespread production methods at the industrial level, which requires this precision. The current research aims to produce new arrangements by using artificial neural networks. The way of working is that by using the data related to the number of production parts, the production time of each part, and the group of parts under investigation, as well as the costs of the devices, this clustering is done in 3 modes of 4, 6, and 9. Performing this type of clustering has higher accuracy and speed than other methods, and the results may be somewhat different in each scenario and with each clustering time, which increases flexibility in selection.

Investing in stocks is fraught with long risks that make it tough to manage and predict the choices out there to the investor. Artificial Neural Network (ANN) is a popular method which also incorporates technical analysis for making predictions in financial markets. The purpose of this work is an applied study which is conducted using description based on testing as method. The discussion is established on analytical-computational methods. In this research, the documents and statistics of the Tehran Stock Exchange are used to obtain the desired variables. Descriptive statistics and inferential statistics, as well as Perceptron multi-layer neural networks are utilized to analyze the data of this research. The results of this research show the confirmation of the high prediction accuracy of the Tehran Stock Exchange index compared to other estimation methods by the presented model, which has the ability to predict the total index with less than 1.7% error.

Personality is one of the most important study structures in organizational behavior that can play an important role in predicting human behavior. To describe the differences in personality, emotional, and social behavior, researchers have proposed the theory of five personality factors, known as the Big Five. One of the decisions investors make is to allocate wealth to financial and non-financial assets. The importance of this decision is especially evident in financial assets due to their nature and the need for more knowledge and expertise in this field because the mistakes of investors in this regard can create many risks and challenges for them. The main purpose of this study is to explain the effect of personality traits and demographic features on the risk-taking behavior of investors in the Tehran Stock Exchange. The present research is applied research in terms of goals and descriptive-survey research from the method view. The statistical sample of this research includes 358 investors of the Tehran Stock Exchange during 2019 and 2020. Research data were collected based on Sivarjan's (2018) questionnaire. The results of data analysis using the structural equation modeling method indicate that personality traits including neuroticism, extraversion, openness, agreeableness, and conscientiousness have a positive and significant effect on risk-taking behavior. Still, demographic characteristics including gender, age, marital status, and education do not have a significant effect on risk-taking behavior.

The present study aimed to investigate the impact of organizational entrepreneurship on improving competitive advantage with the mediating role of innovation. The present study was applied in terms of aim, descriptive-survey in terms of data collection method, and quantitative in terms of type of data collected. The statistical population of the study included 75 executive managers of companies operating in the start-up digital industry. Using a convenience random sampling method and Cochran's formula, 63 people were considered as the sample size. Data were analyzed using Smart PLS software. The results obtained from path coefficients and significant coefficients showed that organizational entrepreneurship and competitive advantage have a significant and positive effect on the innovation of start-up digital industries. It was also concluded that organizational entrepreneurship has a positive and significant impact on competitive advantage. It was also found that competitive advantage could mediate the relationship between organizational entrepreneurship and innovation.

This study will seek to provide the best and most efficient ordering policies for different levels of the perishable food supply chain in order to maximize the overall profit of the chain, and minimize social and environmental damage. Our supply chain includes a four-level supply chain of suppliers, manufacturers, distributors and retailers. In addition to the components of perishable products, the dimensions of sustainable development have been fully investigated and taken into account in the entire chain. In this study, due to the main nature of perishable materials, the statistical population includes 9 dairy companies and 9 meat and protein companies, which in total 18 dairy, meat and protein companies in Fars province, Iran, were studied. Network Data Envelopment Analysis (DEA) was used to analyze the data and WinQsb was used to model and solve it. According to the results, the average efficiency of the supply chain of production and distribution of perishable products in the financial year studied by the research in the suppliers sector was equal to 0.9634. This average was equal to 0.9899 in the producers sector, 0.9903 in the distributors sector and 0.9707 in the retailers sector. Therefore, the average efficiency in the study shows that the most inefficiency problems of the studied companies are related to the supplier sector. Also, the overall average efficiency is equal to 0.9950.

The aim of the current research is to identify the futures of marketing in the banking industry with a focus on blockchain technology. The current research is applied in terms of direction and has a mixed methodology due to the use of qualitative and quantitative methods together. The theoretical population of the research was experts in banking marketing and digital financial technologies, especially blockchain, and the sampling method was done in a judgmental method. The sample size in this study was equal to 15 people. For data analysis, meta synthesis methods, Binominal's statistical test, developed Copras and root definitions tool were used. The tools of data collection in this research were interviews and questionnaires (expert evaluation and priority evaluation questionnaires). 47 drivers were extracted from meta synthesis and these drivers were classified into nine main drivers. The drivers of the research were screened in two stages using theory-based inference screening and Binominal's test, and 12 drivers were considered for prioritization using the Copras technique. The remaining drivers were evaluated using the Copras technique and three criteria of importance, degree of certainty and experts' expertise. The findings showed that the drivers of marketing researchers' interest in digital financial technologies and blockchain and the development of decentralized banking had the highest priority and were selected for scenario planning. Based on these two drivers, four scenarios of crypto bank, conservative banking, pioneer banking and traditional banking were developed. The research proposals were proposed based on the important drivers and the desired scenario (crypto bank).