Asian Journal of Research in Computer Science
Not a member yet
792 research outputs found
Sort by
Enhancing Operational Efficiency in Claims Processing Through Technology
No full textAIM: To analyze the impact of Technology-Driven Claims Automation, with a focus on real-time fraud detection and enhancing accuracy in claims intake and validation. This study explores how advanced technologies such as AI, machine learning, and automation streamline claims workflows, reduce processing time, and enhance decision-making accuracy while mitigating fraudulent activities in real-time.
Study Design: A quasi-experimental design was employed to assess the effectiveness of Technology-Driven Claims Automation. The study analyzed pre- and post-implementation performance metrics, such as Claim Cycle Time, Claims Straight-Through Processing (STP) Rate, and Fraud Detection Rate.
Place and Duration of Study: This study was conducted at Global Insurance Systems over a 16-week period from April to September 2024, involving all applications, tools and software used in Claims.
Methodology: The methodology for enhancing claims processing leverages technology advancements in AI, automation, and predictive analytics to improve efficiency, accuracy, and fraud detection in Property & Casualty (P&C) insurance. It involves automated claims intake and processing, claims document verification, claims triaging and claim adjudication. Automated claims intake and processing eliminates manual data entry by using AI-powered chatbots, RPA, and cloud-based integrations, enabling policyholders to submit claims via self-service portals while AI validates and processes the information. Claims document verification applies OCR, NLP, and blockchain-based authentication to instantly extract, validate, and cross-check information from policyholder documents, invoices, and reports, improving accuracy and preventing fraud. Claims triaging utilizes OCR, machine learning, and computer vision to classify claims based on severity, risk, and potential fraud, ensuring legitimate claims are fast-tracked while suspicious cases are flagged for review. Multi-step workflow automation in claims adjudication integrates rule-based decision engines and predictive analytics to verify policy coverage, assess fraud risks, and automate approvals or payouts, reducing human intervention and processing time.
Conclusion: The introduction of AI, automation, and predictive analytics in claims processing has significantly improved efficiency, fraud detection, and accuracy in the P&C insurance industry. In our study, it reduced Claim Cycle Time by 50%, increased Fraud Detection Accuracy by 25%, reduced operational costs by 40%, and increased Customer Satisfaction by 35%. By leveraging automated claims intake, triaging, adjudication workflows, and document verification, insurers can streamline operations, reduce manual intervention, and enhance customer experience. These advancements enable faster settlements, better risk assessment, and improved compliance with regulatory standards. As technology continues to evolve, embracing AI-driven solutions will be essential for insurers to stay competitive, minimize fraud, and deliver seamless, real-time claims processing
Quantum Machine Learning for Secure Financial Forecasting: Mitigating Data Breaches and Adversarial Exploits
No full textQuantum Machine Learning (QML) offers a transformative approach to financial forecasting by enhancing predictive accuracy and cybersecurity resilience. This study evaluates QML’s effectiveness using financial market data from Yahoo Finance, comparing Quantum Long Short-Term Memory (QLSTM) to classical LSTM and ARIMA models. Security vulnerabilities were assessed using the IEEE DataPort adversarial attack dataset, while encryption performance was analyzed using Quantum Key Distribution (QKD) data from NIST. Experimental results demonstrate that QLSTM outperforms classical models, achieving lower RMSE (1.82), MAE (1.45), and MSE (3.31), indicating superior forecasting precision. Quantum Support Vector Machines (QSVM) exhibit increased adversarial robustness, limiting accuracy degradation to 11.67% under FGSM attacks and 15.60% under PGD attacks, whereas classical models suffer losses exceeding 24%. QKD provides a substantial security advantage over RSA-4096, achieving a 5.87 bps secure key rate and demonstrating over 100 years of resistance to quantum attacks, reinforcing its role as a next-generation cybersecurity mechanism for financial institutions. Despite these advantages, the adoption of QML in financial forecasting faces challenges related to high computational costs, hardware limitations, and integration complexities. Quantum security frameworks require significant infrastructure investments to ensure scalability and reliability. Financial institutions must prioritize QML investment, integrate quantum security mechanisms, and collaborate with regulatory bodies to establish standardized guidelines for secure financial applications. This study contributes to the growing field of quantum-enhanced financial analytics, highlighting its potential to mitigate cyber threats and improve financial forecasting reliability while addressing existing implementation barriers
Data-Driven Decision Making for E-Business Success: A Review
No full textThe revolutionary impact of big data in data-driven decision making (DDDM) is examined in this paper, with particular attention to its vital uses in e-business. According to the report, companies may use Big Data analytics to extract useful information from large, complicated datasets, which will ultimately lead to improved consumer engagement, tailored experiences, and operational efficiency. Artificial intelligence (AI), machine learning, and predictive analytics are examples of advanced technologies that are essential for spotting market trends, boosting innovation, and optimizing marketing strategies. Dynamic pricing, fraud detection, inventory management, and real-time campaign optimization are some of the primary uses that are highlighted. Businesses can stay flexible, competitive, and customer-focused in the digital economy with the help of these data-driven strategies. Big Data integration challenges are also covered in this assessment, including the need for strong data governance frameworks, ethical issues, and data privacy concerns. Expert staff and cutting-edge infrastructure are emphasized in the discussion of striking a balance between using innovation and guaranteeing accountability. Additionally, the research delves into the function of big data in promoting sustainability, emphasizing how its tactical use might stimulate social and environmental responsibility in global commerce. In order to help e-businesses go from intuition-driven to evidence-based decision-making, the results highlight how essential big data is. Organizations may open up new avenues for growth and innovation in a world that is becoming more and more data-centric by coordinating technology, strategy, and ethics
A Multi-level Clustering Framework for Cybersecurity Risk Stratification in Healthcare: A Dynamic, Overlapping Approach to Threat Classification and Mitigation
No full textThe increasing frequency and complexity of cyberattacks targeting the healthcare sector demand innovative approaches to threat classification and mitigation. As healthcare institutions increasingly depend on interconnected digital systems to manage sensitive data, the risk of breaches involving Protected Health Information (PHI) continues to escalate. In response to this challenge, this study proposes a novel, hybrid multi-level clustering framework that integrates Hierarchical Clustering, K-means Clustering, and Fuzzy C-means (FCM) Clustering to dynamically stratify cybersecurity threats in the U.S. healthcare sector. Utilizing a diverse dataset comprising over 1,200 breach incidents from the HHS Breach Portal, enriched with threat intelligence feeds and simulated SIEM logs, the model effectively captures evolving threats based on severity, frequency, and financial impact. Unlike previous models, this framework supports partial membership handling and real-time threat assessment, significantly improving threat categorization and predictive capabilities. Results demonstrate superior performance compared to traditional K-means clustering, with improved accuracy, coherence, and adaptability. Evaluation metrics confirm the model’s efficacy in enhancing decision-making, resource prioritization, and compliance adherence. This approach offers practical applications for healthcare institutions aiming to fortify digital infrastructure against sophisticated, evolving threats. Recommendations include adopting this hybrid model for proactive threat detection, integrating real-time data inputs, and promoting further research into dynamic, overlapping clustering methodologies. The findings present a valuable tool for researchers, policymakers, and practitioners striving to improve cybersecurity resilience and regulatory compliance within the healthcare industry
Multi-model Learning Methods for Oil Price Prediction
No full textPresent-day oil prices are rising due to certain conditions like inflation entire world. It is a major problem in the world. It affects so many fields connected to human life. Oil price prediction is most important for business scenarios. Machine learning algorithms play a key role in oil price prediction. Machine learning models predict the price of fuel. This paper aims to compare the machine learning models with multi-model learning models. To know in terms of accuracy and performance. Ensemble machine learning algorithms are most adaptive for different environments. The predicted price of crude oil in the future is decided using machine learning algorithms. In our research, we tested five models for calculating oil price prediction. Among these five models, tuning three models with hyperparameters. Hyperparameter tuning means AutoML, which boosts the performance of the models. The above three models’ performance shows more than 93%. Two models, support vector machine and linear regression, do not perform well. The accuracy rate is more than 50%
Enhancing Financial Cybersecurity in Cloud Engineering: A Systematic Review of Threats, Mitigation Strategies and Regulatory Compliance
No full textAims: This review analyses the intersection of cloud engineering and cybersecurity in the financial sector, highlighting how advanced cloud technologies can improve defences against cyber threats for safe evolution. The aim is to examine modern methodologies, frameworks, and technologies that enhance financial cybersecurity through cloud-based solutions.
Methodology: A comprehensive literature review methodology is employed to assess existing studies that explore prevalent trends and challenges based on peer-reviewed articles, technical reports, and industry case studies. A total of 16 papers and case studies were selected for their relevance and methodological robustness.
Result and Discussion: It thoroughly discusses the methods used for risk evaluation of data breach, phishing attacks, and ransomware, employing the principles of cloud engineering: scalability, elasticity, and automation. The review has further pointed out that financial institutions using cloud technologies are subjected to some critical cybersecurity threats, including data breaches, insider threats, and vulnerabilities that emanate from hybrid and multi-cloud environments. The paper finds that advanced mitigation techniques (such as a zero trust architecture, AI-driven fraud detection, blockchain, and Infrastructure as Code (Iac) provide solid approaches to boost cloud security. DevSecOps, microservices, automated CI/CD pipelines and other such secure cloud engineering practices are becoming adopted to boost resilience and compliance in a cloud infrastructure. Additionally, the reasons why it is essential to stick to the cloud security practices are being discussed and imposed on common regulations like GDPR, PCI-DSS, for instance, ISO/IEC.
Conclusion and Recommendations for Future Research: Finally, the review recommends that future research should focus on developing AI-driven security orchestration platforms, enhancing cloud governance models, and exploring socio-technical aspects of cybersecurity. Additionally, it advocates for an empirical investigation into the economic and operational impacts of device cloud-type transformations over time
Using Artificial Intelligence for Resource Forecasting in Strategic Project Management
No full textAims: This study aims to evaluate the impact of artificial intelligence on project management processes, with a focus on resource forecasting. It further identifies key implementation challenges and provides strategic recommendations for effective AI integration.
Study design: Analytical research based on secondary data and simulation modeling.
Place and Duration of Study: The research was conducted through analytical evaluation of global scientific publications and applied modeling between January 2024 and February 2025.
Methodology: The study applied an analysis of scientific literature to identify current trends in the use of artificial intelligence, a structural-logical method for generalizing forecasting processes, and machine learning-based simulation modeling to evaluate AI capabilities in project management. Comparative analysis and synthesis methods were used to develop practical recommendations, considering organizational, technical, and economic constraints.
Results: The study revealed that artificial intelligence improves the accuracy of project resource forecasting, reduces the risk of exceeding budgets, and enhances adaptability to change. In particular, the use of machine learning reduced forecasting errors by up to 17% compared to traditional methods. Key implementation challenges were identified, including poor data quality, high implementation costs, and insufficient staff competencies. A phased approach to AI integration is proposed, including pilot project deployment, reliable data preparation, and targeted staff training.
Conclusion: Artificial intelligence plays a critical role in enhancing the effectiveness of strategic project management by enabling more accurate forecasting, optimized resource allocation, and timely adaptation. Future research should focus on improving algorithmic accuracy, developing industry-specific AI models, and creating implementation standards to ensure long-term project sustainability and resilience.
This article is important for the scientific community as it addresses a critical challenge in modern project management - the integration of artificial intelligence into resource forecasting. The review systematizes recent interdisciplinary findings and supports the development of advanced methodologies at the intersection of AI and strategic planning. It contributes to bridging theoretical knowledge and practical applications across various industries. The results may serve as a foundation for further research and innovation in digital project management
Time Series Prediction for Traffic Flow Forecasting Using CNN
No full textTraffic problems are very common nowadays throughout the world. In India also heavy traffic also occurred in many populated cities. For this reason, the public loses their time and life, and this pollution impacts human health. So, traffic research is necessary for this situation. We concentrate on the traffic network to find a better solution or model to predict future traffic. Our proposed model uses a time series for traffic forecasting. It deals with time series analysis for traffic congestion, traffic control, and traffic prediction. This paper focuses on appropriate datasets with different vehicles in various time series. A novel time series forecasting model was used for this research, and it also predicted a 99% accuracy rate. A comparative study is also presented in this research
Experimental Data Analysis to Recognize and Visualise the Factors Contributing to Bank Customer Churn Prediction Using Ensemble Learning Models
No full textCustomer churn happens when a client breaks down using a specific corporation\u27s services and goods. It distresses the profit of industries heavily on their revenues. A novel customer acquisition is valuable up to five times more than absorbing an existing one. The target of this paper comprehend and predict customer churn in the banking sector. The bank wants to create more value out of its customer data. Analyse the data and propose how internal and external utilization of the analysis results increases the bank\u27s revenues. We focus on exploratory data analysis to recognize and visualize features causative of client churn. This analysis predicts the purpose of constructing machine models. These models perform classification tasks for the given dataset. Multiple models were tested in our present research for bank customer churn prediction. Among all models, the LGBM model predicts the highest accuracy, 82.1%
Visibility Improvement in Underwater and Traffic Images Using Color Balance and Fusion
No full textWe present a robust method for enhancing underwater images that suffer from visual degradation due to light absorption and scattering in water. The approach works with a single image and does not rely on additional hardware or prior information about the underwater scene or conditions. The process involves generating two distinct versions of the image from a white-balanced and color-corrected base, each emphasizing different visual features. These images are then fused using spatial weight maps that are specifically designed to enhance color contrast and preserve edge information. To minimize the introduction of low-frequency artifacts caused by abrupt transitions in the weight maps, a multiscale fusion technique is applied. Our method has been extensively tested through both visual and numerical evaluations, demonstrating improved visibility in darker regions, better overall contrast, and enhanced detail sharpness. The technique also performs consistently across different camera settings and has been shown to improve the performance of image processing tasks like segmentation and feature matching