Exploratory Data Analysis And Predicttive Insights On Influenza(Flu) Virus Trends Using Machine Learning
Sathish H,
Sai Kishore G,
Shruthi B,
Arya Sree K,
Sai Ganesh Ch
Influenza is a recurring viral infection that poses a significant global health challenge due to its
seasonal outbreaks and rapid spread. This study focuses on applying Exploratory Data Analysis (EDA)
to examine historical influenza data and identify key patterns, correlations, and seasonal variations that
influence the spread of the virus. Understanding these trends is essential for improving early detection
and prevention strategies.
Machine learning techniques are employed to enhance prediction accuracy, with a Random Forest
classifier used for multiclass classification of influenza risk levels. The system is developed using Python
and integrated with a Django-based web application, enabling real-time predictions. Scikit-learn is used
for model training, joblib for model persistence, and PostgreSQL for database management. The results
demonstrate the effectiveness of machine learning in forecasting influenza outbreaks and highlight its
role in supporting data-driven public health decision-making.
