Multi-Time Series Forecasting for Regional Emergency Call Demand

Accurate emergency call demand forecasting is essential for optimizing resource allocation and response times in Emergency Medical Services (EMS). Time series forecasting, a cornerstone of machine learning, plays a crucial role in predicting demand patterns. This research proposes a novel multi-series forecasting model for scenarios involving multiple independent time series, representing call data from distinct service areas. While previous research has explored multivariate time series and machine learning methods for EMS demand forecasting, this study focuses on comparing a simplified independent time series approach against the proposed multi-series model. By evaluating the accuracy of both methods in predicting future call volumes, the findings will provide insights into the most effective forecasting approach, ultimately contributing to improved resource allocation and enhanced patient care in EMS.