发表机构
Public Health Ontario; Dalla Lana School of Public Health, University of Toronto; University of Toronto; York University（安大略省公共卫生局; 多伦多大学达拉·拉纳公共卫生学院; 多伦多大学; 约克大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究评估ARIMA、随机森林、XGBoost模型，提出MLAMA集成方法，基于安大略省COVID-19数据验证其预测性能更优，支持按操作条件选择预测模型。
AI 中文摘要
公共卫生预测必须能应对监测数据的突发变化，同时避免过度外推噪声、报告伪影或临时趋势。我们评估了自回归积分移动平均（ARIMA）、随机森林和极端梯度提升（XGBoost）模型，使用2020年1月至2023年10月期间安大略省公开的COVID-19病例计数的190周观测数据。滚动原点时间序列交叉验证在模型调优和评估过程中保留了时间顺序。性能在三个操作维度上进行评估：选定转折点后的响应性、1至6周的预测 horizon 以及历史训练数据量。我们还开发了机器学习与ARIMA模型平均法（MLAMA），这是一种非负性能加权集成方法，其权重随预测 horizon 和响应性设置而变化。回顾性比较显示，ARIMA在转折点后适应迅速，但其归一化误差在较长预测 horizon 时增大；随机森林和XGBoost初始响应性较低，但在较长预测 horizon 时归一化误差更稳定。对于研究期末的两周预测，使用最新数据训练比使用更长历史数据表现更好，尤其是XGBoost。MLAMA在大多数预测 horizon 中实现了最低的归一化平均绝对百分比误差，并且在响应性设置下排名最佳方法之列。这些发现支持根据操作条件选择预测模型，而非依赖单一通用优选方法。MLAMA为结合互补的统计和机器学习预测提供了实用框架。配套的Python包目前维护在私有仓库中，正在完成软件验证和可复现性测试。
英文摘要
Public health forecasts must respond to abrupt changes in surveillance data without over-extrapolating noise, reporting artifacts, or temporary trends. We evaluated autoregressive integrated moving average (ARIMA), random forest, and extreme gradient boosting (XGBoost) models using 190 weekly observations of publicly available Ontario COVID-19 case counts from January 2020 to October 2023. Rolling-origin time-series cross-validation preserved temporal order during model tuning and evaluation. Performance was assessed across three operating dimensions: responsiveness following selected turning points, forecast horizons of one to six weeks, and the amount of historical training data. We also developed Machine Learning and ARIMA Model Averaging (MLAMA), a non-negative performance-weighted ensemble with weights that vary by forecast horizon and responsiveness setting. Retrospective comparisons showed that ARIMA adapted rapidly after turning points but its normalized error increased at longer horizons. Random forest and XGBoost were less responsive initially but maintained more stable normalized error over longer horizons. For two-week forecasts at the end of the study period, training on the most recent data outperformed using longer historical periods, particularly for XGBoost. MLAMA achieved the lowest normalized mean absolute percentage error across most forecast horizons and ranked among the best-performing methods across responsiveness settings. These findings support selecting forecasting models according to operating conditions rather than relying on a single universally preferred approach. MLAMA provides a practical framework for combining complementary statistical and machine-learning forecasts. The accompanying Python package is currently maintained in a private repository while software validation and reproducibility testing are completed.
CommentsThis paper has been withdrawn by the author due to organizational policy
