Papers by Jeshwanth Reddy Machireddy
Australian Journal of Machine Learning Research & Applications, 2023
In the era of big data, the optimization of machine learning models within cloud-based data wareh... more In the era of big data, the optimization of machine learning models within cloud-based data warehousing systems has emerged as a critical domain of research and application. This paper presents an in-depth analysis of advanced data science techniques aimed at enhancing the performance and scalability of machine learning models in such environments. Cloud-based data warehousing systems offer substantial advantages, including scalability, flexibility, and the ability to handle vast amounts of data, yet they also introduce unique challenges related to model optimization. Model selection, hyperparameter tuning, and deployment strategies are pivotal aspects of optimizing machine learning models in these contexts. The paper begins by exploring model selection techniques tailored for cloud-based systems, emphasizing the need for models that not only perform well in theory but also scale efficiently with large datasets and distributed computing resources. The selection process involves evaluating various algorithms and architectures, including ensemble methods, deep learning models, and emerging techniques such as transformer-based architectures, considering their suitability for the specific requirements of cloud environments. Hyperparameter tuning represents another critical area of focus. The paper delves into advanced methods for hyperparameter optimization, including grid search, random search, and more sophisticated approaches such as Bayesian optimization and genetic algorithms.
African Journal of Artificial Intelligence and Sustainable Development, 2023
This research paper delves into the integration of artificial intelligence (AI) in digital market... more This research paper delves into the integration of artificial intelligence (AI) in digital marketing practices. It scrutinizes the strategies utilized, hurdles encountered, and forthcoming pathways for leveraging AI technologies, including machine learning, natural language processing, and predictive analytics, to refine marketing campaigns and augment customer engagement. By analyzing contemporary trends and emerging innovations, this paper offers insights into the evolving landscape of AI-driven digital marketing.
African Journal of Artificial Intelligence and sustainable development, 2021
In the contemporary business landscape, the integration of Artificial Intelligence (AI) and Machi... more In the contemporary business landscape, the integration of Artificial Intelligence (AI) and Machine Learning (ML) into data-driven strategies has emerged as a pivotal factor for organizational success and competitive advantage. This paper delineates a comprehensive framework for leveraging AI and ML to enhance business analytics, improve decision-making processes, and foster organizational growth. The framework proposed herein serves as a strategic guide for businesses seeking to harness the transformative potential of these technologies. AI and ML technologies have revolutionized the domain of business analytics by providing sophisticated tools for data processing, pattern recognition, and predictive modeling. The application of AI algorithms facilitates the extraction of actionable insights from vast and complex datasets, enabling organizations to make informed decisions with unprecedented accuracy. Machine learning models, with their capacity for adaptive learning and iterative refinement, offer dynamic analytical capabilities that are crucial for navigating the rapidly evolving business environment.
African Journal of Artificial Intelligence and Sustainable Development, 2021
In the era of big data, the efficient management and analysis of data have become paramount for b... more In the era of big data, the efficient management and analysis of data have become paramount for businesses seeking to gain competitive advantages. Traditional data warehousing and ETL (Extract, Transform, Load) processes are increasingly challenged by the volume, velocity, and variety of data. To address these challenges, the integration of cloud-native Robotic Process Automation (RPA) and Artificial Intelligence (AI) presents a promising approach to architecting intelligent data pipelines. This research explores the design and implementation of such intelligent pipelines, emphasizing how they leverage cloud-native RPA and AI technologies to automate data warehousing processes and advance analytics capabilities. The study begins by analyzing the core components and architectural considerations for building intelligent data pipelines. Central to this architecture is the application of cloudnative RPA, which automates repetitive and time-consuming tasks within the ETL framework. RPA's ability to interact with disparate data sources and perform routine data handling tasks without manual intervention streamlines the ETL process, reduces operational costs, and minimizes human error. Additionally, RPA's scalability in cloud environments enables organizations to handle large-scale data operations efficiently. Complementing RPA, AI technologies play a critical role in enhancing data quality and enabling advanced analytics. AI-driven tools, such as machine learning algorithms and natural language processing models, are employed to transform raw data into actionable insights. These AI technologies support advanced data cleaning, anomaly detection, and pattern recognition, thereby improving the accuracy and reliability of the data warehouse. Real-time analytics capabilities are also significantly enhanced through AI, facilitating prompt and informed decision-making in dynamic business environments.
International Journal of Computer Science and Engineering Research and Development (IJCSERD), 2024
The optimization of pharmaceutical products is the focus of recent advances in digital medicine m... more The optimization of pharmaceutical products is the focus of recent advances in digital medicine methods. The pharmaceutical sector could benefit greatly from artificial intelligence (AI) in several ways, including accelerated product development, improved product quality, and more efficient therapy. This article provides a comprehensive analysis of the current state of artificial intelligence (AI) in the pharmaceutical product lifecycle. A search was conducted in PubMed and IEEE Xplore for all articles published between January and March of 2022. After screening for relevant outcomes, publication genres, and data sufficiency, 73 papers (1.2%) were kept out of 6131. To conduct the systematic review and meta-analysis, we followed the guidelines laid out by the PRISMA statement. By the very nature of their implementation, all AI systems fall into several overlapping classes. Clinical trials and pre-clinical tests accounted for 34% of the 177 initiatives that utilized AI. New small molecule design systems come in at 33%, putting them in second position. Novel drug target discovery is the third most common area for AI implementation. This feature is available in almost a quarter of the systems. Surprisingly, 102 systems (or 57% of the total) focus only on a single domain. When it comes to functionality and coverage of the lifespan, none of the systems are up to the task. When DR, AMD, and Nevus are detected all at once, our comprehensive AI method achieves a high diagnosis accuracy. Higher sensitivities with little effect on specificity are made possible with the incorporation of pathology-specific algorithms. In addition, it lessens the possibility of overlooking by accident findings.
International Journal of Computer Science and Engineering Research and Development (IJCSERD), 2024
Food is essential for human survival. Some of the most crucial factors to think about are minimis... more Food is essential for human survival. Some of the most crucial factors to think about are minimising food waste, optimising the supply chain, and enhancing food logistics, delivery, and safety. The achievement of these goals is greatly aided by the application of AI and ML. Proliferation of ever-more-powerful and pervasive computer networks has enabled modern logistical and industrial systems. Within these networks, there is a continual influx of fresh data from many sources, generated by sensors, equipment, systems, intelligent devices, and humans. Thanks to computers' ever-improving capabilities, we can now analyse Big Data more quickly, thoroughly, and in-depth than ever before. These developments have rejuvenated and ushered in a new era called Industry 4.0 or the Smart Factory, which has increased the importance of artificial information technology (AI). Machine learning and artificial intelligence are discussed in this article within the context of the food industry and business. Important uses of this technique include supply chain optimisation, crop selection, logistics, food distribution, and processing plant predicting maintenance.
International Journal of Computer Science and Engineering Research and Development (IJCSERD), 2024
The processing of many types of information is required for the various business decisions that a... more The processing of many types of information is required for the various business decisions that are made at different levels. When seen from this perspective, the utilisation of appropriate tools will contribute to the process of making good business decisions. These kinds of decisions are intended to be supported in an efficient manner by the framework of the business intelligence system that has been presented. To find out how effective business intelligence (BI) is for companies, this study set out to identify the determinants. Findings from the study point to the need for a business intelligence (BI) efficacy model to enhance advisory services. Making sure decision-makers get the right information at the right time in the right format is the whole point of this paradigm. This study used a quantitative research approach and purposive sampling to recruit research participants from a telecoms company. Business intelligence (BI) departments are directly related to an organization's capacity for making sound decisions. The parts of the business intelligence effectiveness model propose focusing on certain areas to improve the organization's information flow, provide easier access to information, make better decisions, and increase productivity.
International Journal of Information Technology (IJIT) , 2024
Robot offer a method that is both structured and portable. The data and the ETL process can also ... more Robot offer a method that is both structured and portable. The data and the ETL process can also be visualised and analysed with the assistance of data visualisation tools like as Tableau, Power BI, and Qlik Sense. To supply this company with information that is helpful, this study makes use of the nine-step process that was created to implement an Online Analysis Processing (OLAP) database and a data warehouse. Small and medium-sized businesses will find it simpler to analyse data because of the data being performed into dashboards. Additionally, a great deal of helpful information can be shared in a short amount of time and in an effective manner.
INTERNATIONAL JOURNAL OF DATA ANALYTICS (IJDA) , 2024
This article provides an overview of the most important function that data analytics plays in the... more This article provides an overview of the most important function that data analytics plays in the revolutionising of banking and financial services. The purpose of this study is to investigate the ways in which contemporary data platforms enable a comprehensive 360-degree view of customers, optimise loan processes through predictive analytics, boost corporate operations through automation, and provide personalised customer experiences among other benefits. By utilising advanced analytics, financial institutions can streamline their operations, enhance their decisionmaking processes, adhere to regulatory requirements, and create stronger relationships with their customers. Furthermore, this highlights the revolutionary influence that datadriven strategies have in terms of driving operational efficiency and strategic growth within the financial sector.
Journal of Bioinformatics and Artificial Intelligence , 2021
In the evolving landscape of healthcare financing, Health Reimbursement Arrangements (HRAs) and H... more In the evolving landscape of healthcare financing, Health Reimbursement Arrangements (HRAs) and Health Savings Accounts (HSAs) have emerged as pivotal mechanisms intended to enhance cost management for both consumers and employers. Despite their potential, the underutilization of these accounts presents a significant challenge, which, if addressed, could yield substantial improvements in healthcare expenditure and insurance efficiency. This research employs a comprehensive data-driven approach to analyze the multifaceted effects of underutilized HRAs and HSAs on overall healthcare spending and the efficiency of insurance plans.
The healthcare industry is on the precipice of a transformative evolution, particularly evident i... more The healthcare industry is on the precipice of a transformative evolution, particularly evident in the realm of claims processing, which has historically been characterized by complexity, inefficiency, and a significant propensity for human error. The integration of automation and artificial intelligence (AI) into claims processing systems represents a paradigm shift that promises to enhance operational efficiency while simultaneously addressing long-standing challenges within the sector. This article delves into the multifaceted role of automation and AI in revolutionizing claims processing, elucidating how these technologies can streamline operations, mitigate human error, and facilitate real-time processing of claims.
The evolving landscape of the U.S. healthcare system necessitates a comprehensive understanding o... more The evolving landscape of the U.S. healthcare system necessitates a comprehensive understanding of the various factors influencing Medicare enrollment trends and consumer costs, particularly in relation to broker commissions. This paper conducts a detailed datadriven analysis of the impact that Medicare broker commissions have on enrollment patterns and associated consumer expenditures. Utilizing extensive datasets derived from Medicare
Uploads
Papers by Jeshwanth Reddy Machireddy