abstract

Epidemic outbreaks have challenged global public health and economic stability for centuries. With the recent emergence of novel infectious diseases and the rapid spread of pandemics, there is a pressing need for advanced forecasting systems that combine predictive accuracy with operational transparency. This study proposes an integrative model that merges explainable artificial intelligence (XAI) with business analytics (BA) to enhance epidemic response through transparent decision-making. The model leverages machine learning techniques-augmented with explainable frameworks-to identify early warning signals, while BA methods provide interpretative insights into resource allocation, cost–benefit analysis, and intervention strategies. Multi-source datasets, including epidemiological records, environmental indicators, mobility data, and social media feeds, were used to develop and validate the proposed model. The results demonstrate that XAI techniques can elucidate the decision pathways of predictive models, thereby reducing the ‘black box’ effect and enabling public health stakeholders to trust and act on model outputs. Moreover, the integration of BA techniques allowed for the simulation of various outbreak scenarios, supporting robust decision-making under uncertainty. This paper discusses methodological challenges, ethical considerations in data use, and the importance of transparent model deployment. Ultimately, the study advocates for interdisciplinary research that bridges advanced computational techniques with practical public health applications, offering a scalable framework for future epidemic forecasting and response.