Given the importance of customers as the most valuable assets of organizations, customer retention seems to be an essential, basic requirement for any organization. Banks are no exception to this rule. The competitive atmosphere within which electronic banking services are provided by different banks increases the necessity of customer retention. Being based on existing information technologies which allow one to collect data from organizations’ databases, data mining introduces a powerful tool for the extraction of knowledge from huge amounts of data. In this research, the decision tree technique was applied to build a model incorporating this knowledge. The results represent the characteristics of churned customers. Bank managers can identify churners in future using the results of decision tree. They should be provide some strategies for customers whose features are getting more likely to churner’s features.
The objective of this paper is to investigate customers' adoption of mobile payment (M-payment) services. The proposed conceptual model combines technological factors and behavioural factors of M-payment services adoption. A questionnaire is developed and 623 completed questionnaires are gathered from Iranian customers. ANOVA and MANOVA analysis are used to find out the impact of demographic and cultural characteristics on other related research factors. The overall fitness of the proposed model is tested by confirmatory factor analysis and logistic regression. It is shown that the model has a suitable fitness. The model shows that ease of use, usefulness, trust, compatibility, cost, norm, payment habit, availability of mobile phone skills, and convenience are in the suitable condition and these factors influence adoption superiorly.
11 June 2018 in International Journal of Health Care Quality Assurance
Purpose: Resilience engineering, job satisfaction and patient satisfaction were evaluated and analyzed in one Tehran emergency department (ED) to determine ED strengths, weaknesses and opportunities to improve safety, performance, staff and patient satisfaction. The paper aims to discuss these issues.Design/methodology/approach: The algorithm included data envelopment analysis (DEA), two artificial neural networks: multilayer perceptron and radial basis function. Data were based on integrated resilience engineering (IRE) and satisfaction indicators. IRE indicators are considered inputs and job and patient satisfaction indicators are considered output variables. Methods were based on mean absolute percentage error analysis. Subsequently, the algorithm was employed for measuring staff and patient satisfaction separately. Each indicator is also identified through sensitivity analysis.Findings: The results showed that salary, wage, patient admission and discharge are the crucial factors influencing job and patient satisfaction. The results obtained by the algorithm were validated by comparing them with DEA.Practical implications: The approach is a decision-making tool that helps health managers to assess and improve performance and take corrective action.Originality/value: This study presents an IRE and intelligent algorithm for analyzing ED job and patient satisfaction – the first study to present an integrated IRE, neural network and mathematical programming approach for optimizing job and patient satisfaction, which simultaneously optimizes job and patient satisfaction, and IRE. The results are validated by DEA through statistical methods.
1 September 2016 in Simulation Modelling Practice and Theory