Search results

As internet banking service marketing platforms continue to advance, customers exhibit distinct behaviors. Given the extensive array of options and minimal barriers to switching to competitors, the concept of customer churn behavior has emerged as a subject of considerable debate. This study aims to delineate the scope of feature optimization methods for elucidating customer churn behavior within the context of internet banking service marketing. To achieve this goal, the author aims to predict the attrition and migration of customers who use internet banking services using tree-based classifiers.

The author used various feature optimization methods in tree-based classifiers to predict customer churn behavior using transaction data from customers who use internet banking services. First, the authors conducted feature reduction to eliminate ineffective features and project the data set onto a lower-dimensional space. Next, the author used Recursive Feature Elimination with Cross-Validation (RFECV) to extract the most practical features. Then, the author applied feature importance to assign a score to each input feature. Following this, the author selected C5.0 Decision Tree, Random Forest, XGBoost, AdaBoost, CatBoost and LightGBM as the six tree-based classifier structures.

This study acclaimed that transaction data is a reliable resource for elucidating customer churn behavior within the context of internet banking service marketing. Experimental findings highlight the operational benefits and enhanced customer retention afforded by implementing feature optimization and leveraging a variety of tree-based classifiers. The results indicate the significance of feature reduction, feature selection and feature importance as the three feature optimization methods in comprehending customer churn prediction. This study demonstrated that feature optimization can improve this prediction by increasing the accuracy and precision of tree-based classifiers and decreasing their error rates.

This research aims to enhance the understanding of customer behavior on internet banking service platforms by predicting churn intentions. This study demonstrates how feature optimization methods influence customer churn prediction performance. This approach included feature reduction, feature selection and assessing feature importance to optimize transaction data analysis. Additionally, the author performed feature optimization within tree-based classifiers to improve performance. The novelty of this approach lies in combining feature optimization methods with tree-based classifiers to effectively capture and articulate customer churn experience in internet banking service marketing.

Business analytics (BA) is a new frontier of technology development and has enormous potential for value creation. Information systems research shows ample evidence of its positive business impacts and organizational performance. However, there is limited understanding of how decision-makers or users of BA outcomes actually engage with data analysts in the process of data-driven insight generation and how they improve their understanding of business environments using BA outcomes. To aid this engagement and understanding, this study investigates the interaction between decision-makers and data analysts when they attempt to uncover data capacities and business needs and acquire business insights from BA tools.

This study employs an interpretive field study with thematic analysis. The authors conducted interviews with 31 participants who all relied on BA in their daily decisions. The study participants were engaged in different BA roles, including data analysts and decision-makers. They validated the applicability and usefulness of our findings through a focus group with eight practitioners, including decision-makers and data analysts from the same companies.

This study proposes a process model of data-driven sensemaking and sensegiving based on Weick’s sensemaking framework. The findings exhibit that decision-makers are engaged in sensemaking by identifying areas of focus, determining BA scope, evaluating generated insights and turning BA into action. The findings also show that data analysts engage in sensemaking by consolidating data, data understanding, preparing preliminary outcomes and generating actionable reports. This study shows how sensemaking processes and sensegiving activities work together over time through immediate enactment, selection and decision cycles.

This study is a first attempt to understand interactions in the context of BA using the perspective of sensemaking and sensegiving.

This study aims to investigate the adoption and use of electronic health record systems (EHRS) in Tanzanian public primary healthcare institutions. The study’s objectives include understanding the factors that affect EHRS adoption, identifying implementation challenges and evaluating the effect of EHRS usage on healthcare delivery. By addressing these research goals, the study aims to contribute insightful information on the current level of EHRS adoption in Tanzanian primary healthcare facilities and contribute to developing strategies to improve EHRS deployment and healthcare in the nation.

This study combined quantitative and qualitative data using a mixed-methods methodology. Both data types were collected and analysed concurrently using a concurrent triangulation approach. The study aimed to comprehend the variables that affect the adoption and use of EHRS in Tanzanian public primary healthcare institutions. Eleven regions spanning various geographic locations and urban–rural dynamics were chosen as research sites. A survey of 122 healthcare employees was conducted with a sample of 31 healthcare facilities. The questionnaire had closed-ended and open-ended questions to gather quantitative and qualitative data. Descriptive statistics and thematic analysis were used in data analysis. Throughout the investigation, ethical standards and confidentiality precautions were observed.

Several factors affect the adoption and use of EHRS. Perceived usefulness and use, support and training, interoperability, data security and privacy, business culture and leadership are all factors. Inadequate infrastructure, power interruptions, duplication of effort and a lack of data analytic expertise were among the difficulties. Among the effects were improvements in data management, service delivery and coordination, productivity and efficiency, medical supply inventory control, billing and revenue collection.

This study, which complements earlier research that has concentrated chiefly on specialised healthcare settings, gives new insights by investigating the adoption and utilisation of EHRS, especially in primary healthcare institutions. The findings give policymakers and healthcare professionals in Tanzania and other nations vital information to help them decide whether to embrace and use EHRS in primary healthcare.

The energy generation process through photovoltaic (PV) panels is contingent upon uncontrollable variables such as wind patterns, cloud cover, temperatures, solar irradiance intensity and duration of exposure. Fluctuations in these variables can lead to interruptions in power generation and losses in output. This study aims to establish a measurement setup that enables monitoring, tracking and prediction of the generated energy in a PV energy system to ensure overall system security and stability. Toward this goal, data pertaining to the PV energy system is measured and recorded in real-time independently of location. Subsequently, the recorded data is used for power prediction.

Data obtained from the experimental setup include voltage and current values of the PV panel, battery and load; temperature readings of the solar panel surface, environment and the battery; and measurements of humidity, pressure and radiation values in the panel’s environment. These data were monitored and recorded in real-time through a computer interface and mobile interface enabling remote access. For prediction purposes, machine learning methods, including the gradient boosting regressor (GBR), support vector machine (SVM) and k-nearest neighbors (k-NN) algorithms, have been selected. The resulting outputs have been interpreted through graphical representations. For the numerical interpretation of the obtained predictive data, performance measurement criteria such as mean absolute error (MAE), mean squared error (MSE), root mean squared error (RMSE) and R-squared (R²) have been used.

It has been determined that the most successful prediction model is k-NN, whereas the prediction model with the lowest performance is SVM. According to the accuracy performance comparison conducted on the test data, k-NN exhibits the highest accuracy rate of 82%, whereas the accuracy rate for the GBR algorithm is 80%, and the accuracy rate for the SVM algorithm is 72%.

The experimental setup used in this study, including the measurement and monitoring apparatus, has been specifically designed for this research. The system is capable of remote monitoring both through a computer interface and a custom-developed mobile application. Measurements were conducted on the Karabük University campus, thereby revealing the energy potential of the Karabük province. This system serves as an exemplary study and can be deployed to any desired location for remote monitoring. Numerous methods and techniques exist for power prediction. In this study, contemporary machine learning techniques, which are pertinent to power prediction, have been used, and their performances are presented comparatively.

This paper aims to demonstrate how the design of data visualisations can act as a tool to support social marketing messages in prompting behaviour change to reduce food waste using the Elaboration Likelihood Model (ELM) as a theoretical framework. It also responds to a lack of consumer-led insight to develop campaigns in reducing food waste.

The research uses data collected by the End Food Waste Cooperative Research Centre (EFW CRC) in Australia to determine which text-based campaign messages are most likely to prompt people toward reducing food waste. Behaviour change messages were first identified through workshops with 11 food waste experts, then explored through online focus group discussions with 18 participants from three food-wasting market segments. The messages were further tested via a quantitative survey among 1,000 decision makers in Australian households in their own homes, with the top three performing messages examined using summative content analysis.

The significant findings were that participants want to see 1) evidence of how adopting new behaviours would lead to financial savings and benefit the environment, and 2) concrete steps to reduce food waste. When examined through the ELM, the findings suggest that tools that encourage both cognitive and peripheral processing as a means of persuasion, like data visualisations, may be useful for changing food-wasting behaviours.

Applying principles from the field of communication design to the ELM has uncovered the potential for a cross-disciplinary approach to enhance theoretical frameworks for understanding consumer engagement with messages. This process in turn, may lead to the development of more effective behaviour change marketing strategies.

Six principles for using data visualisations in a social marketing campaign are proposed: personal relevance, ease of use, emotional storytelling, context, prioritising the message itself and long-term usage.

This study proposes that data visualisations could enhance the effectiveness of social marketing campaigns by leveraging consumer-derived insights and the persuasive capacity inherent in their theoretical underpinnings.

Information systems (IS) research in general and health IS studies, in particular, are prone to a positivity bias – largely focusing on upside gains rather than the potential misuse practices. This paper aims to explore failures in health IS use and shortcomings in data privacy and cybersecurity and to provide an explanatory model for health record misuse.

This research is based on four data sets that we collected through a longitudinal project studying digital health (implementation, use and evaluation), interviews with experts (cybersecurity and digital health) and healthcare stakeholders (health professionals and managers). We applied qualitative analysis to explain health records misuse from a sociotechnical perspective.

We propose a contextualized model of “health records misuse” with two overarching dimensions: data misfit and improper data processing. We explain sub-categories of data misfit: availability misfit, meaning misfit and place misfit, as well as sub-categories of improper data processing: improper interaction and improper use-related actions. Our findings demonstrate how health records misuse can emerge in sociotechnical health systems and impact health service delivery and patient safety.

Through contextualizing system misuse in healthcare, this research advances the understanding of ineffective use and failures in health data protection practices. Our proposed theoretical model provides explanations for unique patterns of IS misuse in healthcare, where data protection failures are consequential for healthcare organizations and patient safety.

Industrial simulations of turbulent flows often rely on Reynolds-averaged Navier-Stokes (RANS) turbulence models, which contain numerous closure coefficients that need to be calibrated. This paper aims to address this issue by proposing a semi-automated calibration of these coefficients using a new framework (referred to as turbo-RANS) based on Bayesian optimization.

The authors introduce the generalized error and default coefficient preference (GEDCP) objective function, which can be used with integral, sparse or dense reference data for the purpose of calibrating RANS turbulence closure model coefficients. Then, the authors describe a Bayesian optimization-based algorithm for conducting the calibration of these model coefficients. An in-depth hyperparameter tuning study is conducted to recommend efficient settings for the turbo-RANS optimization procedure.

The authors demonstrate that the performance of the k-ω shear stress transport (SST) and generalized k-ω (GEKO) turbulence models can be efficiently improved via turbo-RANS, for three example cases: predicting the lift coefficient of an airfoil; predicting the velocity and turbulent kinetic energy fields for a separated flow; and, predicting the wall pressure coefficient distribution for flow through a converging-diverging channel.

To the best of the authors’ knowledge, this work is the first to propose and provide an open-source black-box calibration procedure for turbulence model coefficients based on Bayesian optimization. The authors propose a data-flexible objective function for the calibration target. The open-source implementation of the turbo-RANS framework includes OpenFOAM, Ansys Fluent, STAR-CCM+ and solver-agnostic templates for user application.

Norway, like other welfare states, seeks to leverage data to transform its pressured public healthcare system. While managers will be central to doing so, we lack knowledge about how specifically they would do so and what constraints and expectations they operate under. Public sources, like the Norwegian policy documents investigated here, provide important backdrops against which such managerial work emerges. This article therefore aims to analyze how key Norwegian policy documents construe data use in health management.

We analyzed five notable policy documents using a “practice-oriented” framework, considering these as arenas for “organizing visions” (OVs) about managerial use of data in healthcare organizations. This framework considers documents as not just texts that comment on a topic but as discursive tools that formulate, negotiate and shape issues of national importance, such as expectations about data use in health management.

The OVs we identify anticipate a bold future for health management, where data use is supported through interconnected information systems that provide relevant information on demand. These OVs are similar to discourse on “evidence-based management,” but differ in important ways. Managers are consistently framed as key stakeholders that can benefit from using secondary data, but this requires better data integration across the health system. Despite forward-looking OVs, we find considerable ambiguity regarding the practical, social and epistemic dimensions of data use in health management. Our analysis calls for a reframing, by moving away from the hype of “data-driven” health management toward an empirically-oriented, “data-centric” approach that recognizes the situated and relational nature of managerial work on secondary data.

By exploring OVs in the Norwegian health policy landscape, this study adds to our growing understanding of expectations towards healthcare managers' use of data. Given Norway's highly digitized health system, our analysis has relevance for health services in other countries.

It has become increasingly clear that the objectives of privacy and competition policy are in conflict with one another with regard to platform data. While privacy policies aim at limiting the use of platform data for purposes other than those for which the data were collected in order to protect the privacy of platform users, competition policy aims at making such data widely available in order to curb the power of platforms.

We draw on Commons' Institutional Economics to contrast the current control-based approaches to ensuring the protection as well as the sharing of platform data with an ownership approach. We also propose the novel category of platform use data and contrast this with the dichotomy of personal/non-personal data which underlies current regulatory initiatives.

We find that current control- and ownership-based approaches are ineffective with regard to their capacity to balance these conflicting objectives and propose an alternative approach which makes platform data saleable. We discuss this approach in view of its capacity to balance the conflicting objectives of privacy and competition policy and its effectiveness in supporting each separately.

Our approach clarifies the fundamental difference between data markets and other concepts such as data exchanges.

The purpose of this paper is to analyse data literacy in the new Digital Competence Framework for Citizens (DigComp 2.2). Mid-2022 the Joint Research Centre of the European Commission published a new version of the DigComp (EC, 2022). This new version focusses more on the datafication of society and emerging technologies, such as artificial intelligence. This paper analyses how DigComp 2.2 defines data literacy and how the framework looks at this from a societal lens.

This study critically examines DigComp 2.2, using the data literacy competence model developed by the Knowledge Centre for Digital and Media Literacy Flanders-Belgium. The examples of knowledge, skills and attitudes focussing on data literacy (n = 84) are coded and mapped onto the data literacy competence model, which differentiates between using data and understanding data.

Data literacy is well-covered in the framework, but there is a stronger emphasis on understanding data rather than using data, for example, collecting data is only coded once. Thematically, DigComp 2.2 primarily focusses on security and privacy (31 codes), with less attention given to the societal impact of data, such as environmental impact or data fairness.

Given the datafication of society, data literacy has become increasingly important. DigComp is widely used across different disciplines and now integrates data literacy as a required competence for citizens. It is, thus, relevant to analyse its views on data literacy and emerging technologies, as it will have a strong impact on education in Europe.