Predictive Analytics Research Articles

Early prediction of mortality and morbidities in VLBW preterm neonates using machine learning.

Predicting mortality and specific morbidities before they occur may allow for interventions that may improve health trajectories. Integrating key maternal and postnatal infant variables in the first 2 weeks of age into machine learning (ML) algorithms will reliably predict survival and specific morbidities in VLBW preterm infants. ML algorithms were developed to integrate 47 features for predicting mortality, bronchopulmonary dysplasia (BPD), neonatal sepsis, necrotizing enterocolitis (NEC), intraventricular hemorrhage (IVH), cystic periventricular leukomalacia (PVL), and retinopathy of prematurity (ROP). A retrospective cohort (n = 3341) was used to train and validate the models with a repeated 10-fold cross-validation strategy. These models were then tested on a separate cohort (n = 447) to evaluate the final model performance. Among the seven ML algorithms employed, tree-based ensemble models, specifically Random Forest (RF) and XGBoost, had the best performance metrics. The area under the receiver operating characteristic curve (AUROC) of sepsis with or without meningitis (0.73), NEC (0.73), BPD (0.71), and mortality (0.74) exceeded 0.7, while the area under Precision-Recall curve (AUPRC) for all outcomes was greater than the prevalence, demonstrating effective risk stratification in VLBW preterm infants. Our study demonstrates the potential of predictive analytics leveraging ML techniques in advancing precision medicine. Reliable prediction of adverse outcomes before they occur has the potential to institute interventions and possibly improve health trajectories in VLBW preterm infants. We used machine learning to develop and test predictive models for mortality and five major morbidities in VLBW preterm infants. Individualized prediction of outcomes and individualized interventions will advance Precision Medicine in Neonatology.

Strengthening Healthcare Data Security with Ai-Powered Threat Detection

As the healthcare industry undergoes rapid digital transformation, the need for robust cybersecurity measures has never been more critical. AI-driven solutions, such as Machine Learning (ML) and anomaly detection, are proving to be pivotal in securing healthcare data. These technologies enable healthcare organizations to identify cyber threats proactively, automate incident response, and enhance data security. Furthermore, AI's ability to provide continuous network monitoring, predictive analytics, and real-time anomaly detection offers healthcare providers the tools needed to mitigate risks before they escalate. This research highlights the key applications of AI in healthcare data security, including its effectiveness in vulnerability management and regulatory compliance. It also delves into the ethical and operational challenges of integrating AI-driven threat detection systems into healthcare settings, including concerns related to bias in AI models, regulatory hurdles, and the complexity of AI system integration into existing healthcare infrastructures. In a 2023 study, Accenture reported that AI-based cybersecurity systems reduced detection and response time by up to 60%, illustrating how AI accelerates response to potential data breaches​. Similarly, HIMSS noted that the risk of data breaches in healthcare could be halved by AI technologies that continuously monitor and analyze data​. These findings emphasize AI's role in minimizing the delays and errors typically associated with human-driven responses​. AI techniques such as supervised, unsupervised, and semi-supervised learning play a crucial role in anomaly detection. These models identify irregular patterns in healthcare systems, flagging potential threats even when subtle​. For example, deep learning approaches, including Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), can uncover outliers in healthcare data, enhancing system security​. The ability of AI to continuously learn from previous attacks ensures that systems evolve with emerging threats, further solidifying its place in healthcare cybersecurity​. Additionally, AI aids in predictive analytics, which can forecast future cyber threats based on historical data, allowing healthcare providers to address vulnerabilities proactively​. By leveraging such capabilities, AI not only safeguards sensitive patient data but also enables healthcare institutions to stay compliant with stringent regulatory standards like HIPAA and GDPR​. However, AI implementation in healthcare security comes with its own challenges. Integrating AI into legacy systems requires substantial infrastructure upgrades, and the complexity of dynamic encryption can strain system resources​. Furthermore, the ethical concerns surrounding AI, such as the transparency of decision-making processes and potential bias in AI algorithms, must be carefully managed to ensure equitable and effective security solutions​

A Literature Review: Which, How and What for the Use of Artificial Intelligence in Gamification

Artificial intelligence (AI) is integrated into educational methods through game-like elements, including gamification and serious games, offering tools and approaches to enhance teaching and learning experiences. A comprehensive review was adopted in this study to generate an overall trend or effect on AI in gamification. The paper selection was based on the three databases. Related 22 articles were collected by searching through academic journals or conference proceedings that were published in English from 2019 to 2024. The findings present that machine learning is utilised in serious games, favouring AI that might support gamification and improve results such as enhanced learning outcomes. Some included studies discuss the direct and indirect connection between technologies and gamification, including personalisation, adaptive difficulty, feedback and motivation, predictive analytics, and data-driven Insights. Overall, those interested in the intersection of artificial intelligence and gamification, including researchers, practitioners, developers, educators, and policymakers, can benefit from the literature review.

Predictive Analytics for Pilot Training in Southern Africa

This paper aims to enhance aviation safety by identifying and addressing pilot performance weaknesses through data-driven techniques, focusing on the strategic adoption of predictive analytics in pilot training across Southern Africa, particularly in South Africa, Namibia, and Botswana. The main objective is to utilize advanced technologies like Natural Language Processing (NLP) and machine learning (ML) to analyze aviation incident reports and identify patterns of pilot errors and operational risks. The study's results highlight vital insights, which pave the way for tailored training programs designed to mitigate risks. The achievements of the study include filling a non-empirical gap by applying the Diffusion of Innovations (DOI) framework to examine the adoption of predictive analytics alongside recommendations for standardized reporting, specialized training modules, and the integration of weather analytics. These outcomes demonstrate the transformative potential of predictive analytics in improving pilot training and enhancing safety in the Southern African aviation sector.

ВИКОРИСТАННЯ ЕЛЕКТРОННИХ СИСТЕМ ДОКУМЕНТООБІГУ ТА ЗВІТНОСТІ ЛОГІСТИЧНИМИ КОМПАНІЯМИ УКРАЇНИ

The article explores the possibilities and ways of using information technologies for document management and electronic reporting at logistics enterprises. Theoretical approaches to understanding the goals and tasks of logistics information systems in transport technologies have been considered. The main information technology systems that change the logistics industry in modern conditions have been characterized, namely: RPA; chat bots; visualization; Artificial Intelligence; predictive analytics. The electronic technologies used for information provision in Ukrainian practice, the IT-Enterprise ERP system of JSC ‘Ukrposhta’ and the CRM system of the company ‘Epicentr K’ have been analyzed. Their characteristics and advantages of use have been defined. It have been found that the basis of the functional component of the modern information system is a single module of operations between the links of the logistics system, which determines the relationship between the functional divisions of the company (in terms of the implementation of logistics functions), intermediate links and consumers of the company’s products. The implementation of a logistics information system in the work of a logistics enterprise makes it possible: - to increase the efficiency of its work, achieve a high level of service for customers and ensure effective control; - to ensure a modern approach to the management of implementation processes and the organization of various types of events; - to monitor the efficiency of commercial operations; - to conduct an analysis of the profitability of the activity; - to increase the effectiveness of price policy, etc. The problems of the introduction of electronic document flow and reporting systems in Ukraine have been noted: - the problem of interoperability in electronic document flow; - lack of clear standards and requirements for electronic reporting, companies may hesitate to switch to this type of reporting; – constant changes in legislation and requirements can create difficulties for enterprises in implementing stable electronic reporting systems; - inconsistency of electronic reporting formats with global ones; high implementation costs; - concerns about data privacy and security can deter companies from switching to electronic reporting, especially when the security of information on the network is at stake.

Evaluating User Acceptance of Mobile Payment Systems in Uganda

Purpose: This research evaluates user acceptance of mobile payment systems. Methodology: This study adopted a desk methodology. A desk study research design is commonly known as secondary data collection. This is basically collecting data from existing resources preferably because of its low cost advantage as compared to a field research. Our current study looked into already published studies and reports as the data was easily accessed through online journals and libraries. Findings: Combining machine learning with DW systems provides significant advantages in different fields. This synergy boosts analytical aptitudes, allowing the organization to go a notch higher than descriptive analytics in predictive and prescriptive analytics. However, such a decision is not simple as it has implementation matters such as data quality problems, scalability, and real-time processing problems. Integration best practices include in-database machine learning processing, a feature store, and proper MLOps practices. Real-life examples from the healthcare industry, banking and financial services, retail, and manufacturing industries show that this integration brings operational enhancements for the business and positive effects on customers and overall organizational performance. Recommendations: Mobile payment providers should prioritize user-centric design principles, focusing on simplicity, usability, and intuitive interfaces. Policymakers should develop regulatory frameworks that establish clear standards for mobile payment systems, focusing on data protection, privacy, and security. Keywords: User Acceptance, Mobile Payment Systems

The Analytics of Robust Satisficing: Predict, Optimize, Satisfice, Then Fortify

In the paper, “The Analytics of Robust Satisficing: Predict, Optimize, Satisfice, Then Fortify,” published in Operations Research, authors Sim, Tang, Zhou, and Zhu introduce a novel approach to decision making under uncertainty. Their method, termed “estimation-fortified robust satisficing,” leverages advanced predictive and prescriptive analytics to optimize decisions where traditional models falter due to risk ambiguity and estimation uncertainties. This approach not only enhances the resilience of decisions against unforeseen variations but also consistently outperforms conventional predictive methods in scenarios characterized by sparse data. This significant advancement promises to fortify decision-making processes in critical sectors such as finance and operations management, offering a new paradigm in handling the inherent uncertainties of real-world systems.

Strategic Innovation in Crisis Management Converting into Opportunity: A Case Study of the Dubai Government

Purpose: The conventional crisis management framework, which is characterized by predetermined protocols and reactive actions, has proven ineffective in the face of the complex circumstances of today. The Dubai Government has acknowledged this and adopted a paradigm shift toward strategic innovation, marking a break from the status quo and a readiness to accept uncertainty as a necessary step toward advancement. The strategic innovation framework used by the Dubai Government's crisis management plan will be thoroughly examined in this research. The purpose of the study is to elucidate the guiding principles that have placed this forward-thinking organization at the forefront of crisis resilience via the prism of this progressive organization. It aims to understand the mechanics of crisis management and to draw general lessons that may be used in other organizational contexts by probing the methodology, technologies, and cultural shifts that support this novel approach (Alketbi, del Rio and Fernández, 2022). Methodology: To encapsulate, this research utilizes a qualitative triangulation approach that focuses on the relationship between strategic innovation and crisis management, specifically examining the Dubai Government. By combining qualitative interviews, quantitative surveys, and content analysis, the study provides a comprehensive view of the topic, enabling a thorough investigation of the research questions and objectives. Findings: Based on prior research and global trends, the main finding is to understand the Dubai Government who has seamlessly merged innovation into its crisis management tactics. The focus is on how the Dubai Government integrates advanced technological tools and fosters a culture where challenges are viewed as opportunities for growth. For instance, the adoption of AI-based predictive analytics in crisis anticipation and response is a testament to this innovative approach. Unique Contribution to Theory, Practice and Policy: The study anticipates that these practices not only enhance crisis management effectiveness but also serve as a model for other organizations globally.

SUPPLY CHAIN RISK MANAGEMENT: STRATEGIC SOLUTIONS FOR REDUCING TRANSPORTATION AND LOGISTICS RISKS

This study investigates strategic approaches to mitigating risks in transportation and logistics within global supply chains, focusing on the integration of advanced technologies, flexibility, collaboration, and sustainability. By employing the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, the study systematically reviews 37 key articles to provide a comprehensive understanding of modern risk management practices. The findings reveal the increasing reliance on technologies such as predictive analytics, the Internet of Things (IoT), and blockchain for enhancing visibility, monitoring, and decision-making. Flexibility in logistics networks, including alternative sourcing and diversified transportation routes, emerged as crucial for mitigating disruptions, while collaboration among supply chain partners, particularly through real-time information sharing, significantly reduces risk exposure. Additionally, the study highlights the growing integration of sustainability into risk management, addressing climate change and environmental risks. This research underscores the need for proactive, adaptable, and sustainable risk management strategies to maintain supply chain resilience in the face of evolving global challenges.

AI and Machine Learning in Enhancing Scalability and Efficiency of Integrated E-commerce and ERP Systems

This article explores the transformative potential of Artificial Intelligence (AI) and Machine Learning (ML) in enhancing the integration of E-commerce platforms with Enterprise Resource Planning (ERP) systems. As E-commerce experiences explosive growth and ERP systems become increasingly complex, businesses face significant challenges in maintaining scalability and efficiency. We examine how AI and ML can optimize various aspects of these integrated systems, from intelligent automation and predictive analytics to anomaly detection and decision support. Through case studies and analysis of current trends, we demonstrate the tangible benefits of AI/ML implementation, including reduced costs, improved accuracy, and enhanced customer experiences. The article also addresses key challenges such as data quality, scalability, ethical considerations, and the skills gap. Finally, we explore future research directions in explainable AI, edge computing, blockchain integration, and natural language processing, highlighting their potential impacts on the E-commerce and ERP landscape.

Smart Benefits Distribution : Leveraging IoT and Data Analytics for Streamlined Office Efficiency

This article explores the transformative potential of integrating Internet of Things (IoT) devices and advanced data mining techniques in benefits distribution systems. Faced with challenges such as long wait times, inefficient processes, and resource mismanagement, government agencies and private organizations are turning to these technologies to revolutionize service delivery. The article discusses how IoT-enabled smart kiosks, occupancy sensors, and process automation tools can streamline operations and improve client experiences. It further examines how data mining techniques, including predictive analytics, clustering, and anomaly detection, can enhance decision-making and operational efficiency. Through a case study and analysis of benefits and challenges, the article demonstrates how this integrated approach can lead to reduced wait times, improved staff productivity, enhanced fraud detection, and significant cost savings, ultimately transforming the landscape of benefits distribution to be more efficient, responsive, and beneficiary-centric.

FRAUD DETECTION IN FINANCIAL TRANSACTIONS THROUGH DATA SCIENCE FOR REAL-TIME MONITORING AND PREVENTION

This study presents a comprehensive review of the use of advanced technologies in credit card fraud detection, with a focus on machine learning, blockchain, and federated learning, to understand their transformative impact on the field. Using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, a total of 97 articles were systematically reviewed and analyzed. The findings reveal that machine learning models, such as decision trees, support vector machines, and neural networks, have significantly improved fraud detection accuracy, reducing false positives and enhancing the ability to detect complex fraud patterns in real-time. Blockchain technology also plays a critical role by providing a decentralized, secure, and transparent framework for fraud detection, ensuring the integrity of transaction records and making fraudulent activities harder to conceal. Federated learning offers a privacy-preserving solution, enabling institutions to collaborate on fraud detection without sharing sensitive data, which is increasingly important in light of stringent regulatory requirements. Additionally, the study highlights the growing use of predictive analytics in forecasting potential fraud, allowing financial institutions to proactively prevent fraud before it occurs. Moreover, feedback loops integrated into fraud detection models allow for continuous improvement, ensuring that detection systems can adapt to new and evolving fraud tactics. Overall, the review underscores the importance of adopting these advanced technologies to build more secure, efficient, and adaptive fraud detection systems capable of safeguarding financial transactions in the modern digital economy.

Adaptive Multi-Agent Reinforcement Learning for Optimizing Dynamic Electric Vehicle Charging Networks in Thailand

The rapid growth of electric vehicles (EVs) necessitates efficient management of dynamic EV charging networks to optimize resource utilization and enhance service reliability. This paper explores the application of adaptive multi-agent reinforcement learning (MARL) to address the complexities of EV charging infrastructure in Thailand. By employing MARL, multiple autonomous agents learn to optimize charging strategies based on real-time data by adapting to fluctuating demand and varying electricity prices. Building upon previous research that applied MARL to static network configurations, this study extends the application to dynamic and real-world scenarios, integrating real-time data to refine agent learning processes and also evaluating the effectiveness of adaptive MARL in maximizing rewards and improving operational efficiency compared to traditional methods. Experimental results indicate that MARL-based strategies increased efficiency by 20% and reduced energy costs by 15% relative to conventional algorithms. Key findings demonstrate the potential of extending MARL in transforming EV charging network management, highlighting its benefits for stakeholders, including EV owners, operators, and utility providers. This research contributes insights into advancing electric mobility and energy management in Thailand through innovative AI-driven approaches. The implications of this study include significant improvements in the reliability and cost-effectiveness of EV charging networks, fostering greater adoption of electric vehicles and supporting sustainable energy initiatives. Future research directions include enhancing MARL adaptability and scalability as well as integrating predictive analytics for proactive network optimization and sustainability. These advancements promise to further refine the efficacy of EV charging networks, ensuring that they meet the growing demands of Thailand’s evolving electric mobility landscape.

The Role of Complex Systems in Predictive Analytics for E-Commerce Innovations in Business Management

This review explores the incorporation of complex systems theory into predictive analytics in the e-commerce sector, particularly emphasizing recent advancements in business management. By analyzing the intersection of these two domains, the review emphasizes the potential of complex systems models—including agent-based modeling and network theory—to improve the precision and efficacy of predictive analytics. It will provide a comprehensive overview of the applications of emergent predictive analytics techniques and tools, including real-time data analysis and machine learning, in inventory optimization, dynamic pricing, and personalization of customer experiences. In addition, this review will suggest future research directions to advance the discipline and address the technical, ethical, and practical challenges encountered during this integration phase.

Performance of Predictive Models in Cervical Cancer Recurrence: A Systematic Review and Meta-Analysis of Biomarkers and Prognosis

This study investigates the use of Predictive Analytics Frameworks (PAF) for identifying biomarkers of recurrent cervical cancer and predicting prognosis. It addresses the limited comprehensive evaluations of the effectiveness of predictive models in this area, despite the growing application of machine learning in healthcare. The purpose of this systematic review and meta-analysis is to assess the performance of predictive analytics models in terms of sensitivity, accuracy, specificity, and the area under the curve (AUC-ROC) for identifying cervical cancer biomarkers and predicting prognosis. To address this research problem, a systematic review and meta-analysis was conducted, covering studies published between 2014 and 2024. A total of 1,515 studies were initially identified from the PubMed and Scopus databases, with 50 research studies meeting the inclusion criteria. Repeated measures ANOVA and meta-analysis were applied using data collected over an 8-year period to evaluate recurrence trends and the predictive power of various models. The findings suggest that predictive analytics models show significant potential for improving diagnostic accuracy in identifying cervical cancer biomarkers. However, the review also highlights several limitations, including the small number of included studies, heterogeneity across studies, and potential bias in retrospective analyses. In conclusion, while predictive analytics frameworks demonstrate promise in improving cervical cancer prognosis and biomarker identification, further research is required to validate these findings and assess their broader clinical utility. The study underscores the importance of continued exploration of predictive models to enhance decision-making in oncology.

AI-driven Predictive Analytics for Enhancing Cybersecurity in a Post-pandemic World: a Business Strategy Approach

Due to heightened technological advancement that has been ignited by the COVID-19 pandemic, the use of technology in running businesses has surged and therefore making businesses prone to cybersecurity threats. The present paper explores the potential of AI as a tool for advancing cybersecurity in the world after a pandemic, and how business organizations can organize its application for protection against new emerging forms of threats. The research draws on secondary industry data and primary case studies of the businesses with AI-based cybersecurity in place. The outcome demonstrates that emerging AI technologies, including machine learning and neural networks, have cut threat detection time by 40% and enhanced the precision of recognizing potential security threats by 30%, beyond conventional cybersecurity solutions. The new and distinct feature of this paper is to elucidate that new threats can be predicted with the help of AI, while there is a continuous need for new training for AI in relation to cyber threats. Drawing from the literature, this paper, therefore, posits that incorporation of AI-based predictive analytics into business cybersecurity models and systems is not only vital for the defense of data and infrastructure against hackers but equally important for the achievement of sustainable, long-term business continuity during the current day, age of technology and globalization.

Stability in Sight: Leveraging Machine Learning for Proactive Political Risk Management in the United States of America

This paper explores the application of machine learning (ML) in political risk management, with a specific focus on recent trends in political violence in the United States OF America. The growing intersection of political polarization, disinformation, and societal unrest has created a volatile political climate, as evidenced by events such as the January 6 Capitol insurrection and rising threats to public officials. The paper argues that machine learning could play a critical role in mitigating such risks by analyzing large datasets, including social media interactions, political speeches, and public sentiment, to predict potential flashpoints of violence. Through predictive analytics, sentiment analysis, and anomaly detection, ML can enhance decision-making processes and provide timely interventions to avert violent incidents. Additionally, case studies demonstrate ML’s superiority over traditional methods in risk assessments. Despite the challenges associated with ML, such as data privacy concerns, algorithmic bias, and the complexity of political contexts, this paper argues that machine learning holds immense potential in transforming political risk management. By integrating diverse data sources and refining risk models, ML can significantly improve accuracy and efficiency in predicting and mitigating political risks. The paper concludes with recommendations for further integrating ML tools in political risk strategies to address the increasingly unstable political environment.

The Impact of Artificial Intelligence on Project Management Efficiency

This research paper examines the influence of Artificial Intelligence (AI) on the efficiency of project management, concentrating on the ways in which AI tools and techniques improve different facets of project management. The study initiates with a comprehensive examination of project management and the increasing significance of AI in various domains, emphasizing the shortcomings of conventional methodologies and the capacity of AI to tackle these issues. The study seeks to evaluate the impact of AI on project processes, pinpoint effective AI tools, and investigate the advantages and obstacles associated with AI integration. A thorough examination of existing literature investigates AI tools, including machine learning, natural language processing, and predictive analytics, along with their applications in planning, scheduling, resource allocation, risk management, communication, and performance monitoring. Case studies and empirical evidence illustrate the beneficial effects of AI on project outcomes, while also highlighting existing gaps in the literature that warrant further investigation. The mixed-methods approach integrates qualitative and quantitative data sourced from surveys, interviews, and case studies, employing both thematic and statistical analysis. The findings indicate that AI plays a crucial role in enhancing project efficiency through the reduction of timelines, improvement of cost control, optimization of resources, and facilitation of proactive risk management, in addition to enhancing communication and collaboration. Nonetheless, factors such as initial investment, skill requirements, resistance to change, and ethical considerations are acknowledged. The discussion outlines actionable strategies for project managers, highlighting the importance of training, incremental integration, ensuring data quality, and promoting innovation. The study concludes by offering recommendations for future research regarding the long-term effects of AI, conducting cross-industry analyses, and creating AI tools specifically designed for project management. This approach aims to provide empirical evidence and strategic insights into the integration of AI for enhanced project outcomes.

Exploring the Future of Salesforce with Einstein GPT

This paper discusses how far the impact of Einstein GPT can go into changing Salesforce, talking from its architecture, applications, and future possibilities. Einstein GPT helps in the integration of advanced generative pre-trained transformers in Salesforce, enabling it to allow natural language interactions and enhanced insights of data. The essay will research through its architecture, including the Data Layer, AI/ML Layer, and Interaction Layer, bringing into focus key applications such as sales automation, improvement in customer service, optimization in marketing, and predictive analytics. This paper considers the moral dimensions of using AI, too. That is, by considering these dimensions, the essay points out how Einstein GPT is bound to set a new course of CRM capabilities and future innovations within Salesforce. Keywords—Salesforce, GPT, Einstein, AI, Integration

Real-time Predictive Health Monitoring using Ai-driven Wearable Sensors: Enhancing Early Detection and Personalized Interventions in Chronic Disease Management

The use of artificial Intelligence in wearable health sensor has brought a great change in the way chronic diseases are being managed since it monitors the health and gives prompt prediction of diseases coupled with recommendations. This paper seeks to investigate the part played by AI wearables in augmenting early detection & proactive plans relating to chronic illnesses, including diabetics, cardiovascular diseases, and hypertension. Implicitly, the purpose of this study is to update the current understanding of the subject by examining the effect that predictive analytics has on patient outcomes and cost. Technologically, the concepts of the research rely on the data collected from different kinds of wearable devices and analyze by machine learning and real time analytic to examine the abnormal of vital signs before symptoms occur. Analysis is carried out on the outcomes which reveals a 25 percent decrease in hospitalization incidences per early diagnosis of chronic diseases and a 30 percent enhancement in the adherence to treatment provided formed by precautions embraced from various sensors data. This research also increases the stock of knowledge on the role of artificial intelligence in healthcare by presenting empirical evidence regarding the use of wearable devices in chronic diseases. The uniqueness of this concept is in the synchrony of monitoring processes with the application of the predictive model in providing proactive health care solutions. Some potential future research and development considerations in AI-assisted technologies in healthcare are also described.