Integrating Clustering and Multivariate Models for Enhanced Infectious Disease Forecasting in India

Abstract

Infectious disease forecasting is of paramount importance in managing public health in India, given its vast population and diverse environmental conditions. This paper introduces a clustering-based multivariate prediction model that forecasts new infectious disease cases by capturing the interaction between various factors such as environmental variables, demographic characteristics, and historical trends. The model aggregates extensive datasets and employs clustering algorithms to segment data, enabling localized and accurate disease forecasting. Advanced multivariate prediction techniques, including machine learning algorithms and regression analysis, enhance the model’s forecasting accuracy. This approach offers proactive public health strategies, aiding in identifying high-risk areas and optimizing resource allocation. The proposed framework demonstrates improved predictive accuracy and management of infectious disease threats in India, paving the way for future integration with real-time data for greater effectiveness.

DOI - https://doi.org/10.65525/SVUP.9788199778009.2026.60-65