Decision Support Systems Research Research Articles

Explainable Learning Analytics: Assessing the stability of student success prediction models by means of explainable AI

Beyond managing student dropout, higher education stakeholders need decision support to consistently influence the student learning process to keep students motivated, engaged, and successful. At the course level, the combination of predictive analytics and self-regulation theory can help instructors determine the best study advice and allow learners to better self-regulate and determine how they want to learn. The best performing techniques are often black-box models that favor performance over interpretability and are heavily influenced by course contexts. In this study, we argue that explainable AI has the potential not only to uncover the reasons behind model decisions, but also to reveal their stability across contexts, effectively bridging the gap between predictive and explanatory learning analytics (LA). In contributing to decision support systems research, this study (1) leverages traditional techniques, such as concept drift and performance drift, to investigate the stability of student success prediction models over time; (2) uses Shapley Additive explanations in a novel way to explore the stability of extracted feature importance rankings generated for these models; (3) generates new insights that emerge from stable features across cohorts, enabling teachers to determine study advice. We believe this study makes a strong contribution to education research at large and expands the field of LA by augmenting the interpretability and explainability of prediction algorithms and ensuring their applicability in changing contexts.

Image-Mining-Based Decision Support Systems: Design Knowledge and its Evaluation in Tool Wear Analysis

Many decision processes are based on image analysis, for instance, medical diagnoses or visual monitoring of industrial processes. At the same time, advances in deep learning have significantly improved information extraction from images. While recent research strongly focuses on extracting information from single images, the potential of mining entire image collections for decision processes has been neglected so far. In this work, we develop design knowledge to use image collections for improved decision-making. We derive design requirements for image-mining-based decision support systems from literature and expert interviews. Drawing on research in image mining and decision support systems, we conceptualize design principles to address the design requirements. Subsequently, we instantiate and evaluate them in the machining industry with the help of an artifact to support tool wear analysis. The results prove the validity of our design knowledge. Our study contributes to research and practice by deriving nascent design knowledge for image-mining-based decision support systems.

Research and Development of Decision Support System for Tourism Management Based on Big Data Analysis

Abstract With the continuous expansion and change of the tourism market, the massive amount, complexity and dynamic change of tourism data make the establishment of tourism management decision support system has become an important issue in the tourism industry. In this paper, we use the plain Bayesian classification algorithm, the improved Apriori association algorithm, and the gray GM(1, N) prediction model to mine and process the tourism big data and combine the 3S technology and the Agent-based knowledge representation technology to realize the construction of the tourism management decision support system based on big data analysis, and make the optimal decision for the planning of tourist attractions and routes. The attraction classification method’s accuracy rate is 72.98%, and its feasibility is high. The integrated error of the adopted GM(1,7) model is only 2.587%, which is smaller than the 3.483% of the GM(1,1) model and the 4.594% of the linear regression model, and the model accuracy is high. The average response time and average TPS of the system are 8.70s and 15.89s, respectively, which generally meet the demand for the system’s processing capability. This study provides a reference for the construction of a decision support system for tourism management.

Feed Selection Decision Support System The Best Cat uses the Analytical Hierarchy Process Method

With the development of technology and increasingly rapid competition in the business world, just opening a Cat Shop is not enough. To win the competition, technology and research are used to overcome the problem of consumers who are confused about choosing the type of food for their cats, because there are many types of cats and cat food available. circulating in the market today.. Cat Shop is a business that provides various kinds of pet needs, such as pet food, animal equipment and animal accessories. The Cat Shop sells various products to the public. Cat Shop currently has a share of the pet market in big cities in Indonesia. This decision support system research uses the Analytical Hierarchy Process (AHP) method. The AHP method is a method that is widely used in the case of weighting criteria and prioritizing each criterion. After this research was applied, the results were able to answer the information needs regarding the selection of the best cat food, it has been able to answer and assist in solving the problem of choosing the best cat food purchase

PROCESS MODEL FOR THE THEORETICAL FRAMEWORK OF MANAGEMENT DECISIONS SUPPORT SYSTEMS

The article examines how the correct use of management decision-making tools helps enterprises achieve their short- and long-term goals. This will allow managers to make balanced decisions that will primarily benefit the enterprise or organization. It will also allow a comprehensive approach to solving the problems that arise in their activities. It has been established that the management decision support system is a multifunctional tool that requires detailed analysis in high-quality journals. The history of the management decision support system was analyzed. It was found that the vast majority of domestic scientists research applied aspects of developments in the field of management decision support systems. And the first scientific works were based on experimental research. It is noted that the first experimental studies were based on creating a decision-making environment. The need to introduce a management decision support system into the activities of institutions and organizations has been revealed. A process model of the theoretical foundations of the management decision support system and strategies for improving the research of the management decision support system are proposed. Its main components are described, and the main implementation problems are identified. It has been established that any constructed model or process model of management decision support system theoretical foundations contains appropriate components that must be applied comprehensively. These components have their own characteristics and are used in different situations. For their application, it is necessary to implement actions of a different nature. First of all, it is obtaining timely, complete, and high-quality information through the interaction of the software complex with available management information. A management decision support system requires a significant number of experts in the chosen field of knowledge who can manage data and process it in large quantities. Accordingly, the more complete the information, the greater the chance of making the right management decision, which can affect the further activities of the enterprise or organization.

Marketing Decision Support System Based on Data Mining Technology

With the continuous development of business intelligence technology, the application research of decision support systems (DSSs) is deepening. In China, the work in this area started relatively late, and there are few DSS research cases to assist in marketing decision-making. Currently, marketing decision support systems have shortcomings in data integration, historical data, query functions, and data analysis. This article analyzes the characteristics of marketing decision-making, discusses the application of data warehouse, OLAP, and data mining technology in marketing decision support systems, and designs a marketing decision support system based on data mining technology. The system uses a BP neural network to conduct data mining marketing forecasting. A three-layer network model for marketing prediction is established, with sales time, product price, and customer purchasing power as network inputs and output as the sales volume of a certain type of product in different locations. The test results show that the average absolute percentage error of this method is 15.13%, and the prediction accuracy is high. Research shows that with the continuous development of data mining technology, the system cannot only help users conduct scientific and reasonable marketing decision-making analyses, making the marketing decision-making process more scientific and reasonable, but also can bring new ideas to enterprise decision-makers, promoting the continuous improvement and progress of the system.

A decision support framework to incorporate textual data for early student dropout prediction in higher education

Managing student dropout in higher education is critical, considering its substantial impacts on students' lives, academic institutions, and society as a whole. Using predictive modeling can be instrumental for this task, as a means to identify dropouts proactively on the basis of student characteristics and their academic performance. To enhance these predictions, textual student feedback also might be relevant; this article proposes a hybrid decision support framework that combines predictive modeling with student segmentation efforts. A real-life data set from a French higher education institution, containing information of 14,391 students and 62,545 feedback documents, confirms the superior performance of the proposed framework, in terms of the area under the curve and top decile lift, compared with various benchmarks. In contributing to decision support system research, this study (1) proposes a new framework for automatic, data-driven segmentation of students based on textual data; (2) compares multiple text representation methods and confirms that incorporating student textual feedback data improves the predictive performance of student dropout models; and (3) establishes useful insights to help decision-makers anticipate and manage student dropout behaviors.

Modeling SCOPUS Trend of Decision Support Systems in Energy: A Bibliometric Analysis

The purpose of this article is to provide a bibliometric analysis from SCOPUS database for identifying the current trending of decision support system (DSS) research on energy . The search resulted in 1458 documents that had been published in field computer science, 569 documents in field engineering, 437 documents in field mathematics, 223 documents in field decision sciences and 105 documents in field energy . The development of scientific research in the area of DSS in the context of energy is consistently growing since 2001 until recent year. It is of utmost necessity to identify the potential areas as well as the severity of this research. Thus, the aim of this study is to model the research trend on DSS for energy by conducting bibliometric analysis in Scopus database. The analysis was performed by using the VOSviewer software and data analysis tool available in the Scopus base. A total of 1458 publications in relation to DSS related energy, were extracted from Scopus database ranging from 2001 to 2021 for further modeling. Co-citation analysis and co-word analysis were conducted to model the evolution of research themes in this field. The findings of this study may help researchers understand the nature of DSS research related to energy from across the world and suggest future research directions.

An Analysis of Clustering the Decision Support Systems in Logistics for Supply Chain Management

Decision-making in logistics is becoming increasingly complex task for businesses such as agriculture, food production, and construction, as it requires decisions at the strategic, tactical, and operational levels, as well as consideration of the triple bottom line. Undoubtedly, decision support systems (DSS) played a crucial role in resolving the difficulties related with decision-making in sustainable logistics. The objective of this work is to investigate the status of research in the domain of DSS for logistics, taking sustainability into account. It is of the utmost importance to determine the prospective areas and significance of this research. By doing a bibliometric analysis, the purpose of this study is to illustrate the scientific research on the Decision Support System in Logistics. Using the Scopus database's VOSviewer programme and data analysis tool, the analysis was conducted. From 1985 to 2022, a total of 1091 papers on DSS and logistics connected to consumers were retrieved from the Scopus database. To show the progression of research ideas in this discipline, co-citation analysis and co-word analysis were undertaken. Transportation decision-making, decision analysis, and intelligence algorithm have been identified as the three primary study clusters relevant to the current research interest. This study's findings may assist researchers in comprehending the nature of Decision Support System research pertaining to logistics from around the world and in determining future research directions.

Data Visualization of Decision Support Systems Research in Sustainability: A Bibliometric Analysis

The development of scientific research for decision support system in the area of sustainability is growing steadily from 1991 with an increasing trend up to 2022. It is of utmost necessity to identify the potential areas as well as the severity of this research. Thus, the aim of this study is to visualize the scientific research on decision support system on sustainability by conducting bibliometric analysis. The data visualization was performed using the VOSviewer software and data analysis tool available in the Scopus database. A total of 1736 publications in relation to decision support system review related to sustainability, were extracted from Scopus database ranging from 1991 to 2022. Co-citation analysis and co-word analysis were conducted to visualize the evolution of research themes in this field. Four main clusters were identified which mainly related to decision support system applications, decision approach, environmental aspect and water management. The findings of this study help researchers to understand the nature of decision support system research in sustainability from across the world and suggest future research directions.

Med-BERT: A Pretraining Framework for Medical Records Named Entity Recognition

A large amount of data is generated every day with the development of Internet medical care, which is of great significance for the clinical decision support system and medical real-world research. Medical records named entity recognition (NER) is important on the aforementioned research topics under the premise of protecting patients’ private information. In this article, we propose a medical dictionary enhanced bidirectional encoder representations from transformers (BERT), dubbed Med-BERT, to achieve better representations of long medical entities. On Med-BERT, we propose a span flat-lattice transformer (Span-FLAT) method on medical records NER, and the entity types include private information such as names and addresses, as well as medical information such as patient symptoms, signs, and diseases. Experimental results on two benchmark medical datasets show the effectiveness of Med-BERT, and the proposed Med-BERT-based Span-FLAT method remarkably outperforms the state-of-the-art methods on medical NER task.

DSS research: a bibliometric analysis by gender

ABSTRACT This research-in-progress article uses a bibliometric approach to explore the research landscape by the gender of publishing authors in the Decision Support Systems (DSS) field over 10 years, from 2011 to 2020. The Web of Science (WOS) provides a valuable information resource on academic disciplines as it contains both the articles published and the articles cited. This research presents information on the gender breakdown of authors publishing on the topic of DSS globally. We examined publication trends over time, considering the main categories and research areas by authors’ gender. As a result, some initial recommendations to guide future research efforts of both DSS academics and practitioners are provided.

Support for cognition in decision support systems: an exploratory historical review

ABSTRACT Decision support systems (DSS) have been traditionally developed to assist with unstructured and semi-structured problems. Early DSS researchers explored a broad range of techniques for supporting human cognition as part of decision making. Cognition during decision making was viewed in terms of two competing, and sometimes cooperating, systems: one that was automatic and fast, and one that was deliberative and slow. The aim of this research is to trace historical studies on cognitive aspects of decision support and determine the theoretical underpinnings of DSS support for cognition. We analysed articles drawing on the seminal literature to derive the relevant dimensions, including the classical Gorry & Scott Morton (1989) framework. This analysis identified opportunities for future research relevant to providing better support for cognition by highlighting some design parameters for information systems.

A paradigm shift to ethical decision-making—incorporating systemic epistemology into complex socio-technical decision support systems research

ABSTRACT Current decision support systems (DSS) research is overwhelmingly positivist and limits the adequate representation of relevant stakeholders. This crisis of relevance precludes the systemic inclusion of social and ethical issues in complex socio-technical DSS designs. For their unstable boundary conditions, such systems also require explicit coverage of their dynamics. Lending a novel perspective to DSS research, this paper proposes a framework with the new decision-making paradigm and the systemic inquiry of boundary critique to explore stakeholder perspectives for more ethically-aware DSS development. Using qualitative research, the developed framework is applied to unleash ethical issues for a dynamic and complex socio-technical university timetabling scenario implemented as a web-based group decision support system. Multiple stakeholder perspectives are recognised and analysed for boundary judgements, while a dynamic stakeholder network considers boundary liquidity and emergence. This work aims to couple systemic epistemology with the socio-technical lens to encourage the inclusion of ethical dimensions in dynamic and complex DSS designs.

Bibliometrics analysis of clinical decision support systems research in nursing

Bibliometrics analysis of clinical decision support systems research in nursing

Designing clinically translatable artificial intelligence systems for high-dimensional medical imaging

The National Institutes of Health in 2018 identified key focus areas for the future of artificial intelligence in medical imaging, creating a foundational roadmap for research in image acquisition, algorithms, data standardization and translatable clinical decision support systems. Among the key issues raised in the report, data availability, the need for novel computing architectures and explainable artificial intelligence algorithms are still relevant, despite the tremendous progress made over the past few years alone. Furthermore, translational goals of data sharing, validation of performance for regulatory approval, generalizability and mitigation of unintended bias must be accounted for early in the development process. In this Perspective, we explore challenges unique to high-dimensional clinical imaging data, in addition to highlighting some of the technical and ethical considerations involved in developing machine learning systems that better represent the high-dimensional nature of many imaging modalities. Furthermore, we argue that methods that attempt to address explainability, uncertainty and bias should be treated as core components of any clinical machine learning system. Substantial advances have been made in the past decade in developing high-performance machine learning models for medical applications, but translating them into practical clinical decision-making processes remains challenging. This Perspective provides insights into a range of challenges specific to high-dimensional, multimodal medical imaging.

How to elicit and cease herding behaviour? On the effectiveness of a warning message as a debiasing decision support system

Behavioural economics has been argued to be a productive basis for decision support system (DSS) research. Whereas traditional economics assumes that individuals make decisions independently of others, behavioural economists have shown that humans tend to follow the crowd in their decisions (i.e., exhibit herding bias). However, the literature is silent on how convincing the information on the decisions of the crowd needs to be to elicit herding bias and on whether herding can be reduced (i.e., debiased) by presenting a warning message. This paper addresses both questions in the contexts of financial decisions that were guided by two DSSs in the form of simulation tools. In particular, we conduct a randomised controlled trial with 768 respondents randomly assigned to peer information. The results indicate that the intervention successfully elicited herding bias and that herding occurs when respondents are informed that at least 50% of other people made a particular decision. The results further show that a DSS in the form of a warning message is not sufficient to debias herding. In conclusion, these findings showed that individuals are easily influenced by erroneous peer information and that this effect is robust against debiasing using a warning message. Hence, DSS developers need to consider more intense debiasing strategies to overcome herding.

Sistem Pendukung Keputusan Penentuan Pemberian Insentif Pegawai THL Menggunakan Metode Promethee Pada Kantor Walikota Pematangsiantar

Pematangsiantar Mayor Office is an institution that is used and functions to serve and protect the community. This paper proposes a decision support system research using the Promethee method. Promethee is one of several methods of determining the order or priority in multi-criteria analysis. This writing uses the Promethee method as a step in determining the provision of incentives for freelance daily staff at the Pematangsiantar Mayor's Office. In this study the authors took 10 alternatives with 5 assessment criteria including absenteeism, achievement, behavior, long history of work and teamwork. With the highest result obtained by alternative 9 on behalf of Triono with a value of 0.422 and the lowest result obtained by alternative 6 on behalf of Soraya with a value of -0.211.

A Web-Based Decision Support System for Aircraft Dispatch and Maintenance

Aircraft dispatch involves determining the optimal dispatch option when an aircraft experiences an unexpected failure. Currently, maintenance technicians at the apron have limited access to support information and finding the right information in extensive maintenance manuals is a time-consuming task, often leading to technically induced delays. This paper introduces a novel web-based prototype decision support system to aid technicians during aircraft dispatch decision-making and subsequent maintenance execution. A system architecture for real-time dispatch decision support is established and implemented. The developed system is evaluated through a case study in an operational environment by licensed maintenance technicians. The system fully automates information retrieval from multiple data sources, performs alternative identification and evaluation for a given fault message, and provides the technician with on-site access to relevant information, including the related maintenance tasks. The case study indicates a potential time saving of up to 98% per dispatch decision. Moreover, it enables digitalization of the—currently mostly paper-based—dispatch decision process, thereby reducing logistics and paper waste. The prototype is the first to provide operational decision support in the aircraft maintenance domain and addresses the lack of correlation between theory and practice often found in decision support systems research by providing a representative case study. The developed custom parser for SGML-based documents enables efficient identification and extraction of relevant information, vastly contributing to the overall reduction of the decision time.

Research of artificial intelligence-based clinical decision support system for primary hepatocellular carcinoma

Objective: To apply artificial intelligence technology in clinical real-world data of patients with primary hepatocellular carcinoma, explore the precise treatment of disease and build up artificial intelligence-based clinical decision support system. Methods: A total of 5 642 patients with primary hepatocellular carcinoma admitted to West China Hospital from July 2004 to June 2016 with complete follow-up records were included in the study. A merged model composed of multiple sub-classifiers was adopted to calculate therapy recommendation coefficient, and receiver operator characteristic curve was analyzed. Survival risk and recurrence risk were predicted by DeepSurv algorithm, and Kaplan-Meier survival curves were further compared among low, middle and high risk groups. Siamese-Net was applied to find similar patients. Results: The Top-1 and Top-2 accuracy of therapy recommendation coefficient reached 82.36% and 94.13% respectively. In internal verification of West China Hospital, the above-mentioned value reached 95.10% in accordance with multi-disciplinary team results. The C-index derived from survival risk model was 0.735 (95%CI:0.70-0.77), and the difference of Kaplan-Meier in pairwise comparison was of statistical significance under log-rank test (P<0.001). Meanwhile, the C-index derived from recurrence risk model was 0.705 (95%CI:0.68-0.73), and the difference of Kaplan-Meier in pairwise comparison was of statistical significance under log-rank test (P<0.001). Conclusions: The artificial intelligence-based clinical decision support system for primary hepatocellular carcinoma has can accurately make therapy recommendation and prognosis prediction for primary hepatocellular carcinoma.