Applied Science and Engineering Journal for Advanced Research
Not a member yet
146 research outputs found
Sort by
Optimizing Cloud Infrastructure through Advanced Development Practices in Financial Applications
Get PDFScalability, cost-effectiveness, and security are all advantages of cloud computing, which has become an indispensable component of financial applications. The optimization of infrastructure to enhance performance, reduce expenses, and enhance security remains a challenge as financial institutions continue to transition to the cloud. This study examines the impact of advanced development methodologies—DevOps, microservices architecture, Infrastructure as Code (IaC), and cloud cost optimization techniques—on the efficacy of cloud services in financial applications.
The research evaluates critical performance attributes, including deployment speed, resource utilization, cost efficiency, system downtime, and security vulnerabilities, in comparison to traditional and optimized cloud configurations. Findings include a 40% reduction in deployment duration, a 30% improvement in resource efficiency, a 25% cost reduction, a 60% decrease in outage, and a 60% reduction in security issues. These results emphasize that strategic cloud optimization significantly enhances operational efficiency while simultaneously guaranteeing compliance and security.
The research reveals that in order to achieve enduring scalability, resilience, and cost efficiency, financial institutions must implement a comprehensive cloud optimization strategy. Blockchain integration and AI-driven cloud administration may be explored in future research to improve the security of cloud applications in the financial sector
Forecasting Performance: Leveraging Machine Learning on Earned Value Data for Proactive Control
Get PDFThis study investigates the utilisation of machine learning methodologies in the context of earned value management (EVM) data, aiming for the anticipatory prediction and regulation of project outcomes. This research seeks to utilise machine learning frameworks, including regression analysis, decision trees, and neural networks, to forecast upcoming project outcomes, pinpoint possible risks, and improve the decision-making process. The study illustrates how the incorporation of sophisticated algorithms alongside conventional EVM data can yield enhanced, immediate insights into cost and schedule effectiveness. The document further explores the ramifications of this methodology for project leaders, providing a comprehensive structure for enhancing project oversight and regulation via insights derived from data
Balancing Innovation and Compliance in Financial SaaS Platforms: Harnessing Technology and Tools Convergence at PayPal
Get PDFThis research explores the strategic integration of RegTech in Financial SaaS platforms with a specific focus on PayPal and analyzes the company balance criteria with the technological processes. Thus, this research employs a secondary data, inductive approach, adopting interpretivism philosophy6 to enhance the research criteria. Thus, this research uses thematic analysis to evaluate PayPal’s adoption of AI-driven fraud detection, blockchain security and data analytics to develop transaction security and user experience while ensuring regulatory adherence. Findings indicate that PayPal has crucial development automation in compliance and reducing regulatory risks while improving efficiency and consumer trust. The company has experienced 2a 0.58% increase in daily transactions with 95% adoption of AI-driven detection by 2023. Moreover, this research analysis highlights that while technological advancements develop efficiency, regulatory complexities across jurisdictions pose ongoing challenges. Therefore, this research underscores the necessity of continuous innovation in compliance management and emphasizes RegTech solutions for sustainable growth
Infusing Generative AI into Supply Chain Management: Driving Intelligent and Anticipatory Operations
No full textBecause global supply chains are changing so quickly, businesses need to use new technologies to make them more flexible, accurate, and strong. This study looked into the possible use of Generative Artificial Intelligence (GAI) in supply chain management (SCM) to make operations smarter and more proactive. The study looked at GAI\u27s effects on important supply chain tasks like demand forecasting, inventory optimization, supplier risk assessment, and logistics coordination using a mix of approaches, including simulation modeling and expert reviews. The results showed that GAI made forecasts much more accurate, sped up decision-making, improved inventory levels, and made lead time less variable. Experts agreed that GAI had a lot of technological potential, but they also stressed the importance of human control, interpretability, and ethical use. The results showed how GAI can change the way supply chain ecosystems work by making them more proactive and data-driven, which lets them adapt to changing market conditions
Application of Machine Learning in Predicting Extreme Volatility in Financial Markets: Based on Unstructured Data
Get PDFSentiment analysis is an important tool for revealing insights and shaping our understanding of market movements from financial articles, news, and social media. Despite their impressive abilities in financial natural language processing (NLP), large language models (LLMs) still have difficulties in accurately interpreting numerical values and grasping financial context, limiting their effectiveness in predicting financial sentiment. This article introduces a simple and effective instruction-tuning method to solve these problems. We have made significant progress in financial sentiment analysis by converting small amounts of supervised financial sentiment analysis data into command data and using this approach to fine-tune a generic LLM. In experiments, our approach outperforms state-of-the-art supervised sentiment analysis models and widely used LLMs such as ChatGPT and LLaMAs, especially when numerical and contextual understanding is critical
Text Sentiment Detection and Classification Based on Integrated Learning Algorithm
Get PDFThe aim of this paper is to explore the importance of textual sentiment detection in the field of Natural Language Processing and to classify and detect sentiment through various machine learning algorithms. Firstly, we train using Park Bayes, Random Forest, XGB and Support Vector Machine models, and then integrate them into a voting classifier for comparative analysis. The results show that the Random Forest model performs the best in the training set; and in both the validation set and the test set, the accuracy of the voting classifier is the highest, reaching 93.32% and 94.47%, respectively, which shows its superiority in the classification of text sentiment detection. Taken together, voting classifier has the best prediction results and provides an effective solution for text sentiment detection. This study not only provides an in-depth comparative analysis of the performance of different machine learning algorithms in text sentiment detection, but also provides a useful reference for subsequent related research and applications
Strength and Durability Assessment of Concrete Bricks Enhanced by Construction & Demolition Waste Integration
Get PDFThe responsible management of construction and demolition waste is a critical issue, primarily due to the substantial volume of waste generated. Landfilling remains a prevalent method for disposal. This project explores the use of construction and demolition waste (C&D) as a substitute for coarse aggregate in cement brick production, with varying percentages (ranging from 0% to 100%). Various mix types were employed in the casting of these bricks. The study encompasses the evaluation of compressive strength at intervals of 7, 14, 21, and 28 days, as well as the implementation of water absorption tests, alternate drying and wetting tests, and examinations for sulphate and chloride attacks
Designing Resilient and Scalable Applications: A Performance Engineering Roadmap for Cloud-Native Systems
No full textMore and more people are using cloud-native architectures, which has made it harder to make applications that work well, scale well, and stay up in very dynamic situations. Conventional performance optimization methods, typically utilized after deployment, are inadequate for managing the intricacies of microservices, container orchestration, and elastic infrastructure. This hypothetical research puts up a systematic performance engineering path for creating cloud-native applications that can handle a lot of traffic and stay up and running. The roadmap includes analyzing performance needs, modeling workloads, evaluating scalability, injecting faults, continuously monitoring, and optimizing the application over time. Simulated findings show that systems built using this roadmap are more scalable when there are a lot of users or a lot of work to do, they can handle more errors, they can recover from failures faster, and they use resources more efficiently. The results show how important it is to make performance engineering a regular and proactive part of cloud-native systems to help with reliability and operational excellence
Precision in Practice: Enhancing Healthcare with Domain-Specific Language Models
Get PDFThis paper investigates the role of domain-specific language models (DSLMs) in enhancing the accuracy and reliability of responses to general medical inquiries. Focusing on the healthcare sector, we explore how LLMs, when fine-tuned with specialized medical datasets, surpass general language models in handling complex medical terminology and ensuring patient data confidentiality. The benefits of these models include increased precision in medical advice, a reduction in misinformation risks, and tailored responses based on individual patient histories. Nonetheless, implementing these technologies comes with significant ethical, technical, and regulatory challenges, such as ensuring patient privacy, maintaining up-to-date medical knowledge, and navigating stringent compliance requirements. The paper concludes by discussing future directions, including the integration of DSLMs with telehealth services and ongoing advancements in model training techniques, underscoring the necessity for continued research, widespread adoption, and rigorous evaluation to fully leverage their potential in improving healthcare outcomes
Study of Physical, Durable and Microstructural Behaviour of Laterite Soil Based Geopolymer Bricks
Get PDFBricks are the major building materials used in the field of construction. The most commonly used bricks are clay bricks and concrete blocks. The discharge of carbon di oxide into the atmosphere has been increasing day by day. For the production of burnt bricks, usually 22 tons of coal were burnt which produces nearly equal amount of carbon di oxide. The most vital role in terms of construction material is usually associated with Portland cement. Since the manufacture of cement leads to the liberation of CO2 in large quantity. So, an alternate is required to replace cement in the place as binding agent. Therefore, the alternative to these is the Geopolymer bricks. Geopolymers have great mechanical properties, and has the synthetic temperature of 250C to 800C. In this study, Laterite soil is used to prepare the bricks by using Geopolymer as a binding material by varying NaOH to Na2SiO3 ratio in Geopolymer precursor. Strength, durable and microstructural behavior of the brick is studied