Prediction Model for the Spread of the COVID-19 Outbreak in The Global Environment (Ron S. Hirschprung and Chen Hajaj)
This project focuses on establishing a prediction model for the spread pattern of the COVID-19 pandemic. Leveraging Data Mining and Machine Learning techniques, we aim to predict the number of confirmed cases in a spatial-temporal space. The methodology introduced in this project utilizes the concept of the Center of Infection Mass (CoIM), adapted from the field of physics, to enhance prediction accuracy.
COVID-19 has had a profound global impact, resulting in the loss of over two million lives and triggering economic recessions. This paper delves into studying the spread pattern of COVID-19 and aims to develop a prediction model. By employing Data Mining and Machine Learning methodologies, we train regression models to forecast the number of confirmed cases in a spatial-temporal context. Our innovation, the Center of Infection Mass (CoIM), borrowed from physics, contributes significantly to our model's empirical evaluation in western European countries. We demonstrate that our methodology enables reasonably accurate predictions over a span of more than a month. Additionally, our empirical findings support the effectiveness of incorporating the CoIM index into prediction models, showcasing notably improved results compared to models that neglect it. We believe that by utilizing our model, policymakers can make more informed decisions, effectively balancing life-saving measures with economic considerations. Thus, this methodology holds promise for contributing to public welfare.
If you find this work helpful or use it in your research, please consider citing: Hirschprung, R. S. & Hajaj, C. (2021). Prediction model for the spread of the COVID-19 outbreak in the global environment. Heliyon, 7 (7), e07416. doi: 10.1016/j.heliyon.2021.e07416