Huaying Shu

Review of relationships among variables in TAM

The technology acceptance model (TAM) is an important tool in information technology research. Many scholars have applied the classical TAM to various research domains. However, the relationships between variables in these TAM models are not strongly desired. Thirty-four articles selected from international journals were analyzed to show that most of the relationships in the classical TAM are significant, but the stabilities of these relationships differ. The significant positive relationships between perceived ease of use and its independent variables are more stable than the others. Various factors can strengthen or weaken these relationships.

Artificial intelligence applications in the telecommunications industry

Abstract: Artificial intelligence (AI) has been applied to the telecommunications industry for more than a decade. The purpose of this paper is to examine the application of AI in the telecommunications industry sector. Our research finds that AIs first main application in telecommunications is in the network management area. Expert systems and machine learning are the two AI techniques that have been widely used in telecommunications, while machine learning and distributed artificial intelligence are the two AI techniques which are most promising for the future. The research also finds that different AI techniques have their unique applications in the telecommunications industry.

Study on Purchase Probability Model in CRM Systems

Representative customer’s purchase probability is the basis to analyze the purchase behavior of always-a-share customer’s segment. Currently, analyzing the representative customer’s purchase probability with the Dwyer model is quite complicated. Using uncertain reasoning, a backtracking Dwyer model and its algorithm are presented in this paper, which solves this problem in a more effective way. The work of this paper is helpful to design analytical CRM systems.

A Study on Customer Satisfaction in Mobile Telecommunication Market by Using SEM and System Dynamic Method

In this article, a new method is presented to research the mechanism of Customer Satisfaction (CS). Firstly, the research model of CS based on the TAM and ACSI is built. Secondly, some important correlation coefficients of research model can be got from the SEM method. Thirdly, with these correlation coefficients, the main functions of system dynamic model are built, and the evolution of the system is simluated with the help of VENSIM. At last, one simple example is designed by using the method and some meaningful conclusions are provided.

A Review on the Relationship Between New Variables and Classical TAM Structure

Integration of different theories and expansion of research areas are the main trends in the research domain of IS adoption. Classical TAM structure has been largely expended by newly added variables. Prior studies [1] have analyzed relationships among variables in TAM and found the stability of classical structure, but what about relationships between new variables and classical structure? We selected 30 articles from the main international journals for analyses. It is found that, SE, SN and PBC are used mostly in extended TAM. The relations between SE, PBC and TAM are consistently significant, but the integration of SN into TAM is not so ideal. In our review scale, this relation is inconsistent. Other variables and relations are also discussed in this article. The conclusions of this article will provide guidance for future researches about extended TAM model building.

Official reverse exchange model of virtual money

With the development of the network, virtual economy is booming, but the absence of reverse exchange mechanism of virtual money restricts the virtual economy. In this paper, first we discuss the current situation and the negative effect resulted from the third-party platform on the profit of issuers and the virtual economy, then by analyzing the advantages and disadvantages of the existed reverse exchange mechanism, we put forward a new model and point out that under the condition of profit maximization, the issuers will not infinite offering virtual currencies, and the ratio of the fiat money exchange rate to the material object exchange rate is equal to the ratio of the corresponding exchange amount of each way.

An Empirical Research of SMC Models and Their Application to CRM

SMC models are a group of models to forecast customers buying behaviors provided in 1987. If SMC models are proved to be true, they are very valuable to design analytical CRM (customer relationship management) systems. Choosing IT distribution market industry as background, an empirical research is done in this paper. We selected 331 customers to test SMC models. The conclusion is that SMC models do work in IT distribution market industry. They have a relative high prediction precision. The application of SMC models in CRM and the revising advice for SMC is also put forward

A New Method to Determine Purchase Probability of Representative Customer

Representative customers purchase probability is the base to analyze the purchase behavior of always-a-share customer. Using Dwyer model, the representative customers purchase probability is solved complexly. Using uncertain reasoning, a back-tracking Dwyer model and its algorithm are presented in this paper, which solve the problem more effectively

An Empirical Research on SMC in an Extended Enterprise Environment

There are few empirical researches and applications of SMC models for shortage of customer data and their complexity. Choosing IT distribution market industry as background, an empirical research is done in this paper. The conclusion is that SMC models do work in IT distribution market industry. They have relatively high prediction accuracy. Also, the revise advice for SMC is put forward to meet different types of customer behaviors.

Predicting Churn Probability of Fixed-line Subscriber with Limited Information: A Data Mining Paradigm for Enterprise Computing

The phenomenon of subscriber churn is becoming more and more serious in the fixed-line communications industry. In order to build customer loyalty and maximize profitability in the ever-increasing competitive marketplace, a churn prediction method becomes necessary for a fixed-line services provider. However, today’s researches on churn prediction in the telecommunications industry mostly concentrate on mobile services field, rarely on fixed-line services field. One prime reason is the less amount of qualified information for churn prediction in the fixed-line services providers. In response to the limitation of information, especially the incompletion of call details and unreliability of subscribers’ demographics in the investigated fixed-line services provider, we propose, design and experimentally evaluate several churn-prediction models applying three different data mining techniques (Decision tree, regression, neural network), with predictors (i.e. input variables) derived only from subscribers’ contractual information and bill details. The predictors can be mainly categorized into four types: duration of service use, payment type, amount and structure of monthly service fees, change of the monthly service fees. The result shows that these limited but appropriately designed predictors can effectively predict subscribers’ churn probabilities and decision tree outperforms regression and neural network in this study, with the optimal predictive and explanatory power. What’s more, it also indicates that duration of service use is the most predictive predictor, and payment type and other variables of amount and structure of monthly service fees within different months especially the latest months are also effective predictors. According to the result that the predictors within the latest months are more effectual, we then build different decision tree models using historical data of different amounts of months. We find that with the reduction of early monthly data for prediction, the model performance index “chumer captured proportion in top ranks” declines very slightly, which can be ignored. However, the amount of the data for processing and the runtime of prediction model decreases significantly. Hence, we suggest that using relatively fewer, latest months’ data to predict subscribers’ chum trends would be an effective way.