clustering

The primary objective of mobile network operators is arguably to maximize their efficiency. Beyond operational and investment costs, maximizing the utilization of available resources can help them achieve this goal. To this end, operators offer discounted data plans during off-peak hours to encourage users to utilize the network during these times. These data plans are typically based on the average traffic load across the entire network at different times of the day. However, they often overlook the fact that traffic patterns can vary significantly across different population areas within a city at various times. In this paper, different population areas are automatically identified using clustering based on traffic patterns. By identifying these areas and considering the traffic patterns specific to each area, the allocation of appropriate data plans for users, based on the regions they frequent, is analyzed and discussed. Additionally, other potential applications of this clustering method for offering various services are presented, followed by a conclusion.

Clustering is one of the basic techniques in data mining and machine learning, which is used to divide a set of data into homogeneous subsets. There are different methods for clustering, each of which has its own strengths and weaknesses. One of the main challenges in clustering is finding the optimal number of clusters and optimal allocation of data to these clusters. Genetic algorithm, as an optimization method based on natural evolution, has a high ability to solve complex problems and search for large solution spaces and can be used as an effective tool in clustering. The purpose of this article is to investigate the efficiency and accuracy of genetic algorithm in data classification and compare it with traditional clustering methods for classification. In order to evaluate the performance of this algorithm, several insurance data sets are used and the obtained results are analyzed with different criteria such as accuracy. Also, different parameters of the genetic algorithm are examined and their effects on the final performance of the algorithm are studied in order to determine the most optimal settings for data classification.

In this research, to form chromosomes, at first, the number of clusters was determined. Considering that each cluster center had as many features as the number of features in the data set, the length of each chromosome was determined by multiplying the number of clusters by the number of features. New and diverse methods were used for Crossover, Mutation and Survival processes. Also, the evaluation criterion similar to the K-means algorithm was chosen to optimize the clustering performance. This innovative approach led to improving the accuracy and efficiency of the classification process.

By applying the method described in this article to three insurance data sets for fraud detection, we have interesting results with 12% improvement in F1 and 10% increase in accuracy in the first data set, 1% improvement in F1 and 1% improvement in accuracy in the first data set. Second and finally, 1% improvement in F1 and 2% improvement in the accuracy of the third data set compared to the K-means method and other methods have been achieved. Due to the 2-mode data in this data set, the problem is solved for two clusters using the algorithm and the best label for each cluster is selected according to the real labels of the data and the result is presented as the results of classification problems. Additionally, significant improvements in metrics such as ARI and other clustering evaluation criteria have been achieved, and remarkable progress has been made compared to the standard genetic algorithm.

Genetic Algorithm is able to solve complex problems without definite solution and can perform better in data clustering than traditional methods such as K-means. By combining probabilities and randomness, this approach provides the possibility to examine more points as cluster centers and improve clustering performance. The results show that this method works better than the famous methods in some cases and provides a suitable structure for data clustering.

The purpose of this study is to cluster the Iranian online shopping consumer market using artificial neural network, so that based on it, customers' needs can be better identified, the characteristics of each cluster can be determined more accurately, and the best clustering method can be chosen. And finally, the development of appropriate strategies for management, communication and better service to customers was achieved. Based on the purpose, the present research is descriptive and of the estimation and evaluation type, and in terms of practical purpose and in terms of time period, the situation of customers has been studied during the years 2021 to 2022. The statistical population included 52,403 online stores, and the present study selected 349 stores based on simple sampling. The method of analysis and classification of data is done by RFM, K-Means and self-organizing fuzzy-neural network. The technique used was the sum of squared error criteria and the Davies-Bouldin index. The findings showed: food items (they had the least delay in purchasing due to frequent needs); cosmetics (the majority of purchases were made by women); Luxury appliances (have the highest monetary value of purchase); industrial supplies and their accessories (the most purchases were made by men) and finally, sanitary supplies, detergents and clothes (have the most frequency of purchases). The results of the research have shown that the use of self-organizing neural networks along with the RFM method is the most suitable method for clustering and separating and valuing customers. Also, Kmeans+ANFIS also achieved good values, but the WRFM+ANFIS method has been more successful in this index.

Granting facilities is an important part of every bank's operations. This part of banking activities is economically important. With its operations, banks can provide the transfer of resources from those that have directly invested to those who need money, this repayment makes another people use these resources. Failure to repay facilities on time will cause the bank's resources to stagnate and in the long will cause the country's economic recession. It is important to monitor the correct allocation of resources because if bank resources are used and unfounded payments are made, the banks will not be able to pay the depositors and will become bankrupt. By examining the researches in the field of banking, it was found that most of the researches have focused on the optimal combination of the investment portfolio in the capital market, and less researchers have paid attention to the discussion of the optimal combination in the money market. Most of the researches that used operational and statistical research methods were related to industrial issues, and less in financial issues and operational research discussions were used. In the optimal portfolio of the combination of facilities or investments, mostly the genetic algorithm has been used and less than other fuzzy methods have been used in the conditions of uncertainty. Therefore, in this research, the improvement of facility payment modeling has been addressed by using convolutional neural networks and CNN-LSTM modeling.

The main goal of this research is to assess the readiness of countries for the Fourth Industrial Revolution. The study aims to provide a model using artificial intelligence algorithms, such as clustering and classification, to predict the movement of countries towards Industry 4.0.

The research utilizes fast-density clustering (FDC) to categorize countries into distinct clusters. Subsequently, the kNN and SVM algorithms are employed for modeling and predicting countries' movements. Additionally, swarm intelligence algorithms are used to optimize the performance of the algorithms.

One of the achievements of this research is the development of a composite index for the classification of countries and predicting their movement toward Industry 4.0. The countries are categorized into three clusters based on their readiness for the Fourth Industrial Revolution, and the characteristics and trends of each cluster are elucidated. Another finding is the optimization of the kNN and SVM algorithms, demonstrating their superior performance compared to other algorithms.

Originality: 

The proposed composite index outperforms similar algorithms, indicating the effectiveness of the proposed method in predicting countries' movement toward Industry 4.0. The study presented a comprehensive analysis of the Iran cluster, including its overall ranking and rankings within specific sub-indices. The findings offer insights into the strategic movement patterns of Iran and provide recommendations for advancing its technological capabilities. This research not only contributes to enhancing the country's readiness in technology but also aims to elevate the power and standing of the Islamic Republic of Iran, particularly in critical sectors such as national defense and security.

Using network data envelopment analysis (NDEA) models to assess the efficiency of Decision Making Units (DMUs) is a widely accepted method in academic research. An ongoing challenge in this field involves the computation and implementation of enhancement solutions within homogeneous clusters utilizing Machine Learning techniques. The primary aim of this paper is to identify the optimal clustering algorithm for a two-stage sustainable supply chain within the petrochemical industry in Iran. Subsequently, the application of NDEA within each cluster aims to ascertain efficiency levels and devise improvement strategies to facilitate a more targeted development approach for inefficient units. This paper investigates the best clustering algorithms in the area of Machine Learning by using quality measurement indicators and using Network Data Envelopment Analysis (NDEA) for measuring the efficiency of DMUs with sustainability approach. Upon examination, it has been determined that the Deep Embedded Clustering algorithm yields the most favorable results when applied to the data set. Furthermore, the comparison of the clustering result with the standard NDEA model has demonstrated the utility of clustering and comparing units in homogeneous categories for the purpose of efficiency calculation and determining the distance to the efficient frontier. This article, showed that how to find the best algorithm for two-stage supply chain clustering. Also, by comparing the effect of clustering on measuring the distance of inefficient units to the efficiency frontier, it was shown that clustering of units can play a significant role in planning to reach a practical development plan in each cluster.

The aim of the current research was to apply the clustering technique in order to analyze the state of knowledge management in Golestan University, so this research is applied, in terms of descriptive-survey purpose. In this research, the researchers have taken a holistic and systemic view of the knowledge management category and did not consider the implementation of knowledge management in the university to be dependent on the availability or need of a specific group. The members of the statistical sample were 281 administrators, faculty members, and scientific assistants of Golestan University, who were selected through stratified sampling and they were measured through Newman and Conrad's general management questionnaire, whose reliability and validity were confirmed using Cronbach's alpha and confirmatory factor analysis, respectively. In the first step, according to the four dimensions of the knowledge management cycle, the current state of knowledge management in Golestan University was analyzed at three levels of managers, faculty members and scientific assistants using non-hierarchical cluster analysis and Rapidminer software, and the number of optimal clusters according to the index Davis-Bouldin was obtained. In the second step, the members of the statistical sample placed in each cluster were analyzed based on their demographic characteristics. The results showed that in both clusters, the status of the four dimensions of knowledge management at the confidence level of 0.95 was lower than the number 3, and the analysis of the demographic characteristics of the clusters with the chi-square test at the confidence level of 0.95 showed that the results obtained with mental templates Preformed has a significant difference. The research results emphasize the implementation of knowledge management in Golestan University.

The effort of this article is to solve one of the main problems in the field of banking, which is closely related to the field of information technology. The combination of the management discussion of this topic with the field of information technology will be one of the important topics in the field of information technology management. The main goal of this article is the clustering of bank customers.At first, all customer characteristics were extracted from the bank's database, which was randomly extracted for 900,000 customers, which will be provided as input to the proposed method of this article. All the characteristics of these customers were extracted and 10 characteristics (except four characteristics of the LRFM method) were listed using the opinions of experts. The proposed method should be able to choose among these 10 features for clustering customers, which results in more resolution in clustering. Due to the high number of cases of this problem, it is not possible to do it manually, and the proposed method tries to provide a separate model for clustering for the customers of each bank by examining different cases. Also, the problem of choosing the right value for the number of clusters in the K-means method is solved by the method proposed in this article. The results show that it is better than the basic RFM and LRFM methods.Keywords: relationship management with bank customers, clustering, RFM model, LRFM model, particle swarm algorithm, K-means method.

The purpose of the present study is to design and explain the purchase journey map of moviegoers based on contact points. In the first step, using the content analysis method, 29 indicators were extracted as the contact points of moviegoers in the three stages of the shopping trip, and based on that, a research questionnaire was designed. In the second step, quantitative approaches were used to investigate the statistical population. To describe the research population, 419 adult moviegoers were clustered and analyzed in two separate clusters using the Davis-Bouldin index. The results showed that in the first cluster, the pre-purchase stage (actresses and director's brand), during the purchase (sanitary facilities), and post-purchase (advice, silence, and bad-mouthing) contact points were most significant. In the second cluster, the pre-purchase stage (previous experience), during purchase (store quality), and post-purchase (information on upcoming movies) contact points were most significant. Naive Bayes was used to design the model predicting the audience return rate. The application of Naive Bayes showed that by using contact points, it is possible to predict the return rate of moviegoers in the first and second clusters with an accuracy of 0.910 and 0.814, respectively. The sensitivity analysis results showed that in the first cluster, the pre-purchase stage (cinema brand), during the purchase (personnel encounter), and post-purchase (discount for the next visit) were the best predictors of consumer behavior. In the second cluster, the pre-purchase stage (word-of-mouth advertising), during purchase (store quality), and post-purchase (handling complaints) were the best predictors of consumer behavior.

In today's rapidly evolving business ecosystem, particularly in the insurance industry, complexity and pace of change have reached a level where adaptation to these fluctuations and ensuring sustainability are essential for survival. This has a significant influence both on small-scale and on strategic decisions made by business managers. Therefore, understanding the level of sustainability of companies within the dynamic contemporary environment is of utmost importance. This study aims to identify the sustainability assessment components of insurance companies in Iran and classify them based on sustainability using a clustering approach.

The study was carried out as applied work in terms of the objective and as a descriptive and survey work in terms of data collection and analysis approach. The statistical population of the study included all insurance companies in Iran. To determine the assessment indicators, the main indicators of the GRI model were extracted through an in-depth literature review and analysis of the Global Reporting Initiative website. After weighing these indicators, a structured questionnaire was designed and distributed among 12 experts, and the validity of the components was assessed through a two-round Fuzzy Delphi method. After confirming the components in two rounds, a structured questionnaire was formulated and distributed to 28 experts. Following data collection, insurance companies were classified using the k-means clustering method in SPSS.

The research findings revealed 21 main components and 35 sub-components for assessing the sustainability of insurance companies in Iran. According to the results, the Iranian insurance companies were classified into three clusters based on sustainability: the first cluster included companies in the formation stage, the second cluster encompassed companies in the growth phase, and the third cluster consisted of companies in the development phase with regards to sustainability. Specifically, 17 companies were in the first cluster, 6 companies in the second cluster, and 5 companies in the third cluster.

Companies strive to take steps towards sustainable development by providing sustainability reports, and the insurance industry is no exception. The insurance industry acts as a facilitator in promoting social, environmental, and economic activities. It possesses the necessary mechanisms and incentives to facilitate sustainable business activities on a macro level. However, segments within the insurance industry are susceptible to emerging risks stemming from social, environmental, and economic factors. Businesses deal with a variety of necessities at different levels of sustainability, and each insurance company aligns itself with a particular level of sustainability. The flexibility of insurance companies to adapt to changes and environmental transformations also varies. Therefore, insurance companies within each cluster must be adequately prepared for the changes.

The accurate and scientific assessment of the risk to issue an insurance policy is one of the most critical and important stages of risk assessment frameworks. This leads companies to identify high-risk customers and determine the policy rates in accordance with their risks, and as a result, the claims will be covered appropriately through the insurance premiums. In this paper, a new method is presented to define the concept of risk factor in more practical, flexible and accurate way. In this method, which is based on an unsupervised clustering algorithm, initially, every single factor is examined based on different ranges and their corresponding impact on customer loss levels. Then, considering their connection with the ranges of other factors in terms of creating similar levels of customer loss, they are combined to form a package. Thus, different packages are created, each of which is considered a risk factor and comprise the ranges of factors affecting different levels of loss. The k-means clustering method was used to divide insurers into clusters with similar risks, which correspond to the risk packages associated with the customers' risk level. The number of desired clusters should be determined in advance, which is the main challenge of using this algorithm. Two main approaches for validation, namely the silhouette score and the elbow method, were presented. Based on the elbow plot and silhouette coefficient, as well as considering the practical and realistic evaluation needed by insurance companies, four clusters were obtained. Cluster 2 and 3 are similar and can be merged to form a cluster of medium risk level. Therefore, three clusters were considered the best outcome for categorizing insurance policyholders. The risk packages can be introduced from the examination of the 3 clusters including People with high, medium and low age (confidence interval) with low price car whose gender is male can be introduced as the highest level of risk; People with medium and high ages (confidence interval) with medium and high car prices can be considered as medium risks, and Middle-aged and older people (confidence interval) with expensive cars were considered the lowest level of risk. From the results of these risk packages, it can be concluded that although a significant population of older policyholders falls into the first package (first cluster), they have the highest level of risk. On the other hand, the older people in the third package (even though their average age is the highest among the clusters) have the lowest level of risk. Another important point is that the risk level decreases as income increases simultaneously with age.

In recent years, one emerging area of interest for researchers has been the study of deviant behaviors in marketing. The objective of this article is to provide an in-depth understanding of the progress in marketing deviant behavior studies by conducting a comprehensive review of scientific articles in this field, utilizing text-mining methodologies.

We identified a total of 103 articles spanning the period from 1997 to 2021 through searches conducted on respected databases like Science Direct, Springer, Taylor & Francis, Emerald, Pro Quest, Sage, and Scholar. These searches were conducted using keywords such as "deviant behaviors of marketing" and "Marketing Deviance." Through a multi-stage screening process involving the examination of titles, abstracts, and keywords, our research team identified and selected a total of 72 articles pertinent to the subject of deviant behaviors in marketing for further text-mining analysis. Then, pre-processing of data was performed, and using cluster analysis, 6 optimal clusters were obtained according to Davies Bouldin index. Using the multi-attribute decision-making technique (SAW: Simple Additive Weighting), the most important roots were ranked in each cluster. Data were analyzed by RapidMiner and Matlab software.

The findings revealed a growing interest in researching deviant behaviors in marketing, particularly in recent years. The analysis generated clusters of topics, including Job and Corporate Identity, Customer Orientation and Service Orientation, Consumer Behavior, Sales States and Behaviors, Marketing Interactions, and Neutralization Techniques. It is predicted that in the future years, research on marketing deviant behaviors will increase, and continue its upward and increasing trend. The analysis of the paper trends indicates that between 1997 and 2013, the majority of articles primarily emphasized the significance of consumer behavior in the context of marketing deviant behaviors. Considering that marketing deviant behaviors have a notable impact on consumer behaviors, and consumers possess the potential to influence other customers, communities, and businesses, many researchers have previously introduced the concepts of marketing deviant behaviors and their effects on various aspects of consumer behavior. The observed trend underscores the prevalence of deviant behaviors within the marketing domain. This trend has evolved from initially introducing consumer behavior in marketing, shifting towards customer orientation and service orientation, and ultimately making its most significant contribution to the understanding of sales states and behaviors. Given this trend, we can predict the future path of marketing deviant behaviors toward the investigation of sales states and behaviors.

This study highlights marketing deviant behaviors' categories and orientations and provides a roadmap for future inquiry on marketing deviant behaviors. Marketing deviant behaviors need to be properly managed by the organizations and managers. This study offers insight to managers by clustering techniques about the trend of marketing deviant behavior research. By recognizing the contexts and major aspects of deviant behaviors in the organization, managers can take better and more effective steps to control and manage these behaviors.

In this research, a combined statistical process control model is presented to identify factors affecting efficiency and quality in manufacturing and component manufacturing industries, and then controlling and optimizing these processes is considered. Manufacturing and component industries are considered as the main body of the country's industries for case study and implementation. Clustering techniques are used to discover factors affecting efficiency. And then using decision tree algorithms to predict efficiency and quality in these industries, and in the final stage, control charts of dispersion and average variables are used to draw control charts. The comparison table of the parameters is prepared by the output of the Clementine software, and RapidMiner software is used in the neural network section. The results obtained from the identification of influencing and forecasting factors are close to the target values from a technical point of view, and the control charts are consistent with the technical control limits of the characteristics and are useful for optimizing the target value, which is efficiency and quality.

The Internet of Vehicles is a new framework for intelligent transportation systems. One of its goals is to improve safety and increase the quality of road travels. Topology changes in IoV present significant challenges to the safety programs. Due to the variety of traffic conditions, the reliability of current clustering methods faces many risks. In this research, a multi-criteria clustering model called RFCV has been proposed with the aim of increasing the reliability of the Internet of Vehicles. This model is independent of infrastructure and introduces four new criteria: "history of vehicle movement," "conformity of vehicle speed with the harmonic average of nearby vehicles'''' speeds," "number of reliable neighbors," and "performance quality in previous clusters." The weight of moving vehicles is considered, and the one with the best weight is selected as the cluster head, while an alternative cluster head is also determined to improve cluster stability. The stability of the cluster ensures that message exchange is possible in the closest time to real-time. The efficiency of the proposed clustering model has been theoretically proven, and simulations with multiple scenarios in SUMO and NS3 environments demonstrate the superiority of RFCV in increasing "route lifetime and packet delivery rate (PDR)" and decreasing "average delay and control overhead" in both densely populated urban and less-populated highway environments.

The success of organizations in achieving strategic goals is highly dependent on how the managers of that organization perform, and this success is more directly related to the selection and appointment of competent and knowledgeable managers at the top of the organizational pyramid. Competency-based management is a strong approach to developing and maintaining the organization's human capital in the long run, and competency models are a useful tool for identifying and developing the knowledge, skills and abilities needed by managers. In general, competency is a set of knowledge, skills, attitudes, abilities, interests and personality traits that enable employees to perform job-related activities effectively and perform job performance as expected or beyond expectations. Do." In accordance with the competencies defined in the evaluation center of the managers of the National Iranian Gas Company and according to the nature of trainable competencies, three categories of communication competencies, managerial and leadership competencies, cognitive and one category of untrained personality competencies have been defined. In this article, we have tried to achieve a set of core competencies in the field of competencies of gas industry managers, which has been achieved based on the performance of managers in organizational excellence. These core competencies are the beacon of the organization in achieving strategic goals and can be purposefully effective in the shortest time and with the least cost in the development process of the managers of the organization.

This research is aim to identify the main and the most updated scientific fields and sub-fields of "Critical Infrastructure Protection". Gaining this goal, current situation of this science is identified in the world and its available to have futurology and processology for our nations experts. The other goal of this paper was introducing the most pioneer countries and international researchers in this field.This research is applicable in nature and is done by scientometrics based on co-word analysis method. Authors' reasearches dedicated that no paper with this methodology has been done on the topic of critical infrastructure so far in our country. For gathering raw data we used Web of Science website and results analyzing and clustering maps drawing were done using VOSviewer software. For drawing sub-clusters diagrams, Xmind software was used.Results of this research showed that critical infrastructure protection as a multi-disciplinary science covers a wide area of issues. But the most important issues or topics on which international researches have been focused are topics like "key products and resources", "cyberspace and banking", "cascading effects", "Industrial control systems", "scada", "cyber attacks", "terrorism" and "food and water resources security". The most pioneer countries are USA, Italy and Germany and Messrs. Steven Rinaldi, Ted g. Lewis and Gerald Brown were known as the most cited international authors in critical infrastructure protection field.