JOURNAL OF INFORMATION TECHNOLOGY MANAGEMENT
Year:2014 | Volume:6 | Issue:1|Papers Count:8

One of the main problems in dynamic customer segmentation is finding the dominant patterns of customer transmission between different segments over time. Accordingly, we concentrate on the customer dynamics in this paper and try to find different groups of customers in transmission between segments overtime. The dominant characteristics of these groups are also investigated. To achieve this objective, a new hybrid technique based on the K-means algorithm, hierarchical clustering and association rule mining is presented and implemented on the data obtained from one of the main telecommunication corporations in Iran. The results show that there are seven different groups of customers. Furthermore, the impact of customer dynamics on segments' changes is investigated over time. In this regard, a new approach of categorizing customers is proposed according to their impact on the structure and the content of segments' changes. These new groups include "the customers who preserve the structure", "the ones who are consistent with the structure" and "the customers who destroy the structure".

expert systems can help to build banks customers'' credit scoring models. Here, selection of key features of the credit scoring is important. Also, it is possible to express the features values as fuzzy. The problem is how to improve features selection by genetic algorithm, in way that these features can be employed as input in fuzzy expert system. This paper presents a hybrid credit scoring model with combination of features selection based on genetic algorithm and fuzzy expert system. The research conducted at the entry, in terms of result and objective is applied and descriptive research as case study, respectively. Ghavvamin financial and credit institution credit scoring date set is used to train and test the model. After data preprocessing, features selection is carried out using genetic algorithm. The range of selected features is determined by interview with an expert and via fuzzy logic and then credit scoring fuzzy rules can be generated. WEKA tool and fuzzy inference system (FIS) in MATLAB are used for data analysis. Results demonestare classification accouracy of the proposed model is more than the other compared methods in this paper. Fuzzy rules created by this model can be used for credit scoring of bank customers.

Today, many organizations plan to implement and exploit ERP system due to its numerous benefits. Despite these advantages, many adopting organizations have failed to achieve their intended goals through utilizing ERP system. Among other factors, organizational characteristics have been proposed as one of the effective factors which can influence ERP success in both implementation and post-implementation stages. This study examines the impact of Organizational Structure as a potential factor on ERP post-implementation success in Iranian adopting organizations. A research model is developed to test fifteen hypothesized relations among the variables. Data is gathered from every adopting organization using a standard questionnaire. Then, Structural Equation Modelling (SEM) Method and Partial Least Squares (PLS) Algorithm are used for data analysis. The findings confirm the impact of Organizational Structure on ERP post-implementation success and indicate how Structural Dimensions affect ERP success facets.

Classifying customers using data mining algorithms enables banks to keep old customers loyality while attracting new ones. Using decision tree as a data mining technique, we can optimize customer classification provided that an appropriate decision tree is selected. In this article we have presented an appropriate model to classify customers who use internet banking service. The model is developed based on CRISP- DM standard and we have used real data of Sina bank's Internet bank. In comparison with the other decision trees, ours is based on both optimization and accuracy factors that recognizes new potential internet banking customers using a three level classification, which is low/medium and high. This is a practical, documentary-based research. Mining customer rules enables managers to make policies based on discovered patterns in order to have a better understanding of what customers really desire.

Trust is one of the most important factors for the development of electronic banking. The purpose of this study is to determine effective factors on trust in e-banking in the form of a conceptual model. Due to the rapid growth of electronic banking in the country, identifying the factors affecting trust in e-banking is very important. The population of this study includes customers of Melli Bank in Urmia. We used structural equation modeling with Lisrel 8.80 for testing hypotheses. Results show that independent variables, including familiarity with electronic banking, tendency to trust, structural confidence and reputation, affect mediator variable, i.e. trust creator beliefs; and trust creator beliefs affect the dependent variable, i.e. trust on electronic banking. Therefore, trust creator beliefs playa mediating role in relationship between independent and dependent variables. The results of this research can be used by public and private banks' top management.

This paper aims to determine the perceptual factors affecting the faculty member's knowledge sharing intention. This research has been set within the frame of Planned Behavior Theory and has been combined of the two prediction behavior models. Knowledge sharing intention is the dependent variable of model. Mediator variables include attitudes, subjective norms and perceived behavioral control, and independent variables include perceived relative advantage, trust in management, perceived organizational support, fear of losing one's unique value, perceived environmental dynamism, and perceived supervisor control. This survey research was implemented within North Branch of Tehran and Science and Researches Campus including 148 stratified random samples of the faculty members. The statistical analysis of the model has been done through structural equation model with PLS software. All hypotheses are confirmed and the power of model prediction for knowledge sharing intention is R 2 =0.579. In order to promote higher education development indexes, the results of this survey can be applied for systematic planning to encourage academic members knowledge sharing.

Professionals with little or no knowledge of Information and Communication Technology (ICT) have a much more difficult task in comparison to co-workers at the same level but with a reasonable knowledge of lCT. The main goal of the research is to determine the level of familiarity with ICT in performing organizational responsibility. The population of the research includes all experts and faculty members of university colleges of Agriculture and Natural resource, University of Tehran. A researchers-made questionnaire was distributed among 124 members as the research sample. The validity of the questionnaire was approved by experts and the reliability was approved by calculating the Cronbach's alpha (95%). The results indicated that there is a positive relationship between the level of ICT usage and the field of education and academic ranking. The results of mean analysis showed a difference between the amount of usage of and familiarity with ICT among men and women and the variance analysis results showed that the amount of familiarity with and usage of ICT is different among different levels of education, academic ranks and different types of employment.

This paper investigates the factors accelerating SMEs' adoption of e-commerce. Initially we proposed a model that included three categories of factors including external environmental factors, internal environmental factors and technology specifications. In addition, we proposed e-commerce adoption stages in two levels of early adoption and institutionalization. Based on surveying 304 SMEs, we tested the proposed model and concluded that the external environmental factors can be divided by two main categories of remote environmental factors and industry level factors. The relations between criteria and latent variables are also discussed and explained.