جستجوی مقالات مرتبط با کلیدواژه « شبکه های عصبی مصنوعی » در نشریات گروه « مدیریت »

The main sources of income and assets are important for any organization. With this view, companies have started to do more to maintain health. Since in many companies the cost of acquiring a new customer is much higher than actual customer satisfaction, customer churn has become the main area of evaluation for these companies. Client-facing companies, including those active in the technology industry, are facing a major challenge due to customer attrition. With the rapid development of the telecommunications industry, dropout prediction becomes one of the main activities in gaining a competitive advantage in the market. Predicting customer churn allows operators a period of time to remediate and implement a series of preventative measures before customers migrate to other operators. In this research, a decision support system for predicting and estimating the churn of customers of Kurdistan Telecommunication Company (with 52,900 subscribers) with different data-mining and machine methods (including simple linear regression (SLR), multiple linear regression (MLR). Polynomial regression. (PR), logistic regression, artificial neural networks, Adabust and random forest) are presented. The results of the evaluations carried out on the data set of the Kurdistan Province Telecommunication Company, the high performance of artificial neural network methods with 99.9% accuracy, Adabust with 99.9% accuracy, 100% accuracy and random forest It shows 100% with accuracy.

The aim of this research is to investigate the capability of artificial neural networks and machine learning algorithms, including Support Vector Machine and Random Forest, in predicting the information content of accounting profits before its announcement in accepted companies on the Tehran Stock Exchange during the period from 2015 to 2020. Daily data required for the research were collected using Rahnaward-e-Novin software, and a systematic random sampling method was used to select 88 companies. MATLAB was used for modeling artificial neural networks and machine learning algorithms, and Python code was employed to calculate abnormal returns in neural networks and machine learning algorithms. The information content of profits was measured through the test of the relationship between profits and abnormal returns, based on the model by Porti et al. (2018). The input variables for artificial neural networks and machine learning algorithms are technical indicators. Accuracy, precision, recall, and F-score metrics were used for performance evaluation. The results of predicting with three models of artificial neural networks, Support Vector Machine, and Random Forest showed that Support Vector Machine and Random Forest had higher accuracy than artificial neural networks in predicting buy, sell, and hold strategies, and only Support Vector Machine had the ability to predict the information content of profits among the three models.Originality / Value: Designing a predictive model for stock price movements in the next trading day using artificial neural networks, Support Vector Machine, and Random Forest as the main innovation of the research. The research findings can increase the speed of information dissemination to the market and attract it, which will reduce the impact of informational asymmetry and information-based trading and ultimately enhance market efficiency.

The increasing complexity of omnichannel retailing has necessitated retailers to redesign processes and forecasting methods and accept new approaches based on machine learning and artificial intelligence. Improving the accuracy of demand forecasting and managing customer needs from different channels due to reducing demand uncertainty are the most important challenges in omnichannel retailing that retailers should deal with. A better understanding of consumer behaviour patterns leads to more accurate demand forecasting, which in turn helps gain insight into transportation flows, improves distribution management, and enables better planning and execution of supply chain operations. This study aims to reduce the uncertainty of demand in omnichannel retailing by improving the accuracy of demand forecasting by considering customers buying behaviour through using machine learning methods.
Design/methodology/approach: In this study to forecast future sales based on customers buying behaviour, a cosmetics retailer’s historical data on the monthly sales from February 2020 to June 2022 is used. The ID of eight products has been selected to analyze the performance of proposed methods and the method that the company applied to forecast demand. Clustering has been implemented using the dynamic time-warping algorithm due to the unequal length of the products’ time series. Initially, the nonlinear autoregressive neural network (NAR) has been applied to the time series in each cluster and later, the nonlinear autoregressive neural network with exogenous input (NARX) has been applied to the time series. The performance of the methods has been evaluated by testing R-squared and all R-squared coefficients and root mean square error (RMSE) to analyze the accuracy measure.
The forecasting methods comparison, moving average (MA), the nonlinear autoregressive neural network (NAR), and the nonlinear autoregressive neural network with exogenous input (NARX) concerning testing R-squared coefficient, and also all R-squared and RMSE indicated that the nonlinear autoregressive neural network with exogenous input presented a good performance for all the products, so it confirmed that the application of the clustering to identification customers buying behaviour through the sales history of the products, integrated with artificial neural networks, to conduct demand forecasting, could be considered a good method for forecasting demand of omnichannel retailing supply chain products.
Practical implications: The proposed method of this study leads to uncertainty reduction in omnichannel retailing by understanding the buying behaviour of customers, identifying patterns and using its analysis in the processes and operations, and its integration with machine learning methods improves distribution management and provides better planning and implementation of supply chain operations. Managers can use the proposed method to accurately predict complex demand patterns in the retailing industry. Using business data in demand planning provides an extra advantage to managers to include important variables based on their judgments.
Social implications: Knowing the factors affecting the sale of a specific category of a product helps to effectively design promotions, advertising campaigns, the optimal combination of category displays and optimization of shelf space in retail stores. Also, accurate demand forecasts lead to better ordering policies, thus minimizing the cost of inventory management and optimal distribution and logistics planning to meet future demand.
Originality/value: The proposed method presents a predictive approach for an omnichannel retailing supply chain that leads to uncertainty reduction in omnichannel retailing by understanding the buying behaviour of customers, identifying patterns, and using its analysis in the processes and operations and its integration with machine learning methods to improve distribution management, and provides better planning and implementation of supply chain operations.

Entrepreneurship in small and medium-sized industries has always been of great importance, as it will play a key role in the employment of a country as well as boost economic growth and increase GDP. The purpose of the present study is to examine the factors that can make entrepreneurship successful in small and medium-sized industries and to suggest a way for industrial entrepreneurs to become more aware of this important economic field. This research is a case study of industrial entrepreneurs in Iran who obtained initial permission to establish a factory (establishment permit) between 2011 and 2014 and some of them managed to exploit the factory (%100 physical progress) And some others have failed. The raw data of 4580 cases of investor licenses were examined. In order to determine existing and determinant patterns of entrepreneurship success, using data mining concepts. The information is pre-processed for subsequent analyzes and by reducing some of the variables that had less impact on the results. Finally through specialized analyzes using neural networks, Multilayer perceptron, Rough set algorithm and decision tree, best rules were extracted and the results were analyzed in detail. Based on the results, factors such as Industrial background, education related to the industry, and being native entrepreneur can play an important role in the success of this entrepreneurship.

The goal of the dynamic facility layout problem is to find the best layout for facilities at a multi period planning horizon so that the total cost of material handling and relocating the facilities is minimized. One of the most important aspects of this issue is to consider the transporters and minimizing material handling time. This paper developed a bi-objective mathematical model which is able to simultaneously minimize the material handling costs between facilities and the cost of rearrangement facilities and material handling time. Due to probabilistic characteristic of the transporters, such as the time of handling operation and existence of the failure, calculating the time required to carry the material using analytical relationships is impossible.Therefore, this paper uses the simulation approach and artificial neural networks. In this approach, a lot of scenarios are generated by combining of variables. Each scenario shows the location of the facilities and how to perform transportation operations in each period. Then each of these scenarios is implemented through computer simulation and simulation results are considered as the response variable. Finally, using input and response variable, an artificial neural network is trained so that it can accurately estimate the time of carrying out the transportation operations. Given that the above problem is a NP-hard; this paper proposes a new Multi-Objective meta heuristic algorithm to optimize the problem and compares the performance of the proposed algorithm with existing algorithms in literature.

The aim of  this research is Identification of the effective factors on bankruptcy prediction of Iranian companies by findings of artificial neural network (ANN) system based on Multilayer Perceptron Approach (PS) , and providing an appropriate statistical model for estimating the bankruptcy of Iranian companies by using the findings of The ANN implementation. we seek to answer the following question: Are we able to design a valid statistical model by using findings of artificial neural network (ANN) system to predict the bankruptcy of Iranian companies? The statistical population in this study is all of listed companies in Tehran Stock Exchange. By considering the criteria and method of systematic deletion, 172 companies from this statistical society have been selected as the sample in this research from 1386 to 1395. In order to make statistical analyzes in this study, we used from  methods  such as artificial neural network system based on multilevel perceptron approach, binary logistic regression, and tests such as Akaic, Schwarz, Hanan Quinn and Z wang test. The results of the analysis of the research data show that the ANN system can identify of the factors affecting on  bankruptcy of Iranian companies in the year before bankruptcy by Precision equal 98%.

Prediction of supply and demand, is a crucial issue for supply chain partners. With the accurate forecasted supply and patterns that indicate the sizes and directions of future production flow, the government and suppliers can have a well-organized strategy and provide a better infrastructure for improving industrial sector.With the aim of developing accurate forecasting tool in steel industry, this study present a new optimized neural network, by combination of Extreme Learning Machine and genetic algorithm. We employed our model on a dataset for steel supply - demand in Iran from jul-2009 to jan2013 to estimating the performance. The results show that prediction accuracy and performance relatively better than other classical approaches, according to RMSE and MAPE evaluations. In our model. Based on statistical tests, our new model is better than other model in accuracy, so can be used in as a suitable forecasting tool in steel supply forecasting problems.

The purpose of this article is to present an approach based on simulation optimization for improving the performance of cellular manufacturing systems through optimizing operator allocation and job dispatching rules in each cell. In this study, we have considered stochastic parameters, machines’ breakdown and multiple products in order to consider the problem as close as possible to real-world situation. The presented approach is composed of Taguchi design of experiments, discrete event simulation, artificial neural networks, and data envelopment analysis. First, controllable and response variables are determined based on the objective of the study and expert judgment. Then, the design of experiments is used in order to develop experimental scenarios base on controllable variables. Furthermore, simulation is used to evaluate experimental scenarios and their related response variables. Then, in order to expand the experimental results to the whole feasible solution space, artificial neural networks is used. Finally, the optimum scenario is determined using data envelopment analysis. After determining the optimum scenario, it is compared to the present condition of the case and the improvements are determined. In order to evaluate the performance of the presented approach, a lathing factory which uses a cellular manufacturing system is considered as the case study. Due to the fact that the high volume of manufacturing systems around the world forms the cellular manufacturing system, optimization of these lines has been of great importance and so far have been studied by many researchers in this regard. Most researchers have considered the problems in simple terms and ignored many of the assumptions. They have been optimized cellular manufacturing line problems by using mathematical modellings and meta-heuristic algorithms, but it should be noted that assumptions such as the uncertainty of problem parameters, machines’ breakdown and variable demand are among the existing and dominant conditions in cellular manufacturing problems, which, by taking them, can bring the problem as close as possible to real-world conditions, and, on the other hand, research results become more practical. Because of the complicated nature of such problems, mathematical modelling will not be efficient and useful. In this situation, simulation is one of the best approaches at hand. By using simulation modelling, it is possible to consider all parameters of the problem, stochastic, which make the model much closer to reality. The purpose of this study is to present an approach for optimizing operator allocation and job dispatching rules on machines in a cellular manufacturing ambience, in order to minimize delay costs per piece and maximizing the average efficiency of machines. Since the model of this study is seeking multiple objectives, the simulation model of the problem includes several responses. In the end, the operator's optimum number for allocation to each cell and the optimal job dispatching rules in each cell will be determined with the aim of achieving the objectives of the problem. Azadeh et al. used fuzzy data envelopment analysis (FDEA) and computer simulation to optimize operator allocation in a cellular manufacturing system. They indicated the effectiveness and superiority of the method through a practical case study (Azadeh et al., 2010)(Azadeh, 2010 #9;Azadeh, 2010 #9). Besides, an approach for multi-response optimization problem by using artificial neural network (ANN) and data envelopment analysis (DEA) is studied by Bashiri et al., (2013). Studies have been done so far show that optimal operator allocation along with the optimal job dispatching rules in the cellular manufacturing system has not been performed in the stochastic conditions, and from this point of view, the present study is unique. This section describes the proposed methodology which is illustrated in Figure 1 In the present study, the cellular manufacturing system was first evaluated and the data needed to simulate the system were collected. After the initial simulation of the manufacturing system in ARENA simulation software, controllable variables were determined according to the features of the manufacturing system. Then, using Taguchi’s experimental design method in Minitab software, experimental scenarios were designed by various combinations of controllable variables. Then, the simulation model was modified and simulated according to any experimental scenario, and the problem response variables, that were the same problem objective functions, were extracted. After extracting the results of the experimental scenarios, considering that without evaluating other not tested scenarios, it is impossible to identify the optimum scenario, by using artificial neural networks, the experimental results were expanded to the entire possible modes. For this purpose, data on experimental scenarios with their results were placed as training data in the neural network. After setting the parameter, the optimal neural network was identified. Table (1) shows that the network number 7 with 6.8% error is chosen as the optimal structure of the neural network.

The purpose of this study is to investigate the effect of relative efficiency of companies on value creation in the automotive industry accepted in Tehran Stock Exchange. The data were extracted from the financial statements of selected companies during in the 2013-2017. Initially, with the implementation of the DEA model with a native model, the relative efficiency is determined for each company. Then the strategic value creation of the companies is measured by the average of the factors such as return on equity, Q Tobin ratio, return on investment, and wealth creation for shareholders. The neural network model used in this study is a multilayer perceptron with back propagation error training pattern. The results show that the implementation of the artificial neural network model in the automotive industry explains the strategic value of the companies to a satisfactory level through the relative efficiency index and other input variables. Although some of the companies are efficient, such as Rana Investments Co., Khawar Spring Co., Saipa Diesel, Bahman Group and Charkheshgar Co., But in recent years, the automotive industry has been inefficient. At the same time, companies in this industry have somehow been able to strategically create value for their shareholders and their owners.

  All kinds of word-of-mouth (WOM) communication are not created in the same way, and their effects vary depending on several factors, such as resource, recipient, message, and status features. Accordingly, for the purpose of effective use of social networks, it is not enough to create a positive WOM relationship but it is important to take into account the conditions and factors through which the users of such communications accept and communicate it with others. Although researchers have been studying WPM communication in various online platforms, including online consumer surveys as well as from a variety of perspectives including marketing and psychology, there is little research on word of mouth communication in the field of social networking. The investigation in the present study shows that there is no research (local and international) investigating social network users based on social incentives affecting participation in WOM communication so far. This research can be considered as the first to deal with the partitioning of social network users based on the motivations of participation in oral communication. The main objective of this research is to identify the social motivations affecting the participation of consumers in advertising campaigns on social networks, the segmentation of users from this perspective, and ultimately providing marketing strategies tailored to each sector.

This research is applied in terms of purpose and descriptive-exploratory in terms of implementation. The data were collected distributing the on-line link to the questionnaire to more than 385 social network users selected based on available sampling method. In order to analyze the data and to partition social network users, self-organizing maps based on artificial neural networks have been used.

Based on the findings, social network users were divided into three sections with different demographic, behavioral and social motivations affecting WOM behaviors. These three sections were titled "Low Active Social Stimulus", "Active Social Stimulus" and "Social Inactivity Stimulus". The first section is applied to users who spend a fair amount of time on social networks, but have less social motivation to engage in word of mouth behaviors. The second section is applied to young people who devote most of their time to social networking activities and are highly motivated. And the third category is applied to those who are motivated enough but devote very little time to working on social networks.

Managers and advertising activists in social networks should consider word of mouth communication as an important part of social interactions. Although the content of WOM messages is often related to brands, the fact is that these types of communications are more likely to be influenced and published by the various incentives of consumer. This kind of behavior suggests that communication strategies should develop to the point where consumers' incentives to engage in oral communication in social networks can be identified and thereby their likelihood of purchasing can be increased. In the first group, it is recommended that marketers take into consideration the incentives that affect this sector and activate them based on the relative great magnitude of this sector compared to other sectors. In the second group, marketers are advised to consider this sector as a motivated sector for communication and encouraging them to have WOM communication. Hence, those who want to advertise their products on social networks should know that this section of social networking users are willing to receive oral messages and that they should provide the product information in a comprehensive and detailed manner so that they can further explore them by sharing it with experts. In the third group, marketers should invite them to engage in oral communication through communicating with individuals with similar beliefs, behaviors and intellectual flow. The members of this section are buying the products that others have verified. Hence, using well-known individuals to advertise their products can be used as one of the appropriate ways to promote products and brands for this section.

Since the improvement of human resource efficiency can play an effective role in the efficiency of organizations, it has always been one of the main research topics.The tendency to leave the organization is one of the factors affecting the efficiency of human capital, which can be predicted using in-data models, conditions governing the organization and the factors affecting it. For this purpose, intelligent algorithms based on neural network and multi-objective genetic algorithm have been used in this research to predict the tendency to leave an organization. In this regard, a standard dataset was created based on a questionnaire of employees satisfaction and the desire to leave the job in the Karoon Oil and Gas Production Company. Then, using an artificial neural network as a classifier and a multi-objective genetic algorithm, the important factors or features were selected. In the next step, an expert system was proposed to select effective features. In order to test and evaluate the neural network algorithm developed with the standard data set, the necessary training was provided. The results showed that by using the proposed model, not only the willingness of employees to leave the organization can be predicted with more than 88% accuracy, but also, the key factors of leaving the organization can be determined.

In today's competitive world, attention to the improvement and development of employees has become increasingly important. One of the procedures that organizations can use to improve their employees is implementation of assessment and development centers. But it should be noted that the implementation of improvement programs for each participants in the assessment center is time-consuming and costly. Accordingly, the aim of this study is reducing costs of assessment center implementation by segmenting the participants in assessment center and providing improvement programs for each sector. Sampling method is targeted and based on criteria and the sample consists of 75 employees. In this research, self-organizing maps have been used for segmentation of employees and the data were analyzed by Viscovery Profiler software. According to the findings, four sectors identified in the assessment center and they have been named: Talented, improvable employee (with a focus on competence), improvable employee (with focus on character) and insusceptible experts. Results of this segmentation can be used in five areas, including training, promotion, solve organizational challenges, recruitment and retention policies and rewards. Based on the results, for the areas that identified in the assessment center, suggestions are offered.

The use of revenue management models has been increased in various industries. The cause of such increasing is as a result of performance and profitability of these models in businesses. Hoteling industry is considered as an important business in the field of revenue management that has a reservation process and stochastic variables due to it. Classic overbooking model is considered as a common model in revenue management that causes to make a trade-off between the number of present customers and no-show customers. This model makes a situation for studying the functions which describe costumers’ presence distribution in probable form and then we can add some customers to system for increasing revenue due to no-shows. In this research, the binomial probability distribution using in overbooking model has been improved and estimated its probable parameter more accurately using artificial neural network as a tool in no-show estimation. This estimation is caused by fitting to effective indexes in show-up or no-show process using one-layer or multi-layer perceptron neural network. Therefore, a dynamic model for each sale and customers’ reservation is represented that it can estimate the probability parameter of customers’ show-up or no-show considering effective indexes.

Today evaluation of customers to classify the quality of providing services is one of the main challenges of Decision-Makers in different organizations. It is difficult to respond to all customers’ demands because of Increasing Volume of Them. On the other hand, in current competitive markets, customers are considered as capital of organizations. This issue results in purposefully study on different groups of customers in competitive markets. One of the effective ways to study the customers and provide the optimism service to them is grouping the market and clustering the customers. In this Research First customers classified in appropriate clusters using neural network techniques SOM in order to provide purposefully service , so each customer can deliver proper service according to its cluster. Then by the proposed model in the paper the membership of each client in the appropriate cluster can be predicted by using DEA-DA technique. This model has provided dynamic clustering process for organizations so that by which new customers will be assessed at any moment and their proper cluster is determined with rasonable accuracy.

Nowadays، marketing is as a key unit in any business. It isn’t covert for every one that customer is the most important assets of commercial organization، one of tools in creation of long relation with customer is; using of relationship marketing، but in spite of severe competition between commercial organizations; this strategy isn’t sufficient. In this research، we have been examined the effect of relationship marketing by combining of Experiential marketing and cause marketing on customer loyalty. The research is in descriptive study form; that it is done with survey measurement method. Statistical sample of research include 321 persons of west Azarbaijan province bank customers. For data analyzing we used artificial neural networks، multiple regression and Pearson correlation test. Multilayer neural networks have been trained by hyperbolic tangent function and they used by forward algorithm recognition model construct. Results showed that; in public and private banks; Experiential marketing، confidence and commitment have positive and meaningful effect on customer loyalty. By results comparison it is distinguished that neural networks are accurately than statistics traditional tests and they are reliable.

The delay in the supply of gasoil has wide Consequences of political, social and economic. Therefore, the gasoil demand forecasting is very important. The use of artificial neural networks in forecasting has many applications. Appropriate design of ANN parameters enhances performance and accuracy of the neuralnetwork model. Trial and error method is used to setting the ANN parameters in the most of studies. Trial and error method is not a reliable solution to achieve the best ANN structure. In the present study, the optimum structure of ANN to forecasting the demand of gasoil in the province of Hormozgan determined by Taguchi experimental design method. Analysis of variance (ANOVA) of the ANN parameters indicates that contribution of the number of neurons in first hidden layer to the changes in the network mean square error (MSE) is about 41% and contribution of the learning algorithm is about 27%. 
Also, the results of this study show that artificial neural networks are designed using Taguchi experimental design method have better performance than other Networks.

In recent years, the existing competitions between investment companies have been increased largely by entering private investors in capital market. Large and powerful companies try to achieve the goals predicted to increase the competition capacity. To analyze the efficiency of investment companies, parametric and non-parametric methods are used. In this research, based on the dissociation power and sensitivity of outliers efficiency frontier in DEA, the efficiency of 31 investment companies listed in Tehran Stock Exchange are evaluated by DEA models and neural network integrated model as 2 non-parametric methods during 2009-2011. Due o the weakness of DEA in ranking efficient units, these units will be ranked by Anderson and Peterson method. In DEA neural network integrated approach, multi-layer perspetron network by LM two training algorithm are used. When comparing the results of integrated model and DEA, the power of neural network will be represented for evaluating the efficiency.

Absence from work is an important challenge for industries and organizations. This costly problem of the organizations has caused managers to think of ways to decrease it. The first step in decreasing the cost of absence relates to identification of the factors affecting absence. The present research، which is the first one using approximate nonlinear functions of neural network approach، presents an appropriate model for predicting the amount of absence and factors affecting it. To do so، 14 effective factors were identified as input parameters، and then the amount of absence was predicted by multilayer perceptron model، through which the manager can decrease the amount of absence. Afterwards، using sensitivity analysis، the effect of each of the input parameters on the outputs of this model was analyzed. The final results indicated that the parameters of organizational commitment and job diversity were mostly effective on absence