elham mazaheri; alireza talebpour; ali rezaian
Volume 19, Issue 2 , August 2015, , Pages 161-182
Abstract
With the emergence of social networks, the relationships among people found a new horizon. Nowadays, a large number of users sign up in social networks with different goals and they get involved in different activities.On the other hand they affect on one another while their roles and effects are not ...
Read More
With the emergence of social networks, the relationships among people found a new horizon. Nowadays, a large number of users sign up in social networks with different goals and they get involved in different activities.On the other hand they affect on one another while their roles and effects are not the same. Some of these users have more effects on the others according to their job status, educational backgrounds and their attractive notes. These users ,whom we call the power nodes, can change the perspective of many users and move them to specific directions. The aim of this research is the identification of the power nodes in Tebyan, as a social network, and such aim was fulfilled through a discovery of the concealed models in the characteristics of the users. This research has followed the standard methodology of CRISP-DM. To reach this end, after the identification of the power nodes, according to the attained sum scores, from three parameters: central relativity, the page rank, and the users activities, a classification was provided from an algorithm tree. The achieved results have shown that the most significant features in determination of a user's power in a social network are education, age and gender.
Kaveh Mahdavi; - -
Volume 19, Issue 1 , July 2015, , Pages 91-116
Abstract
All of the financial institutions for gaining the best profit of their investment are always looking for the best investors, consulters, and borrowers. Besides, different sciences attempt to represent accurate methods for the separation of the customers. For that reason, sciences such as psychology, ...
Read More
All of the financial institutions for gaining the best profit of their investment are always looking for the best investors, consulters, and borrowers. Besides, different sciences attempt to represent accurate methods for the separation of the customers. For that reason, sciences such as psychology, management sciences, mathematics, financial and etc…seek to achieve this aim. The subject that comes into consideration in this paper is the necessity of using the new methods in data mining in mixture with artificial intelligence techniques in order to deal with the sophisticated issue and answer to this question that do the usage of combined approach predict the customer rating well? If we want this process occurs, another dimension must not be forgotten that is the select measurement criteria and in this regard, the researcher has used judging journalist and non-parametric analysis in order to rank criteria thatfinally, select the number of indicatorsin order to implement the hybrid model will lead the researcher to answer this question: do the journalist’s ideas selection criteria result in a good prediction of the credit status of customers? The three indicators “age”, “previous relationship with the bank”, and “credit”to implement a fuzzy neural hybrid model are chosen. The model has been implemented in three layers and results suggest that 89.67% times the system can accurately estimate the proportion of customers provide ratings.To optimize the fuzzy neural network, the ant colony algorithm was used which results in improved performance of the model was 90.5%.
Hassan Rezapour; Mohammad Rezapour; Mohammad Mehdi Sepehri
Volume 17, Issue 4 , January 2014, , Pages 139-160
Abstract
Determining how to assess learners and contents of e-learning are essential activities in its processes. These activities are conducted by a professor or teaching assistant and they determine student assessment methods, such as holding an online test or periodic homework assignment. if the organizers ...
Read More
Determining how to assess learners and contents of e-learning are essential activities in its processes. These activities are conducted by a professor or teaching assistant and they determine student assessment methods, such as holding an online test or periodic homework assignment. if the organizers can be aware of the effectiveness of each activity in the quality of learning,then besides saving considerable time and resources to stakeholders courses, which transfer the content useful and realistic assessment of students and will ultimately improve e-learning. In this paper, first we use unsupervised techniques of data mining for clustering and describe the present status of learners, and extract hidden rules in e-learning data using rule mining and will discover the effective contents in desired results. Next, using supervised methods we predict results of courses. Using real data of an electronic course provided and with designing four different methods for data sampling and training system, predictions were performed and the methods were validated with an accuracy rate of 92.86%. We have shown that the methods of this study can help teachers for a better understanding of learners and impact of such training activities required, such as describe characteristics of learners based on the discovery of hidden patterns in the scores of their acquired and determine the most effective learning activities and decide about real measures of learners.
Mohammad Hesam Ghanbari; Shaaban Elahi; Alireza Hasanzadeh
Volume 16, Issue 2 , July 2012, , Pages 57-71
Abstract
In recent decay development of different technologies is dramitically high and it influences in services. One of fields which is affected from information technology is bankining industry. Wireless technology is one of the information technology fields that has a greate development in recent years which ...
Read More
In recent decay development of different technologies is dramitically high and it influences in services. One of fields which is affected from information technology is bankining industry. Wireless technology is one of the information technology fields that has a greate development in recent years which resualt of that is mobile banking service. Banking industry is a smple that uses data mining technique. Data mining is kind of exploring knowledge to solve a special problem. In this research 232817 data is used to find some models by artificial neural networks and naïve bayes techniques in according with customers' attributes. Furtheremore result of this research help to classify customers who use mobile banking service and then the bank can offer the service to somebody who are in this classification but donot use this service. So in this way the bank can attract more customers, maintain its customers, and keep high customers' satisfaction. Also the research reveals that artificial neural networks is more accurate than naivie bayes and the research's hypothesis is proved.
ashraf norouzi; Babak Teymourpour; Sarvenaz Chubdar; Mohammad Mehdi Sepehri
Volume 15, Issue 4 , February 2012, , Pages 97-125
Abstract
Customer churn management consist of three main phases: identifying churners, discovering the causes of churn and adapting appropriate strategies against this problem. Most of studies in this field focused on prediction of customer churn. Few studies about discovering causes of churn are just about testing ...
Read More
Customer churn management consist of three main phases: identifying churners, discovering the causes of churn and adapting appropriate strategies against this problem. Most of studies in this field focused on prediction of customer churn. Few studies about discovering causes of churn are just about testing primary hypothesis about probable causes. This study because of the shortage of previous studies in this field has made lots of innovations. Some of these innovations are: designing a new framework for discovering causes of churn and designing a hybrid approach from data mining and survey techniques which carried out without benchmarking from any similar study. Proposed framework includes four main steps: feature construction and selection, identification of churners, discovering the causes of churn, and validating the results. Current account customers of Keshavarzi Bank are selected as casestudy of this research and the required data is gathered trough questionnaire. The approach used for discovering causes of churn is extracting the rules which lead to churn in various clusters of customers. For this purpose, decision tree technique with target variable of churn label is utilized. Validating the results is carried out by testing it on validation data set and calculating the top lift and overall error rate. The extracted rules represent that there is a tendency to churn among big segment of keshavarzi's customers. The most important reason (specially among higher salary customers) is about manner of bank agents not reasons expressed by experts such as the way of lending or the profit of backup accounts.
