COVID-19 Case Growth and Containment Predictions Across 42 Countries

42 countries' COVID-19 infection data up to March 26, 2020, used to model pandemic spread and predict early containment signs. The research by Dharun Kasilingam of Mudra Institute of Communications Ahmedabad applies exponential growth modelling and supervised machine learning. Models based on logistic regression, decision trees, random forests, and support vector machines achieved accuracies between 76.2% and 92.9%.

Use Cases

• Modeling exponential growth of COVID-19 cases based on infection data
• Predicting early signs of virus containment using machine learning models
• Analyzing the relationship between healthcare infrastructure and containment success
• Evaluating the impact of government lockdown policies on pandemic spread

Strengths

• Data covers 42 countries, providing a multi-national perspective
• Machine learning models reported accuracies between 76.2% and 92.9%
• Analysis includes specific date coverage up to March 26, 2020

Limitations

• Row count and specific column definitions are unknown
• Last update date is unknown; freshness unverified
• Data may reflect geographic and temporal bias inherent to the early pandemic period

Provenance

Source

Dharun Kasilingam, Mudra Institute of Communications Ahmedabad

Collection Method

Research analysis using COVID-19 infection data from unspecified sources

Time Range

Up to March 26, 2020

Geography

42 countries