List of Articles RFM

• Open Access Article
  • Abstract Page
  • Full-Text
  
  1 - A Study to Improve the Response in Email Campaigning by Comparing Data Mining Segmentation Approaches in Aditi Technologies
  P. Theerthaana S. Sharad
  Manuscript profile
• Open Access Article
  • Abstract Page
  • Full-Text
  
  2 - Mining the Retail Banking Customers Characteristics Using Data Mining Techniques
  J. Nazemi P. Jafari H. Hashemi
  Deregulation within the banking industry's and unprecedented growth competition in new technologies, every day the importance of keeping current customers and attract new customers are added. This study presents a two-step model to identify characteristics of different More

  Deregulation within the banking industry's and unprecedented growth competition in new technologies, every day the importance of keeping current customers and attract new customers are added. This study presents a two-step model to identify characteristics of different groups of bank customers, based on their profitability. The new criteria introduced to analyze the profitability of each customer. And then, this criterion has been used for clustering customers based on their profitability. Because in k-mean algorithm there is not a general rule for the optimal number of clusters and the number of clusters depend on the problem, therefore firstly with applied by Two-step clustering algorithm determine the optimal number of clusters. In this study, Customers clustering to 3 groups as golden, silver, and bronze customers. Then, by using K-mean algorithm different groups of customers are identified. And with help of Apriori algorithm association rules of each cluster is inference. The result of this exploration, help to banks have better understanding of current and future customer expectations. And through this may be facilitated develop of marketing strategies to attract and retain profitable customers. Manuscript profile
• Open Access Article
  • Abstract Page
  • Full-Text
  
  3 - Presenting a New Model of Optimal Coordinated beam former Vector Selection in DRFM for Radar Jamming
  Hasan Mohammadi khodadad Halili Vahidreza Soltaninia Meysam Bayat Saeed Talati
  10.30486/mjtd.2023.1986716.1034
  Manuscript profile
• Open Access Article
  • Abstract Page
  • Full-Text
  
  4 - Monitoring of vegetation changes using daily Landsat-Modis simulated images at in three years of wet, normal and drought in arid region (Case study: Nimroze city)
  Moien Jahantigh Mansour Jahantigh
  10.30495/girs.2023.685742
  Background and Objective land degradation and desertification in arid areas are the most important environmental challenges in the world. This process due to the lack of precipitation and the occurrence of drought, while the unreasonable exploitation of natural and agri More

  Background and Objective land degradation and desertification in arid areas are the most important environmental challenges in the world. This process due to the lack of precipitation and the occurrence of drought, while the unreasonable exploitation of natural and agricultural areas with increasing demand to provide human food needs, affects various environmental and socio-economic dimensions. So, the continuation of this condition during recent years with the destruction of vegetation and soil, wind and water erosion, soil salinity, soil compaction, and declining groundwater aquifers have significant consequences for the production of agricultural products and biodiversity in an arid region. Since the pattern and dimensions of vegetation changes are the most important factors in detecting land degradation, monitoring the vegetation changes is the best approach to analyzing land degrading and desertification trends in an arid region. Therefore, according to the capabilities of remote sensing data due to the wide coverage and multi-timed,  the use of satellite imagery to monitor vegetation changes by using vegetation index is one of the best methods that developed in recent years. Moreover, concurrent access to high spatial and temporal resolution imageries is one of the important factors that affect the monitoring of vegetation changes. To achieve this goal, It needs to incorporate different satellites with high spatial (e.g., Landsat satellite) and temporal (e.g., MODIS satellite) images. The purpose of this study is the monitoring vegetation changes using daily Landsat simulated images at 30 m Spatial Resolution in three years of wet, normal, and drought in the Nimroze area.Materials and Methods The study area is located in the north of the Sistan and Baluchistan provinces. Low precipitation (50 mm), high temperature (48 oC), high evaporation (5 m), and 120-day winds are among the specific climatic conditions that characterize this region. In this study, at first, the hydrological drought status of the Hirmand River was investigated. Using the Hydrostats package in R software, the amount of threshold of flood by running the related codes (by running codes such: daily.cv, ann.cv, high. spell, and low. spell) during the statistical period of study (29 years) was calculated. To determine wet, normal, and drought years calculated the length of periods that flood is higher (high. spell. lengths) and lower (low. spell. lengths) than the threshold. To increase the accuracy of monitoring vegetation changes, it needs to incorporate different satellites with high spatial (e.g., Landsat) and temporal (e.g., MODIS) images. To achieve this purpose, in this study, the Enhanced spatial and temporal adaptive reflectance fusion model (ESTARFM) was evaluated with actual satellite data (OLI, ETM+, TM image). For this purpose at first, pre-processing (geometric, radiometric, and atmospheric correction) was performed on satellite images, and by using the ESTRFM model, simulated daily Landsat images at 30 m spatial resolution for wet, normal, and drought years. In-field operations from different plant communities by GPS were sampled. Comparing filed data with the Normalized difference vegetation index (NDVI) and the soil-adjusted vegetation index (SAVI), the vegetation index that had the highest correlation with field data was selected. To investigate vegetation changes, using the vegetation index (the vegetation index with high correlation), the map of vegetation for each year was prepared (wet, normal, and drought years). After the classification maps of vegetation, by comparison, approach (cross tab), the map of vegetation changes was extracted.Results and Discussion The results of analyzing wet and dry periods showed that, flood volume in dry years compare to normal and wet years decreased 31 and 82 percentages, respectively. To incorporation MODIS and Landsat (OLI, ETM+, TM) Images, using enhanced spatial and temporal adaptive reflectance fusion model (ESTARFM), finding indicate that this model improves the accuracy of predicted fine-resolution reflectance and preserves spatial details for heterogeneous landscapes too. So that the mean coefficient of determination (R2) of blue, green, red and near-infrared estimation bands with actual satellite images data is 0.91, 0.89, 0.92 and 0.91 respectively. Also the average Root-Mean-Square Error (RMSE) in four bands obtained 0.01, 0.027, 0.028 and 0.031 successively. Comparing the obtained field data with the Normalized difference vegetation index (NDVI) and the soil adjusted vegetation index (SAVI), indicate that SAVI index has the highest correlation (R2= 87) with vegetation of study region. By calculate the regression model (using SAVI and field data) and classify the vegetation maps of wet, normal and drought years, 6 class obtained (class1=0-10%, class2=20-10%, class3=20-30%, class4=40-50%, class5=60-80% and class6=>80%). The results of investigation vegetation changes indicate that during the drought period 70% of study area has less than 10% vegetation (equal to 138176.3 hectares) and during normal and wet years by increasing vegetation, this area decreased by 30 and 48% respectively (equal to 66269.98 and 50559.7 hectares, respectively). According to the results during the study period, the most vegetation changes is relate to conversion of class 1 to class 2 (equivalent to 48.5%). moreover 18 and 27% of vegetation changes relate to class 1 and 2 to class 4 and 5 respectively (equal to 16284.26 and 11471.88 hectares, respectively). Also the finding indicates that the most vegetation changes occurrence in wetland-forest (28%), forest-rangeland (21%) and poor rangeland (19%) land uses respectively. Field study also showed that, the most important plant species that grows in this land-use such as the results of analyzing wet and dry periods showed that flood volume in dry years compare to normal and wet years decreased by 31 and 82 percent, respectively. To incorporation MODIS and Landsat (OLI, ETM+, TM) Images, using enhanced spatial and temporal adaptive reflectance fusion model (ESTARFM), the finding indicates that this model improves the accuracy of predicted fine-resolution reflectance and preserves spatial details for heterogeneous landscapes too. So that the mean coefficient of determination (R2) of blue, green, red, and near-infrared estimation bands with actual satellite images data is 0.91, 0.89, 0.92, and 0.91 respectively. Also, the average Root-Mean-Square Error (RMSE) in four bands obtained 0.01, 0.027, 0.028, and 0.031 successively. Comparing the obtained field data with the Normalized difference vegetation index (NDVI) and the soil-adjusted vegetation index (SAVI), indicate that the SAVI index has the highest correlation (R2=87) with the vegetation of the study region. By calculating the regression model (using SAVI and field data) and classifying the vegetation maps of wet, normal, and drought years, 6 classes obtained (class1=0-10%, class2=20-10%, class3=20-30%, class 4=40-50%, class5=60-80% and class6=>80%). The results of the investigation of vegetation changes indicate that during the drought period, 70% of the study area has less than 10% vegetation (equal to 138176.3 hectares) and during normal and wet years by increasing vegetation, this area decreased by 30 and 48% respectively (equal to 66269.98 and 50559.7 hectares, respectively). According to the results during the study period, most vegetation changes are related to the conversion of class 1 to class 2 (equivalent to 48.5%). moreover, 18 and 27% of vegetation changes relate to class 1 and 2 to class 4 and 5 respectively (equal to 16284.26 and 11471.88 hectares, respectively). Also, the finding indicates that the most vegetation changes occur in wetland-forest (28%), forest-rangeland (21%), and poor rangeland (19%) land use respectively. The field study also showed that the most important plant species that grow in this land use such as Aeluropus littoralis, Chenopodiace sp, Tamarix aphylla, Haloxylon aphylum are adaptive to climatic regime in study area.Conclusion In this research for the first time in the Nimroz region of Sistan Vegetation changes were studied using Landsat simulated images during periods of low water, normal, and high water years. Due to low rainfall and harsh climate in the study area, floods in the Helmand River are the only source of water supply required in the study area. The results of analyzing wet and dry periods showed that flood volume in dry years compared to normal and wet years has decreased by 31 and 82, respectively. According to the reduction of flood volume during a drought year, 70% of the study area has poor vegetation and during normal and wet years, providing plants with water needs and increasing vegetation, this area had decreased by 30% and 48%, respectively. According to the results of this study, change in hydrological conditions of the Hirmand River has a significant role in vegetation changes in the study area by using simulated images with high spatial and temporal resolution can improve the accuracy of monitoring vegetation changes to control and management the desertification in Sistan area. Manuscript profile
• Open Access Article
  • Abstract Page
  • Full-Text
  
  5 - Presenting a Conceptual Framework to Increase the Return and Reduce Risk (A case study: customers of Mellat Bank of Arak)
  Mohammad Moradi Mohammad Sadegh Horri iraj Nouri
  10.22034/amfa.2022.1931043.1594
  Manuscript profile
• Open Access Article
  • Abstract Page
  • Full-Text
  
  6 - PRFM Model Developed for the Separation of Enterprise Customers Based on the Distribution Companies of Various Goods and Services
  Mohammad Mahdi Hajmohamad Narges Rahimi Behzad Sasanizadeh
  10.30495/jsm.2021.678895
  Manuscript profile
• Open Access Article
  • Abstract Page
  • Full-Text
  
  7 - Quantitative studies in the management of the banking industry in order to increase customer satisfaction and profitability (case study: Bank Mellat)
  Mohammad Moradi Mohammad Sadegh Horri Iraj Noori
  10.30495/qrm.2023.1991352.1032
  In order to provide all kinds of facilities to their customers, credit institutions need to carry out complete surveys in order to know the applicants from qualitative and quantitative aspects, in order to fully evaluate the ability to repay and calculate the probabilit More

  In order to provide all kinds of facilities to their customers, credit institutions need to carry out complete surveys in order to know the applicants from qualitative and quantitative aspects, in order to fully evaluate the ability to repay and calculate the probability of non-repayment of facilities and services. Financially, these surveys are generally called validation. The purpose of this research is to rank the groups of customers and determine the best parts of them so that the brokerage company can perform credit allocation in a mechanized way. For this purpose, after the initial pre-processing of the data, they are processed in the form of RFM 1 model. Then, using the SOM 2 neural network as one of the clustering algorithms, the customers will be divided into 10 clusters. In the following, using the proposed model, the clusters are ranked. The best clusters are identified and the operation of granting facilities is done for the members of these clusters. Finally, three clusters 5, 1 and 7 were determined as the best clusters, which are the target customers. The coefficient of facilities granted to these top three clusters is 0.271, 0.173 and 0.556 respectively. Manuscript profile
• Open Access Article
  • Abstract Page
  • Full-Text
  
  8 - Integrating AHP and data mining for effective retailer segmentation based on retailer lifetime value
  Amin Parvaneh Hossein Abbasimehr Mohammad Jafar Tarokh
  Manuscript profile
• Open Access Article
  • Abstract Page
  • Full-Text
  
  9 - Designing a Model Providing Services to Key Customers Based on RFM Model Using K-Means Clustering Method
  Ali Sorayaie Amir Yousefizad
  Manuscript profile
• Open Access Article
  • Abstract Page
  • Full-Text
  
  10 - Presenting a customer classification Pattern with a combined data mining approach (case study :Hygienic and Cosmetic products Industry )
  omid Bashardoust Ezzatollah Asgharizadeh moHammadAli AfsharKazemi
  Due to the accumulated volume of customer purchasing information and the complexity of competition in the present era, the importance of creating a platform for analyzing up-to-date and accurate customer data, with the aim of creating effective relationships with curren More

  Due to the accumulated volume of customer purchasing information and the complexity of competition in the present era, the importance of creating a platform for analyzing up-to-date and accurate customer data, with the aim of creating effective relationships with current and loyal customers, more than ever for organizations as It has become a competitive advantage. The purpose of this study was to investigate the behavioral patterns of customers buying Hygienic Products in order to classify them based on the WRFM using data mining methods. 65534 samples were collected from the company databases in the period of 1396-1397 among the customers of Tehran province by the available purposeful sampling method, also with the help of SPSS, the amount of WRFM determined according to the opinion of industry experts and then this field had been to other fields in the research and using Clementine software, customers clustering has been done according to 70% of the data; also, in order to evaluate the quality of clustering, the criteria of Gini Score, error percentage, and normalized mutual information were used. The results indicate the high efficiency of the K-Means clustering method with the number of four clusters with purity percentage (0.761) for customer segmentation. Manuscript profile
• Open Access Article
  • Abstract Page
  • Full-Text
  
  11 - Risk Identification and Analysis Based on the Integrated Approach of PMBOK and RFMEA in Petrochemical Industry Projects
  Masoud Najmi Hasan Mehrmanesh Nosratollah Shadnoush
  Nowadays, as projects become more complex, uncertainty in the implementation of projects also increases. Project risk includes threats to project goals. Risk management is one of the main parts of strategic management of any project and includes processes through which More

  Nowadays, as projects become more complex, uncertainty in the implementation of projects also increases. Project risk includes threats to project goals. Risk management is one of the main parts of strategic management of any project and includes processes through which risks related to activities can be identified methodically. The main purpose of this study is to identify and analyze risk, using the integrated approach of PMBOK and RFMEA methods in petrochemical industry projects. The statistical population consists of employer, contract management, engineering consultant, and contractors of the Kermanshah petrochemical industries company. Of whom 10 were selected for the qualitative part and 248 were selected for the quantitative part (regression analysis). Questionnaires were handed to the selected population. 220 of which, were filled out and returned acceptably. As a result, a total of 22 risks were identified as critical risks (with RPN of 1) and the role of management, organizational, and environmental factors in risk management was investigated. Manuscript profile