Data Science-Driven System Design with LSTM Neural Networks: A COVID-19 Perspective

This paper emphasizes the significance of utilizing data science tools for system design research and their contribution to the field. It suggests selecting appropriate tools based on evaluations of functionality, scalability, and performance, aligning with system goals. A system design presented in this paper is based on data science tools, focusing on a three-layer architecture for an information system. A platform is developed to monitor and predict COVID-19 epidemiological data, addressing data quality issues through preprocessing, outlier detection, and imputation. The study employs advanced deep learning for prediction models, supported by robust validation methodologies. The resulting graphical interface facilitates effective visualization, aiding researchers in comprehending COVID-19 trends and making informed decisions. Overall, the research underscores the impact of data analytics, predictive modeling, and data- driven decision-making on complex phenomena and digital transformation.