Data-based Decision Research Articles

Enhancing Predictive Analytics in Business Intelligence through Explainable AI: A Case Study in Financial Products

Today, when the importance of data-based decision-making is impossible to question, the use of Explainable Artificial Intelligence (XAI) in business intelligence (BI) has inestimable benefits for the financial industry. This paper discusses how XAI influences predictive analytics in BI systems and how it may improve interpretability, and useful suggestions for financial product companies. Thus, within the context of this study, an XAI framework helps the financial institutions to employ higher-performing and more accurate models, like gradient boosting and neural networks, while sustaining interpretability required in tendentious planning and satisfying governance and supervision necessities. These studies reveal that, as applied to the credit scoring dilemma, XAI techniques such as SHAP and LIME do not only enhance prediction consistency and performance, but also offer a detailed understanding of customer behaviours, risk profiles and product performance. They help in interacting and acting within fields that involve decision making on aspects like customer loyalty, probable risks and audit. Furthermore, the study establishes that by incorporating XAI into BI improves model interpretability, which helps financial experts provide tangible rationale for analytical results and conform to regulatory directives. This framework and findings also support the importance of introducing XAI for financial BI applications to improve analytics practice within the sector. , enabling the generation of higher confidence, reliable decisions, which place the subject of XAI as a profound evolution of business intelligence in finance.

Data based individualization in early writing: the importance and measurement of implementation fidelity

In this paper we describe the process of monitoring fidelity of implementation for a teacher-implemented early writing intervention. As part of a large, federally funded project, teachers who worked with students in grades 1 through 3 in schools across two states in the US were recruited and then randomly assigned to implementation and control conditions. Using Data-Based Individualization (DBI) as a framework for best practice in assessment and intervention, teachers in the implementation group received professional development on early writing intervention and assessment and then implemented these practices with their students who had significant writing challenges. Coaches, who were part of the research project, supported teachers and also observed teachers in both the implementation and control conditions at least twice during the course of the 20-week study. This paper focuses on the results of the fidelity measures that were administered throughout the project. An overview of the importance of fidelity checks is followed by a description of the fidelity tools used, as well as data from those tools. Areas of strength and challenge for teachers when implementing early writing assessment and intervention and engaging in data-based decision making with fidelity are discussed, along with recommendations regarding the practical and research importance of fidelity checks.

Systematic Literature Review on Knowledge-Driven Approaches for Construction Safety Analysis and Accident Prevention

Due to its inherent complexities in the process and the dynamic interactions with external environmental factors, the construction industry is widely considered one of the most hazardous industries worldwide. With advancements in artificial intelligence (AI), construction safety management practices have increasingly used knowledge-driven approaches. Such incorporation of knowledge-based methods has led to significant improvements in various elements of construction safety management systems, including hazard identification and risk assessment, selection of risk mitigation strategies, analysis of accident information, sharing of health and safety knowledge, access to regulations, and identification of applicable safety requirements. Against this background, this paper presents a systematic literature review to provide an overview of the current state of the art in the use of knowledge-driven approaches in construction safety management. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) procedure, this study reviews how the knowledge-driven approach is utilized in the construction safety management field to automate different activities that come under it. Journal papers published from 2000 were considered for this review, and the analysis focused on the contributions of research, the evolution of knowledge-driven approaches, sources of incorporated knowledge, methods of system development, yearly publications, and publication by journals. The results provide a comparison of related studies over two decades and offer insights into trends and gaps in this research field. Notably, the trend analysis shows a dramatic increase in the number, as well as the depth, of research efforts utilizing AI techniques for analyzing unstructured data, such as construction images and texts from construction documents, and drawing data-based decisions for accident prevention.

Machine learning for particle size prediction in iron ore grinding process

The mining industry is finally embracing the new opportunities brought by Industry 4.0, and one opportunity to be explored is the use of machine learning and artificial intelligence tools. To meet the continuous global demand for iron ore and improve the performance of facilities, process optimization is essential and may revolutionize the industry with data-based decision-making and increased efficiency and profitability. In iron ore beneficiation plants, the potential gains from machine learning tools are significant, and tend to increase in the milling process, where the grinding phase incurs the highest energy costs among mineral processing operations. This article presents the application of machine learning techniques for the prediction of the main product quality parameter of a milling plant. CRISP-DM, a well-established approach for data science projects, was applied, and the results demonstrated the effectiveness of the model, achieving satisfactory predictive performance. The deployment reduces reliance on laboratory testing and provides energy savings through proactive process control optimization.

How Professional Learning Networks Can Support Teachers’ Data Literacy: In Conversation with Experts

In the last decade data-based decision making has been promoted to stimulate school improvement and student learning. However, many teachers struggle with one or more elements of data-based decision making, as they are often not data literate. In this exploratory study, professional learning networks are presented as a way to provide access to data literacy that is not available in schools. Through interviews with scientific experts (n = 14), professional learning networks are shown to contribute to data-based decision making in four ways: (1) by regulating motivation and emotions throughout the process, (2) by encouraging cooperation by sharing different perspectives and experiences, (3) increasing collaboration to solve complex educational problems, and (4) encouraging both inward and outward brokering of knowledge. The experts interviewed have varying experiences on whether professional learning networks should have a homogenous and heterogenous composition, the degree of involvement of the school leaders, and which competencies a facilitator needs to facilitate the process of data-based decision making in a professional learning network.

Shaping the Future of Learning, Teaching, and School Leadership Management

This paper is about transformative trends in education, exploring learning, teaching methodologies, and management of school leadership, which will redefine education in the next ten years and beyond. The concept of personalized learning, the integration of technology in study activities, and the reform of leadership from the traditional, routine-oriented style into the more open, adaptive one are the critical issues of the research currently being conducted. These changes referring to personal learning differences, lifelong learning, and collaborative environment are meant to make them more evolved or advanced. Through the analysis, teachers being purely instructors changed to facilitators of learning, cultural responsiveness to teaching was emphasized, and the impossibility of attaining good outcomes without digitalization was brought into view. On the other hand, transformational leadership is especially relevant for change management with respect to community participation and data-based decision-making. This view of all angles on the future shows how the education systems that tend to be more flexible and diverse, as well as the ones that are better suited to meet all the diverse learning needs of all students, are the ones to thrive in this new global paradigm.

Development of Data-Driven Educational Decision Implementation Guidelines Assisted by Formative Tests in Science Learning

Data-Based Educational Decisions (DDED) is an important part of the learning process where DDED is used to improve the quality of learning. This research purpose to develop Data Driven Educational Decision Implementation Guidelines (DDED) supporting formative tests in IPA learning. DDED is an adaptation of Data Drive Decision Making (DDDM) in learning. DDED is based on Data Drive Decision Making (DDDM), which is a decision-making process that has been widely applied in the world of management. The DDED directs teachers to be adaptive and flexible in implementing various methods, models, teaching materials and learning media based on student access. The development design used is 4D which consists of defining, designing, developing and deploying. The content of the guidelines has been agreed through expert consensus through the fuzzy delphi technique. Fuzzy Delphi Method to create a broad and detailed understanding, especially in education. The consensus indicated that formative tests should include relevant questions and quizzes, comprising both multiple-choice and essay formats, aligning with the principles of DDED. The resulting guideline tests the level of validity and user response. Users respond well to the guidelines developed.

Implementasi Data Mining dengan Metode Regresi Linear untuk Prediksi Hasil Penjualan di PT Awitama Cyndo Wahana

The increase in the number of new entrepreneurs in Indonesia is influenced by technological developments, easier access to information, and government support. This increases the need for legal services such as making business permits and business agreements. Lack of understanding of the legal aspects of business can hinder business growth. PT Awitama Cyndo Wahana, a legality management service provider, has great potential to support new entrepreneurs. However, this company has not utilized sales data to predict future sales. This research uses sales data from PT Awitama Cyndo Wahana to predict sales using the linear regression method. The test results show that the Root Mean Squared Error (RMSE) is 458618.289, the Absolute Error is 183084.456, and the Relative Error is 0.98%. These results indicate that the prediction model has an adequate level of accuracy, although there are some prediction errors. The practical implication of this research is that PT Awitama Cyndo Wahana can use these sales predictions to plan more effective marketing strategies and make data-based business decisions, so that they can better support the growth of new entrepreneurs.

Utilizing Cobit 4.1 and Balance Scorecard to Manage Information Technology Business Process in Higher Education Institution

Pamulang University's Information Technology Strategy Plan aims to develop a comprehensive strategy to maximize IT efficiency and effectiveness in the institution. Using the COBIT 4.1 approach, SWOT analysis, and Balanced Scorecard, this plan identifies strengths, weaknesses, opportunities, and threats in the current IT infrastructure and develops an integrated strategy for IT development. COBIT 4.1 provides a framework for managing and controlling IT by ensuring that IT processes support business objectives and meet stakeholder needs. The SWOT analysis explores the internal and external factors that influence IT at Pamulang University, while the Balanced Scorecard helps in establishing balanced strategic metrics and objectives across multiple perspectives, including financial, customer, internal processes, and learning and growth. This strategic plan is expected to improve IT management, support the achievement of Pamulang University's goals and facilitate data-based decisions for innovation and continuous improvement.

Barriers and Enablers to Data-Based Decision Making in Australian Place-Based Community Initiatives: A Qualitative Study Informed by the COM-B Model and Theoretical Domains Framework

AbstractThis study investigated barriers and enablers to collecting, reporting, and using data and evidence-based lead indicators in decision-making. Four Australian place-based initiatives (PBI) focused on improving child health and reducing inequities participated. Eight interviews with PBI leaders revealed barriers and enablers aligned with all three Capability, Opportunity, and Motivation factors of the COM-B model of behaviour. Difficulties sharing data across services and with the PBI was a main barrier. Enablers were largely related to opportunity factors (e.g., data access) and demonstrating to service providers the benefits to families. Interventions targeting multiple barriers and enablers are needed for consistent, routine use of lead indicators.

Enhancing knowledge transformation in digital education: an analysis of the SECI model’s application in course design and execution

This study investigates the application of the SECI model of knowledge dimensions in the design and execution of educational courses in “Innovation and Digitization Management” and “Data-Based Decision Making” microdegrees, developed within the rapidly evolving educational landscape of 2023 and 2024. The research incorporates a diverse sample of learners across multiple demographics to enhance generalizability. Leveraging natural language processing (NLP) and text analysis, the study explores patterns in course content that correlate with positive learner feedback and effective knowledge transformation. The methodology, combining both quantitative and qualitative approaches, includes data preprocessing, tokenization, vectorization, and clustering to compare and contrast course elements with learner feedback systematically. Preliminary findings indicate that the integration of the SECI model, emphasizing real-time content sharing and example-based learning, significantly enhances the transfer of knowledge from tacit to explicit forms. This research aims to identify a replicable cadence in content preparation that optimizes learning outcomes, applicable to a broad range of educational contexts including data-related courses, innovation, digital transformation or knowledge-management topics.

Mathematical Literacy as a Key Competency for Maritime Education: Systematic Review of Cadet Competencies

This study discusses the role of mathematical literacy as the main competency that cadets need to have in the field of maritime education. Through a systematic literature review (SLR), the mathematical literacy competencies needed by cadets in the maritime field are navigation, problem solving, use of modern technology, operational management, critical and logical thinking, and accurate data-based decision making. This systematic review provides an illustration of literacy mastery Mathematics not only supports cadets' understanding of basic maritime concepts, but also improves cadets' abilities in dealing with challenges or unexpected situations on board ships and while at anchor. Therefore, developing mathematical literacy must be a priority in cadet education and training programs to produce graduates who are competent and ready to face the complexity of the global maritime industry.

Measuring Elementary Student Reading Gain in the Context of School-Implemented Multitiered Systems of Support

There is limited research with mixed results about student reading gains in Grades 1 to 5 within typical school-implemented Response to Intervention (RTI). As part of a larger study, we used school-administered screening data on a widely used computer-adaptive test (Measures of Academic Progress) to describe reading gains across one academic year. We observed relatively faster growth in the first grade than in the later grades. We found stronger growth for students not identified with a disability relative to students with low or high-incidence disabilities or a 504 plan. We explored moderation of gains for students receiving tiered interventions based on administrators’ interviews about RTI implementation. We observed that better ratings of administrators’ articulation about using the evidence-aligned RTI components of progress monitoring, data-based decision-making, and Tier 2 interventions were related to greater gains for students receiving Tier 2 or 3 intervention. We discuss implications, limitations, and directions for future research.

Implementasi Total Quality Management dalam Meningkatkan Daya Saing Perusahaan

This research examines the effect of implementing Total Quality Management (TQM) on company competitiveness. The results show that TQM has a significant and positive effect on increasing competitiveness and company performance. Key contributing factors include customer focus, continuous system improvement, education and training, and employee involvement and empowerment. TQM improves various aspects of competitiveness such as operational efficiency, innovation, customer satisfaction, productivity and product quality. Effective strategies to overcome TQM implementation challenges include top management commitment, development of a quality culture, gradual implementation, effective communication, use of quality tools, continuous evaluation, and encouraging innovation. The research also discusses the impact of TQM on supply chain management and the importance of data-based decision making. In conclusion, effective TQM implementation can significantly increase a company's competitiveness in an increasingly competitive global market.

Health information systems data for decision-making: case study in three cities on current practices and opportunities

A functional and reliable Health Information System (HIS) is vital for data-based decision-making in public health. Here we describe the assessment of data processes and general HIS principles by adapting a global approach to three cities. The assessments supported the data strategy of the CARDIO4cities initiative in each city aiming to improve urban population health by increasing the use of cardiovascular disease (CVD) data to inform decision-making. We aimed to explore data collection processes and entities, data availability and quality as well as data ownership and sharing regarding a set of identified key performance indicators (KPIs). KPIs were based on a global theory of change (ToC) and a global evaluation and indicator framework and were tailored to each location. By first assessing existing sources and processes regarding data, recommendations for changes and improvements are sure to build on current circumstances. To map the data, existing data collection, analysis and storage processes were investigated. A flow chart was created to visualize the data pathways and challenges for each system and findings were compared across cities to document differences and similarities. Data quality and interoperability of various separate systems were the most prominent challenges for all HISs. The observed dvata quality issues originated from incorrect, missing and incomplete data and were connected to the misunderstanding of indicators, incomplete data input forms or the lack of a systematic data routine in the workflow. Harmonization of the HISs to ensure interoperability can facilitate data collection and analysis of health data and can provide a solid basis for health management decision-making. Based on the presented HIS cases, we recommend to examine, map and verify current processes when conducting a HIS assessment, to visualize findings and to gauge the interest of government entities to ensure political support.

TEACHING AND LEARNING TO CONSTRUCT DATA-BASED DECISION TREES USING DATA CARDS AS THE FIRST INTRODUCTION TO MACHINE LEARNING IN MIDDLE SCHOOL

This study investigates how 11- to 12-year-old students construct data-based decision trees using data cards for classification purposes. We examine the students' heuristics and reasoning during this process. The research is based on an eight-week teaching unit during which students labeled data, built decision trees, and assessed them using test data. They learned to manually construct decision trees to classify food items as recommendable or not. They utilized data cards with a heuristic that is a simplified form of a machine learning algorithm. We report on evidence that this topic is teachable to middle school students, along with insights for refining our teaching approach and broader implications for teaching machine learning at the school level.

The impact of urbanization on environmental degradation in Jakarta

Background: The urbanization discussed in this paper refers to the process of expansion in the proportion of the population living in urban areas. Urbanization is seen as one of the processes of increasing population that drives the functional change of an area, from rural to urban activities. The case discussed in this paper is urbanization occurring in Jakarta city. This paper aims to examine the relationship between urbanization and the decline in environmental quality, especially in Jakarta city. Method: In assessing environmental quality, the reference used follows that set by the Ministry of Environment and Forestry, namely the Environmental Quality Index (EQI) which consists of three elements, namely the Water Quality Index (WQI), Air Quality Index (AQI) and Land Cover Quality Index (LCQI), so the variables used are WQI, AQI and LCQI. The data collection method used in this paper is secondary data collection through literature review and official data sources from related stakeholders. The collected data is then analyzed descriptively to determine the relationship between urbanization and each of these variables. Results: Based on the literature review and the results of the LCQI data used, it appears that there is a negative correlation between population growth and land cover in Jakarta Province. This condition is marked by an increase in floods and also an increase in surface temperature. In terms of air quality, this paper found a negative correlation between urbanization and AQI. However, for the condition in 2013 - 2018, a positive correlation was found between the population and AQI. Conclusion: This indicates that an increase in population is not always followed by a decrease in environmental quality. Meanwhile, in relation to water quality, population growth from the urbanization process has a significant impact on water quality in Jakarta. Novelty/Originality of this study: The development of a sophisticated and comprehensive correlation analysis method between population growth and environmental quality indicators (IKLH, IKA, IKU), which integrates spatial and temporal data, provides a predictive tool that city governments can use to monitor, manage, and plan mitigation strategies for the impacts of urbanization on the environment more effectively and proactively, and supports data-based decision-making in sustainable urban planning.

An Economic Optimization Model of an E-Waste Supply Chain Network: Machine Learned Kinetic Modelling for Sustainable Production

Purpose: E-waste management (EWM) refers to the operation management of discarded electronic devices, a challenge exacerbated due to overindulgent urbanization. The main purpose of this paper is to amalgamate production engineering, statistical methods, mathematical modelling, supported with Machine Learning to develop a dynamic e-waste supply chain model. Method Used: This article presents a multidimensional, cost function-based analysis of the EWM framework structured on three modules including environmental, economic, and social uncertainties in material recovery from an e-waste (MREW) plant, including the production–delivery–utilization process. Each module is ranked using Machine Learning (ML) protocols—Analytical Hierarchical Process (AHP) and combined AHP-Principal Component Analysis (PCA). Findings: This model identifies and probabilistically ranks two key sustainability contributors to the EWM supply chain: energy consumption and carbon dioxide emission. Additionally, the precise time window of 400–600 days from the start of the operation is identified for policy resurrection. Novelty: Ours is a data-intensive model that is founded on sustainable product designing in line with SDG requirements. The combined AHP-PCA consistently outperformed traditional statistical tools, and is the second novelty. Model ratification using real e-waste plant data is the third novelty. Implications: The Machine Learning framework embeds a powerful probabilistic prediction algorithm based on data-based decision making in future e-waste sustained roadmaps.

Single-case design emphasis in American Psychological Association-accredited school psychology programs.

Single-case design (SCD) is an underutilized research methodology in school psychology literature. Despite its relevance to practitioners and applied intervention researchers alike, the majority of intervention research disseminated in school psychology journals tends to involve group designs, such as the randomized controlled trial. Group designs are useful for answering a wide variety of research questions but may not always be relevant to practitioners seeking procedures that work for their students or researchers seeking for the optimal design to answer their research questions. In comparison, the relative dearth of SCD studies in school psychology literature, in conjunction with common values among the field regarding data-based decision making and the scientist-practitioner model to training, raises questions about the cause of this gap. The present study sought to review doctoral training programs in school psychology and evaluate their relative emphasis on SCD in training. Seventy-six American Psychological Association-accredited school psychology programs were reviewed, and results indicated that roughly two thirds of programs do not emphasize SCD during training. Implications regarding school psychology training and research are discussed and recommendations are provided on future directions for school psychology trainers and researchers. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Fertilizer application parameters for drip-irrigated peanut based on the fertilizer effect function established from a "3414" field trial.

Scientific fertilization is an important technical means of achieving high and stable peanut yields. Using soil testing and formula fertilization, the "3414" optimal regression design was used and included 14 nitrogen (N), phosphorus (P), and potassium (K) fertilization treatments. Ternary quadratic functions of the fertilizer effect were established according to three-season field experiments and the regression analysis of fertilizer-yield function was performed to explore the optimal fertilizer application mode and ratio for peanuts under mulched drip irrigation (MDI), and a suitable fertilizer application system was established. The ternary quadratic equation relating peanut yield (y) and the fertilizer application rates of N (N), P (P2O5), and K (K2O) was obtained after fitting, i.e., y = 2912.528 + 21.432N + 16.324P + 6.181K - 0.051N2 - 0.109P2 - 0.061K2 + 0.017NP + 0.023NK + 0.086PK, and significance analysis and typicality assessment were performed. The model R 2 was 0.9709, both values are extremely significant (p < 0.01), which indicates that the obtained ternary quadratic fertilizer effect function is typical and could be used for statistical purposes and fertilization recommendations. Three quadratic fertilizer effect functions were obtained. Among them, the equation for K is extremely significant, and the equations of N and P are significant. According to the assumption that the marginal yield is zero and the marginal profit is zero, the fertilizer application rate with the maximum yield, the fertilizer application rate with the best economic benefits, and the corresponding yields were obtained. The optimal fertilizer application rate predicted by the ternary quadratic fertilizer effect function was relatively high, so the three quadratic fertilizer effect functions were used for prediction. Under the test conditions, the recommended fertilizer application rates for peanuts under MDI are 256.6 kg N per ha, 164.2 kg P2O5 per ha, and 213.2 kg K2O per ha, the recommended fertilization ratio is 1:0.64:0.83, and the recommended ratio under formula fertilization is 23:15:19. The study has developed a data-based decision support system for Xinjiang drip-irrigated peanut, which assists farmers and agricultural managers in making more scientific and precise fertilization decisions based on the specific growth requirements of the crops and soil conditions. This evidence-based methodology enhances the precision of agricultural management, which is conducive to increasing crop yields while reducing resource wastage and environmental impact. However, multipoint and multiyear experiments are still needed to ensure that the findings are adaptable to the diverse soil conditions and fluctuating climate patterns that may be encountered in practice.