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.
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.