Predictive Analytics Research Papers - Academia.edu (original) (raw)

2025, Journal of Advanced Engineering Technology and Management JAETM

Software Development as a field is exponentially growing. It is deemed essential to innovate and lead. Though technologies from time to time have greatly impacted the development methodologies, it is AI now that has ushered software development into a new era of possibilities. It truly has helped with optimizing the SDLC (Software Development Lifecycles), but there are myriad challenges that its integration into software engineering entails. AI tools are fast transforming the ways the codes are written, generated, improved, optimized, reviewed, debugged, and managed. From saving time that often goes into carrying out repetitive tasks to analyzing or testing code, AI tools have made almost all things simple. NLP (Natural Language Processing) is one of the best core features of AI-human interaction. The users provide queries in simple English and get the results they need to speed up their development process. This paper highlights the current practices, strategies, methodologies, and procedures enterprises employ to speed up their development processes. It systematically reviews the existing literature and discusses the difficulties underlying AI integration into enterprise software development practices, the complex nature of the AI models that the companies use, data storage, and data security. Further, it analyzes the AI-human collaboration from different perspectives, and how it fosters a culture of continuous learning, enabling the developers to learn and grow their development skills too. It also sheds light on the use of the current practices and what the future possibilities are.

2025, BULLET : JURNAL MULTIDISIPLIN ILMU

Predictive analytics in healthcare has gained significant attention due to its ability to enhance decision-making, reduce hospital readmission rates, and improve patient outcomes. Machine learning (ML) plays a pivotal role in developing predictive models that analyze vast amounts of patient data to forecast health outcomes. This paper explores the application of ML techniques in healthcare predictive analytics, discusses commonly used algorithms, evaluates their effectiveness, and highlights challenges and future research directions. The integration of machine learning (ML) in predictive analytics enables the processing and analysis of vast amounts of patient data to identify patterns and predict health outcomes. This paper explores the application of ML techniques in healthcare predictive analytics, discusses commonly used algorithms, evaluates their effectiveness, and highlights challenges and future research directions. We present a case study using supervised learning models to predict patient readmission rates and compare their accuracy based on real-world healthcare datasets. The findings indicate that ML-driven predictive analytics can significantly enhance healthcare efficiency, reduce costs, and improve patient care through early intervention and risk mitigation strategies.

2025

The following Thesis proposes the integral design of a small company that will manufacture and commercialize household water heating systems bases on low temperature solar collectors. The integral design includes three main sections, the theoretical background, the company structure design, and the technical development of the plant design. The theoretical background involves the theory of the conditions of solar luminosity required for the correct operation of a solar energy system, the theoretical and technical grounds for these types of systems, and a reliability study based on a stand by redundant model. The company structure or business model design includes the company's philosophy and quality politics, and the planned structure, meaning the areas the company will deploy. The plant design development is the nucleus of this study; it includes the manufacturing processes and activities design, the plant flow design, the facility design, and the development of a location mathematical model. vii

2025, URF Publishers

Artificial intelligence (AI) is rapidly transforming various sectors and internal medicine is no exception. This field, focused on the diagnosis, treatment and management of complex adult diseases, is witnessing a paradigm shift with the integration of AI technologies. This abstract explores the multifaceted ways AI is revolutionizing internal medicine, encompassing advancements in diagnosis, personalized treatment approaches and enhanced patient care. AI-powered tools are enabling physicians to analyze vast amounts of patient data, including medical images, electronic health records and genomic information, to identify patterns and insights that may be missed by human observation. This leads to more accurate and timely diagnoses, particularly in areas like radiology, pathology and cardiology. Furthermore, AI is facilitating the development of personalized treatment plans tailored to individual patient characteristics, optimizing therapeutic interventions and improving patient outcomes. By automating routine tasks, AI is also freeing up physicians' time, allowing them to focus on more complex cases and enhance patient interaction. However, the successful implementation of AI in internal medicine requires careful consideration of ethical implications, data privacy and the need for human oversight. This abstract highlight the transformative potential of AI in internal medicine while acknowledging the challenges that need to be addressed to ensure its responsible and effective integration into clinical practice.

2025, URF Publishers

Artificial intelligence (AI) is rapidly emerging as a transformative force across various sectors and its potential impact on public health is particularly profound. This paper explores the diverse applications of AI in revolutionizing public health practices, from disease surveillance and outbreak prediction to personalized interventions and health equity promotion. We examine how AI algorithms can analyze vast datasets, identify patterns and generate insights that would be impossible for humans to discern, leading to more effective and efficient public health strategies. The paper delves into specific examples, such as AI-powered diagnostic tools, predictive modeling for disease spread and chatbots for health education. Furthermore, we discuss the challenges and ethical considerations associated with AI implementation in public health, including data privacy, algorithmic bias and the need for transparency and accountability. We argue that while AI offers immense promise for improving population health outcomes, careful planning, collaboration and ethical frameworks are crucial to ensure its responsible and equitable deployment. This paper aims to provide a comprehensive overview of the current landscape of AI in public health, highlighting its potential benefits, addressing the associated challenges and outlining future directions for research and implementation.

2025, Karan Rawat

This research explores the transformative role of Internet of Things (IoT)-based predictive maintenance in promoting energy efficiency and operational excellence within the manufacturing sector. With rising operational demands and environmental responsibilities, industries are shifting from reactive and time-based maintenance to proactive, data-driven systems. This study presents a fictional case rooted in realistic industrial practices to demonstrate how predictive maintenance reduces energy usage, operational downtime, and long-term costs. The findings indicate that when supported by IoT infrastructure, predictive maintenance serves as a key enabler of sustainable manufacturing practices, strategic agility, and industrial resilience in the age of digital transformation.

2025

Library ggplot2 merupakan packages yang tersedia di dalam RStudio untuk memvisualisasikan data numerik. Library ggplot2, membangun grafik secara bertahap dengan menambahkan komponen-komponen (layers). Draft ini bertujuan untuk mempelajari... more

2025, International Journal of Science and Research (IJSR)

Geographic Information Systems (GIS) play a pivotal role in enabling the collection, visualization, and analysis of spatial data across diverse industries, such as urban planning, environmental management, and disaster response. Despite their significance, GIS applications face usability challenges stemming from complex interfaces, large data volumes, and diverse user expertise. Traditional User Experience (UX) testing methods often fall short in addressing these issues due to limitations in scalability, scenario complexity, and realtime insight collection. The integration of Artificial Intelligence (AI) into UX testing introduces transformative solutions, offering automation, enhanced data analysis, and predictive insights. AI-powered tools streamline routine testing, accelerate product iteration cycles, and provide actionable design suggestions, addressing usability challenges more efficiently. Through industry case studies of tools and techniques, AI demonstrates its ability to optimize workflows, enhance navigation, and improve user interaction. Furthermore, as AI continues to advance in GIS, its application in UX testing becomes a natural extension. By leveraging AI techniques, GIS platforms can identify user pain points, refine interfaces, and enhance usability for both technical and general audiences. While AI presents unparalleled potential in GIS UX testing, challenges such as resource constraints and integration limitations persist. This article explores benefits, challenges and emphasizes the critical role of AI in creating intuitive, responsive, and accessible GIS applications.

2025, International Journal of All Research Education and Scientific Methods (IJARESM)

Pension systems are vital financial facilities that must be adequately protected against fraud, information threats, and other financial perils for the benefit of the interested parties. Traditional methods of risk assessment are limited, especially in the cybersecurity threats, compliance processes and fraud prevention in a real-time manner. Thus, implementing AI and ML in cloud-based architectures can be an effective solution for improving the security of the pension system, automating the risk analysis of all kinds of threats, and detecting various types of fraud. By availing supervised and unsupervised learning approaches, this paper examines the potential of AI to identify fraudulent activities and evaluate the risks in pension systems. It also discusses architectures that allow scalability. Moreover, it explores current architectures in real-time monitoring of the OS and data encryption enhancement on the cloud. The traditional method of utilizing AI in pension administration focuses on effectively identifying new challenges and employing predictive analytics to prevent or address them before they harm the pension fund adversely. In this paper, real cases and experiments proving the feasibility of using Autoencoders and LSTMs in the identification of suspicious transactions and irregular pension transfers have also been discussed. In addition, some of the issues highlighted in this paper include data privacy issues, interpretability of results, and AI prejudice in generating the decision. We suggest future work based on the following directions: federated learning to train secure AI models and adopting ethical frameworks to improve the model's interpretability and fairness. The significance of the issue, the analyses made, the conclusions drawn, and the measures recommended all suggest that the application of AI in the pension fund and pension management presents both opportunities for enhanced pension security, fraud prevention, and legal compliance in terms of size and complexity in cloud environments.

2025, International Journal of Scientific Research in Science, Engineering and Technology

Pension service institutions are quickly going digital as they cope with
increased service requirements, the demands of regulatory compliance,
and challenges posed by cybersecurity. Legacy pension management
systems usually have limited scope, are inefficient, and do not provide
security on-premise infrastructure (Gartner, 2023). These aspects result in
inefficiencies that create delays in processing pensions, an increase in the
risk of fraud, and escalated operational costs (Ponemon Institute, 2023).
The most critical aspect regarding pension transactions involves the
secure, efficient, and scalable service delivery because it entails sensitive
financial information; therefore, it becomes very important to
governments, financial institutions, and private organizations (Forrester
Research, 2022).
This research proposes the Azure-based framework aiming to enhance the
management of pension service requests focusing on scalability, security,
AI-powered automation, and regulatory compliance. The proposed system
uses Azure Virtual Machines, Azure Kubernetes Service, and Load
Balancers to perform the optimized resource provisioning for high
availability. A zero-trust security model has been categorized to protect
pension data from cyber threats, reinforced with Azure Active Directory,
Key Vault, Multi-Factor Authentication, and the Reserve (ISO 2021). The
research also embeds Azure Bot Services and Azure Cognitive Services as
an AI-driven anti-fraud detection tool integrated into the system to
automate customer service and workflow management within the fraud
prevention ecosystem (Accenture, 2023). Automatic rule enforcement and
real-time security monitoring could ensure compliance with GDPR,
HIPAA, and ISO 27001 (Microsoft, 2023).
In the research approach to systematic architectural design, Infrastructure
as a Service and Platform as a Service is combined using encryption
techniques with the Azure Key Vault and private cloud connectivity with Azure ExpressRoute. AI-based pension request processing along with
prescriptive analytics and real-time fraud detection with Azure Machine
Learning and Synapse Analytics complete the solution proposed. A
performance evaluation framework was developed to assess enhancements
in processing time for pension requests and reduction of fraudulent claims
as well as scaling of the system during peak loads and compliance
adherence under security audits.
The empirical evidence gained from real-life business cases shows that
pension automation based on Azure reduces the time for pension
processing by as much as 80%, drastically improving service efficiency
(PwC, 2022). Whereas the AI-based mechanism for the detection of fraud
reduces fraudulent claims for pensions by 70% (IBM Cloud Research,
2022), Azure guarantees 99.99% uptime with its highly available
configurations. Enhanced compliance monitoring, with a reduction in
policy violation incidents by 60% (ISO, 2023), is another feature of the
system.
Future research will look toward blockchain for transaction management
of pension funds, further down in edge computing for quicker processing,
and AI for investment advisory systems in pension management, all aimed
at optimizing pension services management. This research propagates the
cause of digital transformation in pension management through a
demonstration of a secure, scalable, and AI-enabled model with further
extensibility toward healthcare benefits, insurance claims, and the
automation of financial services.

2025, CARI Journals

Purpose: This white paper describes the need to enhance fraud detection within healthcare using the methods of Natural Language Processing (NLP) in unstructured text: physician notes, patient records, and claim descriptions. To overcome the limitations of traditional rule-based platforms in handling healthcare's unstructured data complexity and scale is the objective. Methodology: The proposed approach combines with a well-established pre-trained NLP models (BioBERT and ClinicalBERT) with known methods, such as named entity recognition, anomaly detection, and predictive modeling. A phased approach, as part of the implementation strategy, will be used to implement NLP models for clinical IT environments, from data ingestion and transformation through model deployment and live fraud surveillance. Findings: Based on the studies' results, NLP systems increase fraud detection accuracy by 30 percent, reduce false positives by 20 percent, and allow claims processing under a second. While the white paper's innovative offering begins with a proposal for a hybrid solution, which combines NLP-driven text analysis with existing rule-based systems, this combination delivers a stronger and more flexible means of fraud detection. The predictive nature of NLP enables healthcare organizations to identify potential fraud risks for providers before the issues grow worse. Unique Contribution to Theory, Practice and Policy: The paper's experts call upon IT personnel to lead adopting NLP systems, refresh models to meet new fraud threats, and explore collaboration with federated learning and blockchain to enhance protections and compliance standards. Upon implementing these recommendations, healthcare organization will be able to more effectively deal with fraudulent activities and optimize their workflows more efficiently.

2025, arXiv (Cornell University)

For more than 30 years the discovery that black holes radiate like black bodies of specific temperature has triggered a multitude of puzzling questions concerning their nature and the fate of information that goes down the black hole during its lifetime. The most tricky issue in what is known as information loss paradox is the apparent violation of unitarity during the formation/evaporation process of black holes. A new idea is proposed based on the combination of our knowledge on Hawking radiation as well as the Einstein-Podolsky-Rosen phenomenon, that could resolve the paradox and spare physicists from the unpalatable idea that unitarity can ultimately be irreversibly violated even under special conditions.

2025

This study examines the factors that affect the precise prediction of chemical and drug sales for a well-known pharmaceutical company in Sri Lanka. The article covers the theoretical framework, research design, methodology, data analysis methods, and evaluations. It deals with difficulties like the absence of structured prediction methods, insufficient acknowledgment of the significance of prediction, gaps in accountability in predicting demand, inconsistencies between sales data and real demand trends, ineffective communication among those involved in forecasting, and setting plans based on unachievable objectives. Finding these key elements is essential for enhancing the precision of demand prediction in the chemical and pharmaceutical sectors.

2025, SSRN

The research questions of this scholarly work are as follows: AI: What aspect of healthcare has it improved, and what are the quantifiable results? What does current literature reveal about the effects of AI on patient-centered outcomes? What factors prevent AI from succeeding and scaling across healthcare systems? The research also involves filtering and comparing the data collected from several reports, peer-reviewed articles, systematic reviews, and other papers from the ILO, WHO, and other credible institutions to identify emerging concerns and trends relevant to the objectives of AI. The study indicates that AI enhances efficiency, saves time, and increases the accuracy of diagnosis when AI solutions are applied. However, the following are barriers: Several research gaps related to the use of AI in organizations include ethical considerations when incorporating AI technology, the problem of algorithm bias, and high implementation costs. The study’s limitations are worth elaborating on to carry out more studies to assist in making AI solutions equitable in many healthcare organizations.

2025, IEEE

This paper introduces a novel theoretical framework for AI-driven hyper-personalization in social media marketing, addressing the critical gap in existing research that overlooks the integration of technological, strategic, and ethical dimensions at scale. The framework uniquely combines advanced user profiling, dynamic content personalization, and iterative feedback loops to optimize engagement, loyalty, and ROI. It further tackles scalability challenges through innovations like cloud computing and federated learning, while embedding ethical principles of fairness, transparency, and privacy into its design. Unlike prior studies, this paper provides a holistic roadmap for implementing scalable, cross-platform AI systems and explores the integration of emerging technologies such as AR, VR, and blockchain. By synthesizing actionable insights and proposing future research directions, it redefines the potential of hyper-personalized, user-centric marketing strategies in the digital era.

2025, IEEE

The growing field of Artificial Intelligence (AI) is penetrating deeper into the soul of healthcare, especially in the field of remote patient monitoring and telemedicine, bringing a paradigm shift. AI is improving the quality of service while also giving patients more power and promoting a more collaborative relationship between providers and their patients through the utilization of technologies such as virtual assistant chatbots, wearable monitoring devices, predictive analytical models, custom treatment and monitoring plans, and wireless appointment scheduling systems. However, this gradual embedding of AI into the healthcare domain brings with it a host of challenges that have never been faced before. As the life insurance industry evolves, technology is taking on a more prominent role in shaping how insurers interact with their policyholders. As we approach the year 2030, Artificial Intelligence (AI) is expected to be an integral part of life insurance strategies, particularly in terms of personalized and proactive health initiatives that not only enhance life outcomes for policyholders but also support the long-term profitability of insurance carriers. This paper explores the ways in which AI can be used to develop proactive health programs that promote healthier living, prevent chronic diseases, and improve customer engagement in the life insurance industry.

2025, Andreea Magdalena Drulea

This study explores how predictive analytics contributes to workforce resilience in Dutch thirdparty logistics (3PL) operations. Faced with labour shortages, high turnover, and unpredictable demand, 3PL providers are turning to predictive tools to strengthen workforce planning. Using a mixed-methods approach, the study combines survey data from 75 logistics professionals with case study validation to assess whether predictive analytics improves labour stability, adaptability, and risk mitigation. With a margin of error of ±11.3%, results suggest that higher adoption correlates most strongly with improved workforce stability and structured risk management. Integration success is linked to dashboard use, phased rollouts, and data accuracy. However, issues such as resistance to change, poor forecasting inputs, and fragmented systems continue to limit outcomes. The findings suggest that predictive analytics supports workforce resilience only when paired with strategic alignment and internal readiness. Future research should explore long-term adoption effects, policy interactions, and cross-sector comparisons.

2025, Kuantum Journal of Artificial Intelligence, Robotics, Machine learning and Data Science

Abstract
In the evolving landscape of software development, test automation is becoming increasingly critical for ensuring
high-quality releases at speed.
This paper explores the transformative potential of integrating AI-driven predictive analytics into test automation
frameworks. By leveraging advanced machine learning algorithms, predictive models, and data-driven insights, this
approach aims to optimize test coverage, enhance defect detection and improve the overall efficiency of the testing
process. The paper details the key techniques involved in implementing predictive analytics in test automation,
presents case studies highlighting its impact, and discusses the challenges and future directions of this innovative
approach.
The introduction of predictive analytics into the domain of test automation represents a paradigm shift. It allows
testing to not only be automated but also be intelligent, enabling the identification of potential issues before they
manifest in production environments. This shift from reactive to proactive testing is essential in a world where
software is becoming increasingly complex, and the costs associated with defects are growing exponentially.

2025, International Journal of Science and Research (IJSR)

In the face of increasing climate-related catastrophes and large-scale emergencies, the need for seamless coordination between military and civilian agencies has become more critical than ever. Effective disaster preparedness relies heavily on the ability to integrate, analyze, and act on diverse data sources. However, traditional systems often suffer from fragmented data silos, inconsistent formats, and slow decision-making processes, hindering timely and coordinated responses. This paper explores the application of Extract, Transform, Load (ETL) processes and Business Intelligence (BI) tools as a robust framework to bridge this operational gap. ETL pipelines are used to collect and standardize data from weather agencies, emergency services, defense systems, and non-governmental organizations (NGOs), transforming it into a structured format suitable for analysis. Once integrated, BI platforms generate real-time dashboards, predictive models, and visual reports that enhance situational awareness and facilitate proactive decision-making across agencies. The proposed method also includes the implementation of an MLP-LSTM architecture for forecasting critical disaster variables, such as casualty rates and resource needs, based on historical and real-time data. By combining temporal sequence learning with complex feature extraction, the model significantly improves the accuracy and speed of disaster impact predictions. Real-world scenarios, including responses to hurricanes and wildfires, are used to validate the effectiveness of this approach. Graphs illustrating improvements in data quality, loading time, response efficiency, and reduced casualties further reinforce the benefits of this system. Despite the advancements, limitations remain in terms of interoperability, data privacy, and the need for real-time automation in some legacy systems. Future work will focus on enhancing AI-driven ETL processes, incorporating IoT-based real-time feeds, and establishing standardized data-sharing protocols across jurisdictions. Overall, this study presents an integrated, data-driven model that strengthens disaster readiness and response through improved collaboration between military and civilian infrastructures.

2025, https://soim.edu.in/

In this paper, I examine the emerging paradigm shift in business analytics, focusing specifically on the intersection between artificial intelligence integration and data democratization. Drawing on nearly a decade of research experience, I investigate how these two seemingly divergent trends are creating a new analytical framework that simultaneously increases technical sophistication while expanding accessibility. Through a mixed-methods approach combining case studies and quantitative analysis, I demonstrate how organizations achieving balance between these forces show measurably higher rates of data-driven decision making (37% increase) and innovation outcomes (42% improvement in new product development cycles). This research addresses a significant gap in current literature, which has predominantly focused on either technical implementation or organizational adoption in isolation, rather than their synergistic relationship.

2025, Journal of Information Systems Engineering and Management

In the dynamic landscape of project management, the anticipation and mitigation of risks are paramount to achieving project success. Predictive analytics, encompassing statistical techniques and machine learning algorithms, offers a proactive approach by analyzing historical data to forecast potential project risks. This paper explores the integration of predictive analytics into risk identification and mitigation processes within project management. Utilizing methodologies such as Monte Carlo simulations and regression modeling, the study demonstrates how predictive analytics can enhance decision-making, optimize resource allocation, and improve project outcomes. The findings underscore the significance of datadriven strategies in preempting risks and ensuring project resilience in an increasingly complex and uncertain environment.

2025, World Journal of Advanced Engineering Technology and Sciences

This article explores the complex intersection of artificial intelligence, personalization, and privacy in digital environments, exploring how organizations can effectively balance personalized user experiences with ethical considerations and regulatory compliance. The article shows key challenges in this domain, including regulatory frameworks like GDPR and CCPA, ethical concerns such as algorithmic bias and discrimination, and the growing importance of zero-party data as a user-centric approach to data collection. The article further analyzes how explainable AI (XAI) frameworks can address the "black box" nature of AI systems while building user trust. Through article analysis of current literature and industry practices, this article provides strategic recommendations for implementing responsible AI personalization that respects user privacy, maintains transparency, and establishes trust-based relationships between organizations and their users in an increasingly AI-driven digital ecosystem.

2025, European Journal of Computer Science and Information Technology

Microsoft's AI chatbot Tay represents a pivotal case in conversational AI development, illustrating the critical importance of architectural safeguards and ethical constraints in machine learning systems. This technical examination dissects the architectural design flaws, implementation vulnerabilities, data processing weaknesses, and training regime deficiencies that contributed to Tay's rapid behavioral degradation when exposed to adversarial inputs. By identifying specific technical shortcomings-from inadequate content filtering to excessive parameter sensitivity and problematic reinforcement learning configurations the article establishes a framework for understanding conversational AI failures and outlines necessary implementation requirements for creating responsible systems that maintain ethical boundaries while preserving adaptive learning capabilities.

2025, IJPUBLICATION | IJRAR | www.ijrar.org | E-ISSN 2348-1269, P- ISSN 2349-5138

Artificial Intelligence (AI) and Machine Learning (ML) have profoundly reshaped electrical engineering by introducing automation, predictive analytics, and optimized system performance. AI-driven methodologies now enhance power grids, signal processing, industrial robotics, and smart energy management. This paper provides an extensive review of AI and ML applications in electrical engineering, discussing case studies, technical frameworks, challenges, ethical concerns, and future directions.

2025

Traffic offenses pose a significant challenge to road safety, particularly in developing countries like Nigeria, where the consequences often result in severe accidents and fatalities. This paper surveys recent advancements in artificial intelligence (AI) and deep learning methodologies applied to traffic offense prediction. By reviewing various studies, we examine the effectiveness of different models, including multidimensional data analysis, computer vision, and neural networks, in identifying and predicting traffic violations. The literature highlights the importance of integrating diverse data sources and local context to enhance the accuracy of predictive systems. Despite notable progress, significant gaps remain, especially in region-specific applications that consider unique traffic dynamics. Our findings underscore the need for further research to develop robust, context-aware AI solutions that can effectively mitigate traffic offenses and improve overall road safety. This survey aims to provide a comprehensive overview of existing approaches while laying the groundwork for future innovations in traffic management systems.

2025

Phishing attacks pose a significant cybersecurity threat globally, with developing nations like Nigeria facing unique challenges due to localized tactics and cultural factors. This paper presents a novel approach to phishing mitigation in Nigeria, leveraging Natural Language Processing (NLP) and Deep Learning techniques to enhance both automated detection and user training. We analyze a corpus of Nigeria-specific phishing attempts, identifying linguistic patterns and cultural references commonly exploited by attackers. Using this data, we train a deep learning model capable of detecting localized phishing content with high accuracy. Building on this technical foundation, we design a dynamic anti-phishing training program that adapts to individual user behavior and local phishing trends. A Hybrid Deep learning modelsrecurrent neural networks (RNNs) and transformer-based models (BERT), was trained on large datasets of phishing and legitimate samples to learn discriminate features and classify new instances. Our results demonstrate significant improvements in both automated phishing detection rates and user resilience to social engineering tactics. The model achieved high precision (0.89), recall (0.94), and F1-scores (0.92, 1.00).This research contributes to the field by showcasing the potential of combining advanced AI techniques with culturally informed strategies to create more effective, localized cybersecurity solutions.

2025, Journal of Science Engineering Technology and Management Science

The research looks into the role of AI in matching large datasets to make decisions, reduce risks, and improve efficiency in these two sectors. Large datasets allow early detection of diseases, the development of personalized treatments, fraud avoidance, and improved forecasting in finance because of AI. There are challenges, including low quality of data, different systems not being able to share, ethical aspects, and rules. By using secondary data and carrying out thematic analysis, the study identified that using advanced AI, such as ensemble and federated learning, can make predictive systems flexible, secure, and transparent.

2025, ER Publication

This study examines how artificial intelligence is reshaping the landscape of digital marketing, with particular focus on its capacity to improve personalization, streamline automated processes, and support data-informed strategic decisions. By incorporating technologies such as machine learning, predictive modeling, and generative tools, marketers are now better equipped to deliver individualized content, enhance campaign efficiency, and respond to consumer behavior more effectively. At the same time, the growing reliance on AI introduces critical challenges, including issues of data ethics, algorithmic fairness, transparency, and organizational preparedness. This paper provides an integrated analysis of these developments, offering insights into both the benefits and complexities that AI brings to contemporary marketing practices.

2025, AI-DRIVEN MARKETING ANALYTICS FOR RETAIL STRATEGY: A SYSTEMATIC REVIEW OF DATA-BACKED CAMPAIGN OPTIMIZATION

Artificial intelligence (AI) has emerged as a transformative force in retail marketing, fundamentally reshaping how organizations design, implement, and optimize campaign strategies. This umbrella review synthesizes findings from 72 peer-reviewed systematic reviews and meta-analyses published between 2010 and 2024, providing a comprehensive, macro-level evaluation of how AI is applied within marketing analytics to enhance retail performance. The reviewed literature spans a wide array of AI techniques-including supervised learning, unsupervised learning, deep learning, reinforcement learning, and natural language processing (NLP)-and their respective roles in improving campaign forecasting, real-time adaptability, customer segmentation, personalization, sentiment analysis, and attribution modeling. The study finds that supervised learning algorithms are widely utilized to predict campaign performance metrics such as conversion rates and customer retention, while deep learning models, particularly LSTM and CNN, are applied in modeling sequential consumer behavior and enhancing journey personalization. Reinforcement learning is frequently employed to enable real-time decision-making in campaign delivery and loyalty programs, while unsupervised clustering methods like Kmeans and DBSCAN are central to AI-enabled psychographic and behavioral segmentation. Additionally, NLP techniques-especially transformer-based models like BERT and GPTare instrumental in analyzing sentiment, identifying intent, and optimizing conversational engagement across digital touchpoints. A key contribution of this review is the synthesis of emerging research that addresses legal and ethical implications, with a particular focus on regulatory frameworks such as the General Data Protection Regulation (GDPR) and California Consumer Privacy Act (CCPA). These regulations have prompted shifts in AI marketing system design, leading to increased transparency, and consumer control. The study offers valuable insights for scholars, practitioners, and policymakers seeking to understand the scope, effectiveness, and governance of AI-driven marketing analytics in retail contexts.

2025

2025, Comparative Analysis of Machine Learning Algorithms for Predicting Credit Risk in Microfinance Institutions in Uganda

Credit risk remains one of the most persistent threats to the sustainability and operational efficiency of microfinance institutions (MFIs), particularly in developing countries like Uganda, where traditional credit appraisal systems are largely manual, subjective, and inadequate for detecting borrower default risk. In response to these challenges, this study undertakes a comparative analysis of selected machine learning (ML) algorithms to enhance credit risk prediction among Tier III MFIs in Uganda. Grounded in Asymmetric Information Theory and Credit Scoring Theory, the study adopts a quantitative, positivist research paradigm and employs a comparative experimental research design. Secondary data comprising 5,000 anonymized loan records from selected MFIs (2020–2024) will be pre-processed using data cleaning, encoding, feature scaling, and SMOTE-based class balancing techniques. Four ML models Logistic Regression, Decision Tree, Random Forest, and Support Vector Machine will be trained and evaluated using standard performance metrics, including accuracy, precision, recall, F1-score, and the Area Under the Curve (AUC). A 10-fold cross-validation strategy will be used to ensure model robustness and mitigate overfitting. The study aims to identify the most effective algorithm for improving credit scoring in Uganda’s microfinance sector, offering a data-driven framework to support decision-making, reduce loan default rates, and promote financial inclusion. Findings will also contribute to academic discourse, regulatory innovation, and the practical adoption of ethical artificial intelligence in credit risk management within resource-constrained financial ecosystems.
Keywords: Credit Risk Prediction, Machine Learning, Microfinance Institutions, Uganda, Logistic Regression, Random Forest, Support Vector Machine, Credit Scoring, Financial Inclusion, Algorithmic Comparison

2025, IGI Global

As cyber threats grow, national security measures struggle to keep pace with sophisticated attacks. Deep learning and large language models (LLMs) revolutionize cybersecurity by enabling advanced threat detection automated response... more

2025

Laboratory billing is complicated and vital to healthcare. Billing inefficiencies can cause claim denials, reimbursement delays, and financial losses due to complex coding, frequent compliance updates, and human error. Laboratory billing is being transformed by AI and automation, improving accuracy, efficiency, and compliance. AI and automation streamline laboratory billing, reduce errors, and improve financial performance. Intelligent billing and payment automation can boost lab revenue. Simplified processes, reduced denials, increased reimbursement, flawless payment methods, and more can greatly improve laboratory functions.

2025, International Journal of Science and Research (IJSR)

Water subjected to the presence of a magnetotelluric anomaly shows consistent and significant shift in pH, even when fully shielded against magnetic, electric and electromagnetic fields during exposure. Results indicate presence of a yet... more

2025, Journal of Artificial Intelligence and System Modelling (JAISM)

Millions of people worldwide suffer from Chronic Obstructive Pulmonary Disease (COPD), a common chronic respiratory illness. Readmissions can frequently be avoided when patients at high risk are treated promptly and with increased monitoring. Therefore, it becomes vital to identify hospital readmission risk early on. This research undertook a comparative analysis between 2 distinct models, Extra Trees Classification (ETC) and Adaptive-Boost Learning Classifier (ADAC), each augmented with School Based Optimization (SBO) and Flying Foxes Optimization (FFO) techniques for hyperparameter optimization. Their efficacy was evaluated in forecasting COPD using various performance metrics, including accuracy, precision, recall, and F1-score. Independent evaluators were engaged to scrutinize the model outcomes to ensure impartial assessment. These original models were further refined through hybridization with the aforementioned optimizers, resulting in ETSB (ETC + SBO), ETFF (ETC + FFO), ADSB (ADAC + SBO), and ADFF (ADAC + FFO). In the testing phase, the ETFF model demonstrated superior performance with an accuracy of 0.8917, while the ADAC model exhibited comparatively weaker performance with an accuracy of 0.7500. Similarly, in terms of precision, the ETFF model outperformed others with a value of 0.8940, whereas the ADAC model showed the weakest precision performance with a value of 0.7610.

2025

This study explores the transformative impact of People Analytics and Artificial Intelligence (AI) on modern Human Resource Management (HRM) practices. Using a mixed-methods approach, including case studies, interviews with HR professionals, and secondary data analysis, the research investigates how organizations are integrating these technologies to enhance HRM efficiency, effectiveness, and sustainability in employment practices. The case studies highlight a range of applications, such as optimizing recruitment, refining workforce planning strategies, and enhancing employee engagement through data-driven insights. These applications are analyzed in terms of their contribution to sustainable employment, including fostering fair and equitable work conditions. Interviews with HR professionals provide in-depth perspectives on the challenges and successes of AI and analytics adoption, emphasizing the evolving role of HR as a strategic partner in decision-making and their key contribution to sustainable workforce management. Secondary data sources further enrich these insights, offering contextual background that reinforces the study's findings, particularly regarding the broader implications for sustainable work and employment. The research emphasizes the strategic need for organizations to embrace AI and People Analytics to remain competitive in the digital age, while ensuring that these technologies are implemented responsibly to drive innovation, optimize HRM practices, and improve overall organizational performance. By addressing both the opportunities and challenges of AI and People Analytics in HRM, this study advances the literature by providing a comprehensive understanding of their strategic implications for sustainable work and employment. Future research could explore the long-term effects of AI on workforce dynamics, ethical concerns, and strategies to enhance diversity and inclusion through AI-driven HRM practices, with a particular focus on sustaining high-quality employment in the digital era.

2025, Journal of Management World 2025, 2: 451-460

The deployment of 5G technology is revolutionizing customer engagement in the telecom industry, offering faster connectivity, ultra-low latency, and seamless digital experiences. This study explores the impact of 5G-driven digital transformation on customer retention in the UAE telecom sector by examining how advanced technologies-such as AI-powered chatbots, real-time analytics, immersive AR/VR experiences, and IoT integration-enhance user engagement and satisfaction. Employing a qualitative research approach, this study conducts in-depth interviews with 15 industry experts, including telecom executives, digital transformation specialists, and customer experience strategists. Thematic analysis is applied to extract key insights on the benefits, challenges, and future potential of 5G in fostering customer loyalty. Findings reveal that while 5G enables hyper-personalization, seamless omnichannel experiences, and improved customer support mechanisms, telecom providers face significant challenges, including high infrastructure costs, data privacy concerns, and regulatory compliance. The study contributes to existing research by providing a strategic framework for telecom operators to leverage 5G in customer retention initiatives. Additionally, it offers practical implications for policymakers, industry stakeholders, and digital marketers in optimizing 5G-driven customer engagement models. By bridging the gap between technological advancements and customer loyalty strategies, this research presents actionable recommendations for sustainable growth in the UAE telecom industry.

2025, IGI Global

The integration of Internet of Things (IoT) technologies and big data analytics offers transformative potential for the maritime industry by enhancing safety, sustainability, and efficiency. This research explores IoT-enabled systems and big data platforms to address challenges like navigational safety, environmental compliance, and resource optimization. IoT devices provide real-time data for predictive maintenance, while big data analytics processes vast datasets to uncover actionable insights. The study highlights sustainability through fuel optimization, emission monitoring, and reduced environmental impact. Challenges, including data privacy and cybersecurity, are examined alongside strategies for secure implementation. Case studies in shipping and port management showcase successful applications, offering a framework for leveraging these technologies to advance innovation in maritime operations.

2025, Academy Journal of Science and Engineering (AJSE)

Galamsey, also known as illegal small-scale mining, persists in causing significant damage to Ghana's environment, including water bodies, agricultural areas, and public health. The present study introduces a comprehensive approach that utilizes Artificial Intelligence (AI) technology to promptly identify, oversee, and forecast illicit mining operations. By employing satellite imaging, drone monitoring, predictive analytics, and machine learning models, we propose a scalable and effective method to reduce the environmental and economic impact of galamsey. A methodology is presented that describes the development and execution of an artificial intelligence system utilizing actual data from high-risk mining areas in Ghana. The present study provides empirical evidence supporting the efficacy of artificial intelligence (AI) in facilitating real-time surveillance and forecasting forthcoming illicit mining operations. Furthermore, we address possible obstacles, including technical constraints, privacy issues, and the scarcity of proficient staff, and provide suggestions for surmounting these hindrances.

2025, REST Publisher

Introduction: This study offers a thorough analysis of deep learning and artificial intelligence from 1961 to 2018, providing information about the underlying mechanics, industrial applications, and future developments. The study aims to help researchers and practitioners understand the evolution, challenges, and opportunities associated with AI-driven innovations. Research Significance: This study's importance stems from its comprehensive exploration of the impact of AI on various industrial domains. AI-driven data analytics, predictive maintenance, and decision-making systems are reshaping industrial landscapes by improving operational efficiency and reducing costs. By analyzing past trends and current developments, this study offers insightful information for upcoming AI applications. It also draws attention to difficulties associated with to AI adoption, such as data security, algorithmic transparency, and ethical considerations, ensuring a holistic perspective for stakeholders in academia and industry. Methodology: SPSS Statistics is a powerful software tool utilized for to analyze data in a number of domains, like as social sciences, healthcare, marketing, and education. It offers an extensive collection of statistical tools for organizing, evaluating, and interpreting data. SPSS allows users to perform a wide range of analyses, such as descriptive statistics, regression, ANOVA, factor analysis, and hypothesis testing. Its sophisticated data manipulation features and user-friendly interface make it popular among researchers and analysts. SPSS also supports the creation of charts and reports, aiding in the presentation of data-driven insights.

2025, INTERNATIONAL JOURNAL OF ENGINEERING INNOVATIONS AND MANAGEMENT STRATEGIES

The increasingcomplexity of real-world problemsofteninvolves multiple conflicting objectives thatrequire intelligent and adaptive solutions. This paper proposes an Intelligent Multi-Objective Optimization Framework thatintegratesdynamic self-adaptation mechanismswithevolutionarylearningalgorithms to efficientlynavigatecomplexsearchspaces. Unliketraditionalstaticoptimization techniques, the proposedframeworkdynamicallyadjusts control parameters in real-time, enablingbetter convergence and diversitypreservationthroughout the optimization process. Evolutionarystrategiessuch as geneticalgorithms, differentialevolution, and particleswarmoptimization are enhancedwith feedback-driven adaptation modules, allowing the system to evolveitsstrategiesbased on historical performance and environmental shifts. Experimentalresults on benchmark multi-objective problemsdemonstratesuperior performance in terms of convergence speed, solution diversity, and robustnesscompared to existingmethods. The frameworkisalsovalidatedthrough case studies in domainssuch as supplychain design, energy management, and smart city planning. The integration of dynamiclearning and multi-objective trade-off handling enables the framework to provide high-quality, Pareto-optimal solutions with minimal manual intervention, makingit a promisingapproach for solvingcomplex real-time optimizationproblems in adaptive environments.

2025, International Journal of Information Technology & Management Information System (IJITMIS)

This comprehensive technical article explores the transformative impact of Natural Language Processing (NLP) in modern survey programming, examining how advanced computational techniques are revolutionizing data collection and analysis... more

2025, International Journal for Multidisciplinary Research (IJFMR)

This study explores the role of artificial intelligence (AI) in enhancing decision-making and operational efficiency in mergers and acquisitions (M&A) within the U.S. capital market. In recent years, AI technologies have been increasingly adopted to support various stages of the M&A process, including target identification, due diligence, valuation, and integration. The primary aim of this research is to examine how AI contributes to improved outcomes in M&A transactions and to assess the associated risks and limitations. The study employs a case study methodology, analyzing selected M&A transactions where AI tools were integrated into strategic and operational decision-making. The findings indicate that AI significantly reduces the time and cost associated with due diligence, enhances data accuracy, and supports better forecasting and scenario analysis. Furthermore, the study revealed that AI enables more objective decision-making by minimizing cognitive bias and processing large volumes of structured and unstructured data. The study also identifies several challenges. These include concerns about data privacy, cybersecurity risks, the transparency of AI algorithms, and the potential legal implications of relying on automated systems. The research highlights the need for comprehensive legal frameworks and ethical guidelines to govern the use of AI in M&A. In conclusion, AI has the potential to transform the M&A landscape in the U.S. capital market by improving efficiency, accuracy, and strategic clarity. Nevertheless, its successful integration requires careful attention to legal, ethical, and regulatory considerations.

2025, InternationalJournal of Emerging Trends in Computer Science and Information Technology

However, these environments encounter challenges related to resource fragmentation, inconsistent governance structures, and interoperability limitations, which impact overall performance during high workloads, system failures, and sudden demand fluctuations. This study presents a systematic evaluation framework to assess multi-cloud strategies using critical performance indicators, including response time, fault recovery, scalability, and data consistency. A scenario-based testing methodology is employed to analyze the performance of four multi-cloud architectures: Hybrid Multi-Cloud, Multi-Cloud Balancing, Cloud Bursting, and Distributed Multi-Cloud. Additionally, SWOT and PESTLE analyses are incorporated to examine strategic, technical, and regulatory factors influencing multicloud deployment. The findings demonstrate that Distributed Multi-Cloud Architecture achieves the highest reliability (94%) and the fastest failure recovery time (15s), ensuring superior fault tolerance. Meanwhile, Cloud Bursting offers the lowest response time (220ms) and the highest scalability rating (5), making it ideal for dynamic workload management. This study provides data-driven insights to support organizations in optimizing multi-cloud performance, improving governance models, and enhancing interoperability.

2025, International Journal of All Research Education and Scientific Methods (IJARESM)

It can be noted that digital platforms and search engines have revolutionized the way people and organizations look for information. However, query analytics does introduce a new avenue through which AI can improve the understanding and projection of trends involved in financial searches for significant advantages that businesses, researchers, and policy thinkers can take advantage of. Still, it can work millions of user search queries, discern trends in new currents, and offer a precious understanding of markets' probable behavior or where widespread interest could sooner or later shift. These enable financial institutions to improve the decision-making process about providing products needed by customers and the movement of the market. Studies have shown that these simplified search patterns are accurately identified and analyzed by natural language processing and machine learning algorithms, which propels innovation in financial services (Smith & Jones, 2021). Even more, integrating AI analytics ensures that real-time flexibility is deemed crucial in the unforgiving financial market where timing and accuracy are everything, as Brown et al. (2020) pointed out. However, there remain many issues associated with the use of analytic AI tools, medical imaging being a good example. Three main issues raised with using diffusion on a large scale are data privacy, concerns of bias within the algorithm, and combining multiple data sources. They also reveal that since the quality and variability of the input data affect the precision of the predictions, strict data management measures are required. This has also been backed by the fact that domain-specific training is one of the essentials to achieving the best performance, particularly in high-nuanced domains such as the financial domains (Johnson et al., 2019). In this respect, the article describes some primary methodologies, key challenges, and practical implications of applying AI-driven query analytics for prediction in financial search trends. To this end, this work will consider case scenarios and explore empirical literature to assess how AI is changing the face of financial data analysis and make valuable recommendations for managing its implications (Peterson, 2022). Keywords: Artificial intelligence technologies, Dynamics in searching financial information, MID in analyzing the search terms, how to pave AI in finance, natural language processing, predictive modeling of markets, data mining of financial info, analyzing the trends in the search engines, algorithmic prediction, data-driven approaches to decision making, financial innovations, real-time analysis, consumption trends in finance, data management in finance.

2025, International Journal of ADVANCED AND APPLIED SCIENCES

Through the phenomenon of data, big data and data analytics have provided an opportunity to collect, store, process, analyze and visualize an immense amount of information. Healthcare is recognized as one of the most information-intensive sectors. An urge to explore analytics has been sparked by the rapid growth of data within the healthcare sector. Most employers in Malaysia provide medical benefits that are included in the medical insurance plan for their employees. Data collected such as the history of medical claims are stored with the HR (Human Resource) which contributes to the potential of analyzing and recognizing trends within medical claims to better understand the use and overall health of the employee population. Patients with higher risk will generally convert into patients with high costs. Hence, early intervention of these patients will allow employers to potentially minimize costs and plan preventative steps. In predictive analysis, Decision Trees and Regression are ...

2025

The transformative impact of Artificial Intelligence (AI) on the burgeoning e-commerce sector in the United Arab Emirates (UAE). Focusing on consumer perspectives, the study examines the synergistic relationship between AI integration and the evolving e-commerce practices within the UAE. It highlights how the incorporation of AI redefines business operations and consumer interactions on e-commerce platforms, showcasing the UAE's leading position in innovation and technological advancement. Utilizing rigorous primary research methods, including surveys and interviews, alongside comprehensive secondary research, the findings reveal significant trends such as the predominance of younger demographics, a preference for personalized experiences, and growing concerns regarding data security and privacy. The results indicate a strong consumer inclination towards AI-driven features; however, respondents also underscore the necessity for enhanced data protection regulations and increased customization. This study underscores the importance of a balanced approach to AI implementation, emphasizing the critical role of customer trust and innovation in supporting the UAE's rapid e-commerce growth.