Papers by IAEME Publication
IAEME PUBLICATION, 2023
The advent of machine learning (ML) has revolutionized systemic risk identification in global fin... more The advent of machine learning (ML) has revolutionized systemic risk identification in global financial markets by enhancing predictive capabilities and reducing the probability of financial crises. This paper explores the application of ML techniques in identifying and managing systemic risk, providing a detailed review of pre-2022 literature. Employing quantitative analyses and case studies, this study demonstrates the strengths and limitations of ML in capturing risk patterns. It further evaluates ML's role in complementing traditional financial models, emphasizing areas such as sentiment analysis, credit risk evaluation, and market volatility prediction. While ML offers promising advancements, challenges persist in terms of algorithmic transparency and ethical considerations. The findings contribute to ongoing discussions on optimizing ML-driven financial risk management practices.
IAEME PUBLICATION , 2025
AI-driven Master Data Management (MDM) frameworks have emerged as a cornerstone for ensuring data... more AI-driven Master Data Management (MDM) frameworks have emerged as a cornerstone for ensuring data integrity, real-time synchronization, and enhanced business value. By leveraging machine learning algorithms and advanced analytics, these frameworks streamline data governance, reduce inconsistencies, and enable actionable insights. This paper explores the role of AI in transforming traditional MDM systems, reviews existing literature, and identifies the benefits, challenges, and future prospects of these frameworks.
IAEME PUBLICATION, 2024
The adoption of Artificial Intelligence (AI) in modular cloud infrastructures has transformed res... more The adoption of Artificial Intelligence (AI) in modular cloud infrastructures has transformed resource management, enabling predictive scaling, cost optimization, and improved fault tolerance. This paper explores AI-driven innovations in modular cloud systems, reviews literature and proposes a framework for efficient resource allocation. It discusses key challenges, applications, and case studies, and concludes with future research directions.
The emergence of high-frequency analytics (HFA) in financial technology (FinTech) has revolutioni... more The emergence of high-frequency analytics (HFA) in financial technology (FinTech) has revolutionized decision-making by leveraging machine learning (ML) algorithms. This paper explores the integration of ML-driven methods in HFA, discussing their effectiveness in predictive modeling, anomaly detection, and trade optimization. The results reveal significant advancements in applying ML models, particularly deep learning and ensemble techniques, which enhance the speed and precision of high-frequency financial applications. Tables and figures illustrate comparative results and highlight the impact of these methods on real-world FinTech ecosystems.
IAEME PUBLICATION, 2025
The rise of cloud computing has brought unprecedented opportunities for resource optimization but... more The rise of cloud computing has brought unprecedented opportunities for resource optimization but also significant challenges in efficiently managing resources across dynamic environments. Artificial Intelligence (AI)-driven decision systems offer robust solutions for optimizing resource allocation by predicting workloads, automating scaling, and minimizing costs. This paper examines AI methodologies for cloud resource allocation, reviews literature up to 2021, and discusses challenges and practical applications.
IAEME PUBLICATION, 2025
The integration of real-time data analytics (RTDA) within cloud-based learning systems (CBLS) has... more The integration of real-time data analytics (RTDA) within cloud-based learning systems (CBLS) has emerged as a transformative approach to enhance student performance and system efficiency. This research explores how RTDA can optimize adaptive learning, personalize educational content, and monitor learner engagement. By analyzing original studies, we identify key trends and challenges, propose a conceptual framework, and evaluate its practical implications. Through case studies and statistical analysis, the findings reveal substantial improvements in learning outcomes, operational scalability, and resource utilization. This paper underscores the potential of RTDA to revolutionize CBLS by enabling data-driven decision-making and fostering dynamic learning environments.
Cognitive computing has emerged as a transformative paradigm, integrating artificial intelligence... more Cognitive computing has emerged as a transformative paradigm, integrating artificial intelligence (AI) and machine learning (ML) to emulate human thought processes. This paper explores the interplay between cognitive computing paradigms and enterprise software architectural frameworks, emphasizing the synergistic potential to enhance operational efficiencies and decision-making capabilities. A detailed review of literature, supported by graphical illustrations, delves into the fundamental principles, challenges, and future directions of this confluence.
IAEME PUBLICATION, 2025
The integration of Artificial Intelligence (AI) into enterprise software applications has emerged... more The integration of Artificial Intelligence (AI) into enterprise software applications has emerged as a pivotal trend in modern software engineering. This paper explores the architectural frameworks and methodologies that facilitate embedding AI in scalable enterprise applications. By examining state-of-the-art practices, challenges, and innovations, we provide a comprehensive guide for developers and organizations seeking to leverage AI in large-scale systems. The findings are supported by literature reviews, graphical analyses, and proposed guidelines for optimized implementation.
IAEME PUBLICATION, 2025
The rapid growth of big data has created an urgent need to convert vast and
complex datasets into... more The rapid growth of big data has created an urgent need to convert vast and
complex datasets into actionable intelligence. This paper explores the interplay
between data engineering and artificial neural networks (ANNs) to process,
analyze, and derive meaningful insights. By implementing robust data engineering
pipelines and leveraging ANNs, businesses can gain deeper insights, optimize
operations, and improve decision-making processes. This study also reviews pre2021 literature to establish a foundational understanding and proposes a structured
framework for future applications.
IAEME PUBLICATION, 2025
The exponential growth of data in various fields necessitates advanced techniques to analyze and ... more The exponential growth of data in various fields necessitates advanced techniques to analyze and interpret multidimensional data efficiently. Multidimensional data visualization (MDV) plays a crucial role in transforming high-dimensional datasets into interpretable visual representations. This paper explores key MDV techniques, emphasizing their applications, advantages, and limitations in big data analysis. Methods such as parallel coordinates, dimensionality reduction, and hierarchical visualization are critically reviewed alongside emerging methods like t-SNE and UMAP. A literature review identifies trends and gaps, supported by examples and visualizations for enhanced comprehension. The findings underscore the transformative impact of MDV techniques in making complex datasets more accessible and actionable.
IAEME PUBLICATION, 2023
The integration of multidimensional big data analytics with dynamic financial risk assessment has... more The integration of multidimensional big data analytics with dynamic financial risk assessment has become pivotal in enhancing decision-making frameworks across industries. This study explores the synergy between advanced analytics techniques and financial risk management, leveraging historical and predictive data to optimize decision accuracy and efficiency. A conceptual framework is developed, highlighting the interplay between data dimensions, financial indicators, and adaptive modeling. The findings emphasize the transformative potential of big data analytics in financial decision-making, offering significant implications for policymakers and organizations.
IAEME PUBLICATION, 2023
AI-driven predictive analytics plays a crucial role in advancing digital transformation within th... more AI-driven predictive analytics plays a crucial role in advancing digital transformation within the financial technology (fintech) sector. This paper explores how artificial intelligence (AI) algorithms analyze large datasets to forecast trends, manage risks, and enhance operational efficiency in fintech. By leveraging predictive analytics, fintech companies can make data-driven decisions, personalize customer experiences, and improve financial services. This study reviews various AI-driven predictive models and their applications in fintech, highlighting their impact on innovation and competitiveness. Case studies illustrate successful implementations, emphasizing the transformative potential of AI-driven predictive analytics in driving fintech forward.
IAEME PUBLICATION, 2024
Cloud technologies have transformed the financial services industry by enhancing scalability, ope... more Cloud technologies have transformed the financial services industry by enhancing scalability, operational efficiency, and data management capabilities. However, these benefits bring challenges in maintaining data security and achieving regulatory compliance, especially for financial institutions that operate under stringent oversight. This research paper examines the current state of data security in cloud computing for financial institutions, exploring security mechanisms and compliance frameworks that have been developed to address these concerns. A comprehensive review of literature from original research papers is conducted, identifying emerging threats, best practices, and technologies supporting secure cloud environments. By analyzing case studies and statistical data, this paper offers insights into the effectiveness of current security measures and provides recommendations for enhanced compliance strategies.
IAEME PUBLICATION, 2023
The insurance industry is increasingly adopting artificial intelligence (AI) to enhance decision-... more The insurance industry is increasingly adopting artificial intelligence (AI) to enhance decision-making processes. However, the opacity of AI models often raises concerns about transparency, accountability, and fairness, particularly in risk assessment and pricing. Explainable AI (XAI) addresses these issues by providing insights into how AI models reach their decisions, fostering trust and compliance with regulatory requirements. This paper explores the role of XAI in improving risk transparency within the insurance sector, reviewing pre-2023 literature and presenting practical applications. Through analysis, we demonstrate the potential of XAI to revolutionize risk assessment practices, ensuring ethical AI usage while enhancing customer trust and operational efficiency.
IAEME PUBLICATION, 2023
The advent of machine learning (ML) has revolutionized systemic risk identification in global fin... more The advent of machine learning (ML) has revolutionized systemic risk identification in global financial markets by enhancing predictive capabilities and reducing the probability of financial crises. This paper explores the application of ML techniques in identifying and managing systemic risk, providing a detailed review of pre-2022 literature. Employing quantitative analyses and case studies, this study demonstrates the strengths and limitations of ML in capturing risk patterns. It further evaluates ML's role in complementing traditional financial models, emphasizing areas such as sentiment analysis, credit risk evaluation, and market volatility prediction. While ML offers promising advancements, challenges persist in terms of algorithmic transparency and ethical considerations. The findings contribute to ongoing discussions on optimizing ML-driven financial risk management practices.
IAEME PUBLICATION, 2024
The advent of Blockchain and Artificial Intelligence (AI) technologies offers transformative pote... more The advent of Blockchain and Artificial Intelligence (AI) technologies offers transformative potential in securing healthcare insurance data. Healthcare data breaches are increasingly common and costly, necessitating robust security measures. Blockchain provides a decentralized and tamper-proof structure, while AI enhances real-time threat detection and predictive analytics. This research paper explores the integration of these technologies, examining their synergy in protecting sensitive healthcare insurance data. It reviews existing literature, highlights recent advancements, and proposes a unified framework for implementing Blockchain and AI in healthcare insurance data security. Quantitative analyses demonstrate the effectiveness of such integration in minimizing breaches and optimizing system performance.
IAEME PUBLICATION, 2020
Traditional sequenced search-based alerting mechanisms in SIEM Enterprise Security are effective ... more Traditional sequenced search-based alerting mechanisms in SIEM Enterprise Security are effective for detecting predefined attack scenarios but exhibit significant limitations in handling the complexity and variability of modern threats. These mechanisms rely on rigid sequences of conditions to trigger alerts, which often results in missed detections when attackers use alternative techniques to achieve their objectives. This creates critical gaps in security monitoring and leaves enterprise environments vulnerable to sophisticated attack strategies.
To address these challenges, this paper introduces a Risk-Based Alerting (RBA) framework that leverages the advanced capabilities of SIEM’s Risk Analysis Framework. Unlike sequenced search-based systems, the RBA framework dynamically evaluates and scores events based on multiple factors, including the fidelity of the security event, the risk profile of the asset involved, and the criticality of the associated attack scenario. This approach ensures comprehensive coverage by capturing both high-fidelity and low-fidelity alerts. However, only high-priority alerts that exceed a predefined risk threshold are classified as "notable," significantly reducing the noise generated by low-impact alerts.
The RBA framework employs adaptive risk scoring mechanisms that account for evolving attack patterns and operational contexts. By incorporating non-overlapping scheduling, throttling mechanisms, and real-time dashboard enhancements, the framework streamlines alert prioritization and improves the overall efficiency of security operations. Furthermore, the integration of industry-standard frameworks, such as MITRE ATT&CK, ensures a robust and comprehensive mapping of attack techniques, enabling precise detection and actionable insights.
Our findings demonstrate that the RBA framework significantly enhances the prioritization and detection of critical events while mitigating operational inefficiencies. Key outcomes include a substantial reduction in false positives, improved usability of risk analysis dashboards, and better alignment with real-world threat landscapes. This paper concludes by highlighting the potential of RBA to transform SIEM Enterprise Security into a more dynamic, responsive, and effective defense mechanism against modern cyber threats.
A REVIEW PAPER ON THE STUDY OF ROAD USER CHARACTERISTICS USING VISWALK FOR KR MARKET
IAEME PUBLICATION, 2024
The rapid urbanization of cities such as Bangalore has led to a significant rise in both pedestri... more The rapid urbanization of cities such as Bangalore has led to a significant rise in both pedestrian and vehicular traffic, particularly in densely populated areas like KR Market. Understanding the dynamics of road user behaviour in these high-activity zones is essential for improving infrastructure and ensuring safety. This review paper explores the movement patterns of pedestrians, drawing on various studies to provide a comprehensive analysis. A key focus is on Viswalk, a sophisticated microscopic simulation tool for pedestrian dynamics, which facilitates the examination of critical behaviors such as walking speeds and crowd interactions. The insights gained from this analysis offer valuable information that urban planners and policymakers can leverage to make informed, data-driven decisions aimed at enhancing the safety and experience of road users in urban marketplaces.
IAEME PUBLICATION, 2024
Real-time data processing has emerged as a transformative force across industries, with global da... more Real-time data processing has emerged as a transformative force across industries, with global data volumes projected to reach 180 zettabytes by 2025. This technical analysis examines four significant implementations: PayPal's fraud detection system, Amazon's recommendation engine, Philips Healthcare's patient monitoring platform, and GE's predictive maintenance system. The article demonstrates how modern organizations leverage advanced technologies including edge computing, machine learning, and distributed systems to process millions of events per second while maintaining sub-100ms latencies.
Uploads
Papers by IAEME Publication
complex datasets into actionable intelligence. This paper explores the interplay
between data engineering and artificial neural networks (ANNs) to process,
analyze, and derive meaningful insights. By implementing robust data engineering
pipelines and leveraging ANNs, businesses can gain deeper insights, optimize
operations, and improve decision-making processes. This study also reviews pre2021 literature to establish a foundational understanding and proposes a structured
framework for future applications.
To address these challenges, this paper introduces a Risk-Based Alerting (RBA) framework that leverages the advanced capabilities of SIEM’s Risk Analysis Framework. Unlike sequenced search-based systems, the RBA framework dynamically evaluates and scores events based on multiple factors, including the fidelity of the security event, the risk profile of the asset involved, and the criticality of the associated attack scenario. This approach ensures comprehensive coverage by capturing both high-fidelity and low-fidelity alerts. However, only high-priority alerts that exceed a predefined risk threshold are classified as "notable," significantly reducing the noise generated by low-impact alerts.
The RBA framework employs adaptive risk scoring mechanisms that account for evolving attack patterns and operational contexts. By incorporating non-overlapping scheduling, throttling mechanisms, and real-time dashboard enhancements, the framework streamlines alert prioritization and improves the overall efficiency of security operations. Furthermore, the integration of industry-standard frameworks, such as MITRE ATT&CK, ensures a robust and comprehensive mapping of attack techniques, enabling precise detection and actionable insights.
Our findings demonstrate that the RBA framework significantly enhances the prioritization and detection of critical events while mitigating operational inefficiencies. Key outcomes include a substantial reduction in false positives, improved usability of risk analysis dashboards, and better alignment with real-world threat landscapes. This paper concludes by highlighting the potential of RBA to transform SIEM Enterprise Security into a more dynamic, responsive, and effective defense mechanism against modern cyber threats.