Analysing user trust in electronic banking using data mining methods

The potential fraud problems, international economic crisis and the crisis of trust in markets have affected financial institutions, which have tried to maintain customer trust in many different ways. To maintain these levels of trust they have been forced to make significant adjustments to economic structures, in efforts to recoup their investments and maintain the loyalty of their customers. To achieve these objectives, the implementation of electronic banking for customers has been considered a successful strategy. The use of electronic banking in Spain in the last decade has been fostered due to its many advantages, giving rise to real integration of channels in financial institutions. This paper reviews different methods and techniques to determine which variables could be the most important to financial institutions in order to predict the likely levels of trust among electronic banking users including socio-demographic, economic, financial and behavioural strategic variables that entities have in their databases. To do so, the most recent advances in machine learning and soft-computing have been used, including a new selection operator for multiobjective genetic algorithms. The results obtained by the algorithms were validated by an expert committee, ranking the quality of them. The new methodology proposed, obtained the best results in terms of optimisation as well as the highest punctuation given by the experts.     

Understanding sources of user variability in computer-based data entry performance

The pervasive use of computers in work settings implies that an increased number of workers, with varying levels of skills and abilities, will be performing computerbased tasks. This study investigated the impact of age, cognitive abilities, and computer experience on the performance of a real world data entry task. One hundred and ten subjects, ranging in age from 20 - 75 years, performed the task for nine hours following task training. The results indicated that abilities such as visuo-spatial skills, motor skills and processing speed had a significant impact on performance as did age and prior computer experience. With respect to age, the older participants completed less work than the younger and middle-aged subjects. Age differences in psychomotor skills and processing speed appeared to be important factors underlying age effects. In fact, the data indicated that after controlling for differences in these abilities age was no longer a significant predictor of work output. Further, after controlling for differences in work output the older people made fewer errors than the younger people. Overall the data suggest that older people will be at a disadvantage in the performance of computer-based data entry work to the extent to which speed of responding is emphasized. However, if speed of responding is not a critical element of performance they will be able to achieve comparable levels of performance to that of younger people.     

Understanding sources of user variability in computer-based data entry performance

The pervasive use of computers in work settings implies that an increased number of workers, with varying levels of skills and abilities, will be performing computerbased tasks. This study investigated the impact of age, cognitive abilities, and computer experience on the performance of a real world data entry task. One hundred and ten subjects, ranging in age from 20 - 75 years, performed the task for nine hours following task training. The results indicated that abilities such as visuo-spatial skills, motor skills and processing speed had a significant impact on performance as did age and prior computer experience. With respect to age, the older participants completed less work than the younger and middle-aged subjects. Age differences in psychomotor skills and processing speed appeared to be important factors underlying age effects. In fact, the data indicated that after controlling for differences in these abilities age was no longer a significant predictor of work output. Further, after controlling for differences in work output the older people made fewer errors than the younger people. Overall the data suggest that older people will be at a disadvantage in the performance of computer-based data entry work to the extent to which speed of responding is emphasized. However, if speed of responding is not a critical element of performance they will be able to achieve comparable levels of performance to that of younger people.     

Recommendation System based on user interaction data applied to intelligent electronic books

Nowadays, new technologies and the fast growth of the Internet have made access to information easier for all kind of people, raising new challenges to education when using Internet as a medium. One of the best examples is how to guide students in their learning processes.The need to look for guidance from their teachers or other companions that many Internet users experience when endeavoring to choose their readings, exercises o practices is a very common reality. In order to cater for this need many different information and recommendation strategies have been developed. Recommendation Systems is one of these.Recommendation Systems try to help the user, presenting him those objects he could be more interested in, based on his known preferences or on those of other users with similar characteristics.This document tries to present the current situation with regards to Recommendation Systems and their application on distance education over the Internet.     

Human performance evaluation of user interfaces for spatially-constrained text portrayal and access

To maximize visualization effectiveness, graphical data are commonly augmented with text to provide detailed information and define specific values. This text is often displayed in a pop-up dialog box pertaining to an object, permitting simultaneous display of the object and associated alphanumeric information. However, a human operator performance cost may be incurred when the resulting portrayal occludes critical information within the visualization. To address this issue, we developed and evaluated three alternative, spatially constrained, text portrayal techniques. These techniques and their associated access interface were designed to reduce occlusion while providing rapid access to desired alphanumeric data. Each technique was evaluated against the pop-up dialog using a dual-task human performance paradigm. Performance measures included accuracy, response time, display occlusion, and subjective feedback. The basis for the spatially-constrained text access technique design, their implementation affordances, and limitations are discussed. The alternative techniques and their user interface concepts resulted in mixed accuracy and response time performance compared to the pop-up dialog. Specific design features reduced data access time to one third of the time required to access the spatially-constrained text access techniques. Overall, equivalent performance was obtained among the variants while the potential for occlusion was reduced during use of the novel designs.     

Usability risk level evaluation for physical user interface of mobile phone

The mobile phone has become an indispensable device in everyday life. However, many usability problems were generated by the multi-functionality of mobile phones. There was an important increase on the user interface (UI) design and usability. With the introduction of a variety of forms and keypads in mobile phones, the user's need of controllability, grip-stability, and usability were raised in the UI aspect. Therefore, in this study, we investigated the physical user interface (PUI) elements of mobile phones, and defined the degree of usability risk such as key level value, function level value, and grip level value. Also, this study proposed an evaluation framework to quantitatively measure the usability risk in the mobile phone PUI elements. For this, the mobile phone PUI elements were analyzed and classified by key type, function, and form-factor. Hence, in the case study was investigated and evaluated 133 mobile phones in the market by the proposed framework. As a result, the proposed evaluation framework enabled the measurement of the mobile phone usability risk level in the early stages of the concept design. This made possible the prediction of design problems related with the mobile phone PUI.     

Re-examining information systems user performance: Using data mining to identify properties of IS that lead to highest levels of user performance

As competitive pressures increase, managers try to realize every bit of productivity from people, business processes and new information technologies (IT). This leads one to ask, how can managers configure information systems to achieve higher levels of performance from end users? In this regard, managers continually seek advice on how to meet the promises and expectations of continued increases in productivity through the use of IT. However, results from research on how to achieve higher performance through the use of IT in organizations has been mixed. Consequently, it has been difficult for IS researchers to give managers any advice on investing in specific aspects of IS that would lead to the highest performance possible. We focus on this question in this research. We use a data mining approach to tease out information about specific characteristics of IS that managers can manipulate to achieve desired outcomes with regards to individual performance. Our findings offer both researchers and managers significant new knowledge that can make a difference to IT user performance research theory and the practice of user performance management. Further, our research method offers a novel approach to linking theory and practice in IS research, a problem that is of great concern to many IS researchers. The approach is generalized and can be implemented by academic or industry researchers who are interested in generating hypotheses from data for the purpose of theoretical or applied research.     

Effectiveness of user testing and heuristic evaluation as a function of performance classification

For different levels of user performance, different types of information are processed and users will make different types of errors. Based on the error's immediate cause and the information being processed, usability problems can be classified into three categories. They are usability problems associated with skill-based, rule-based and knowledge-based levels of performance. In this paper, a user interface for a Web-based software program was evaluated with two usability evaluation methods, user testing and heuristic evaluation. The experiment discovered that the heuristic evaluation with human factor experts is more effective than user testing in identifying usability problems associated with skill-based and rule-based levels of performance. User testing is more effective than heuristic evaluation in finding usability problems associated with the knowledge-based level of performance. The practical application of this research is also discussed in the paper.     

Integrated framework of risk evaluation and risk allocation with bounded data

This paper presents an integrated framework for risk evaluation and risk allocation with bounded data in a critical risk management. A risk evaluation framework using the Imprecise Data Envelopment Analysis (IDEA) method is proposed to be applied to operations of Korean Army helicopters. The risks pertaining to pilots, missions and helicopters are evaluated based on bounded data, and pilots are appropriately allocated to missions and helicopters using goal programming with bounded risk scores. Using bounded data, two risk allocation models are developed to be used with the expected value and lower/upper limit values, resulting in improved reliability of the solutions. Numerical experiments show reasonable solutions and valuable information for risk management.     

基于用户兴趣度的数据归约效果评估方法

面对特定数据归约方案,不同的用户对归约效果具有不同的评价,针对目前数据归约效果评估方法缺乏针对性、忽视用户个性化需求的问题,基于现有的指标体系,提出基于用户兴趣度的数据归约效果评估方法。通过定义用户兴趣度的权重子空间,根据用户对数据集归约方案评价的历史数据计算用户对指标的偏好,利用蒙特卡洛仿真近似计算出用户对数据归约效果的可接受程度作为评估归约效果的参数,实现面向不同用户的数据归约效果评估方法,为面向不同关注点的系统用户推荐不同数据归约方案提供定量依据。     

基于用户QoE的流媒体系统性能测评模型设计

影响流媒体用户服务质量体验QoE(Quality of Experience)的因素有很多,如何对用户QoE进行量化判别是一个复杂的问题。为此,以媒体传输指标MDI为基础,研究了用于测量流媒体用户QoE的基本指标,并提出了相关测量数据的获取方法。以流媒体用户的实际体验质量为依据,提出了一种有效的流媒体系统性能评价模型,该模型为流媒体系统的性能分析和优化调整提供了理论基础,具有广泛的应用价值。     

Modelling user preferences and mediating agents in electronic commerce

An important ingredient in agent-mediated electronic commerce is the presence of intelligent mediating agents that assist electronic commerce participants (e.g. individual users, other agents, organisations). These mediating agents are in principle autonomous agents that interact with their environments (e.g. other agents and web-servers) on behalf of participants who have delegated tasks to them. For mediating agents a (preference) model of participants is indispensable. In this paper, a generic mediating agent architecture is introduced. Furthermore, we discuss our view of user preference modelling and its need in agent-mediated electronic commerce. We survey the state of the art in the field of preference modelling and suggest that the preferences of electronic commerce participants can be modelled by learning from their behaviour. In particular, we employ an existing machine learning method called inductive logic programming (ILP). We argue that this method can be used by mediating agents to detect regularities in the behaviour of the involved participants and induce hypotheses about their preferences automatically. Finally, we discuss some advantages and disadvantages of using inductive logic programming as a method for learning user preferences and compare this method with other approaches.     

Facilitating data exploration with query previews: a study of user performance and preference

Networked and local data exploration systems that use command languages, menus, or form fill-in interfaces rarely give users an indication of the distribution of data. This often leads users to waste time, posing queries that have zero-hit or mega-hit results. Query previews are a novel visual approach for browsing databases. Query previews supply users with data distribution information for selected attributes of the database, and give continuous feedback about the size of the result set as the query is being formed. Subsequent refinements might be necessary to narrow the search. As there is a risk that query previews are an additional step, leading to a more complex and slow search process, a within-subjects empirical study was ran with 12 subjects who used interfaces with and without query previews and with minimized network delays. Even with 12 subjects and minimized network delays statistically significant differences were found, showing that query previews could speed up performance 1.6 to 2.1 times and lead to higher user satisfaction.     

Facilitating data exploration with query previews: A study of user performance and preference

Networked and local data exploration systems that use command languages, menus, or form fill-in interfaces rarely give users an indication of the distribution of data. This often leads users to waste time, posing queries that have zero-hit or mega-hit results. Query previews are a novel visual approach for browsing databases. Query previews supply users with data distribution information for selected attributes of the database, and give continuous feedback about the size of the result set as the query is being formed. Subsequent refinements might be necessary to narrow the search. As there is a risk that query previews are an additional step, leading to a more complex and slow search process, a within-subjects empirical study was ran with 12 subjects who used interfaces with and without query previews and with minimized network delays. Even with 12 subjects and minimized network delays statistically significant differences were found, showing that query previews could speed up performance 1.6 to 2.1 times and lead to higher user satisfaction.     

Healthcare data warehousing and quality assurance

Healthcare data warehousing presents unique challenges. The industry is rife with often incompatible medical standards and coding schemes that require careful translation. Healthcare data comes from many sources and is delivered in many forms, including published books, individual spreadsheets, and several tape or data formats. Results derived from a healthcare data warehouse must be delivered in accessible form to diverse stakeholders, including healthcare regulators, physicians, hospital administrators, consumers, community activists, and members of the popular press. The industry's widely decentralized and largely autonomous data collection efforts make data quality a significant challenge. Finally, the sensitivity of healthcare data makes privacy and security issues paramount. Healthcare data warehousing will make rigorous, quantitative information available to healthcare decision makers. The authors describe a fully functional healthcare data warehouse used to produce several reports for communities throughout Florida. Building on this work, they're actively pursuing a research agenda to enhance technical data warehousing capabilities while investigating innovative community and clinical healthcare applications     

Mapping of user interfaces on electronic appliances

The purpose of this study was to investigate mapping of user interfaces on consumer electronic appliances. A digital clock with five different interface modes was chosen for the experiment. Forty elderly subjects (above 65 years) and 40 middle-aged subjects (45-64 years) participated in the study. Every subject had to complete three different tasks, namely time setting, alarm time setting and date setting. The researchers investigated what problems were encountered when performing these tasks and collected data such as operational time, the number of total inputs, subjective estimation and interview information. The findings of this study indicated that the interface modes had significant effects on operational time, the number of total inputs and subjective estimation. Finally, the study confirms that when the spatial relationship between buttons and display contents are clearly indicated, the operation is easier to complete.     

A structural model of end user computing satisfaction and user performance

The proliferation of end user computing has necessitated the development of reliable and valid instruments that measure satisfaction in this environment and evaluate its success when used in improving user performance. An instrument for measurement of end user computing satisfaction (EUCS) is developed. Using exploratory factor analysis, six attitudinal dimensions for measurement of EUCS are first identified. Structural equation modelling techniques are then used to explore the relationship between EUCS and user performance. It is shown that the six attitudinal dimensions of EUCS account for a significant portion of the variation in user performance.     

Mining interests for user profiling in electronic conversations

The increasing amount of Web-based tasks is currently requiring personalization strategies to improve the user experience. However, building user profiles is a hard task, since users do not usually give explicit information about their interests. Therefore, interests must be mined implicitly from electronic sources, such as chat and discussion forums. In this work, we present a novel method for topic detection from online informal conversations. Our approach combines: (i) Wikipedia, an extensive source of knowledge, (ii) a concept association strategy, and (iii) a variety of text-mining techniques, such as POS tagging and named entities recognition. We performed a comparative evaluation procedure for searching the optimal combination of techniques, achieving encouraging results.     

Using multiple data sources to get closer insights into user cost and task performance

This pilot study explores the use of combining multiple data sources (subjective, physical, physiological, and eye tracking) in understanding user cost and behavior. Specifically, we show the efficacy of such objective measurements as heart rate variability (HRV), and pupillary response in evaluating user cost in game environments, along with subjective techniques, and investigate eye and hand behavior at various levels of user cost. In addition, a method for evaluating task performance at the micro-level is developed by combining eye and hand data. Four findings indicate the great potential value of combining multiple data sources to evaluate interaction: first, spectral analysis of HRV in the low frequency band shows significant sensitivity to changes in user cost, modulated by game difficulty—the result is consistent with subjective ratings, but pupillary response fails to accord with user cost in this game environment; second, eye saccades seem to be more sensitive to user cost changes than eye fixation number and duration, or scanpath length; third, a composite index based on eye and hand movements is developed, and it shows more sensitivity to user cost changes than a single eye or hand measurement; finally, timeline analysis of the ratio of eye fixations to mouse clicks demonstrates task performance changes and learning effects over time. We conclude that combining multiple data sources has a valuable role in human–computer interaction (HCI) evaluation and design.     

A user interface evaluation environment using synchronized video,visualizations and event trace data

This paper presents a simple but very powerful technique to support user interface evaluation along with a prototype open environment — I-Observe, the Interface OBServation, Evaluation, Recording, and Visualization Environment. I-Observe's technique requires recording user interface sessions in multiple modalities, both as a trace of interesting events and through video images. It provides tools to allow the user interface evaluator either to analyze and visualize the event tracer data, or to combine the event trace and video modalities. The analyst using I-Observe can search the event stream for patterns of interesting or important user actions, then use the recorded timestamps associated with these actions to present only the sections of the video recording of interest. This allows the analyst to study, for example, all places where the user invokes a help system or a particular command to be observed, without manually searching the recording or sitting through long sessions of unrelated interactions. By combining the precise recording of automatic event trace capture with the rich contextual information that can be captured in a video and audio recording, this technique allows analyses to be performed that would not be practical with either media alone.