Artificial neural network (ANN) models are rarely used to forecast population in spite of their growing prominence in other fields. We compare the forecasts generated by ANN long short-term memory models (LSTM) with population projections from traditional cohort-component method (CCM) for counties in Alabama. The evaluation includes forecasts for all 67 counties that offer diversity in terms of population and socioeconomic characteristics. When comparing projected values with total population counts from the 2010 decennial census, the CCM used by the Center for Business and Economic Research at the University of Alabama in 2001 produced more accurate results than a basic multi-county ANN LSTM model. Only when we use single-county models or proxy for a forecaster’s experience and personal judgment with potential economic forecasts, results from ANN models improve. The results indicate the significance of forecaster’s experience and judgment for CCM and difficulty, but not impossibility of substituting these insights with available data.

中文翻译：

---

比较用于人口预测的人工神经网络和群组组件模型

尽管人工神经网络 (ANN) 模型在其他领域越来越突出，但它们很少用于预测人口。我们将 ANN 长短期记忆模型 (LSTM) 生成的预测与来自阿拉巴马州县的传统群组分量方法 (CCM) 的人口预测进行比较。评估包括对在人口和社会经济特征方面提供多样性的所有 67 个县的预测。将预测值与 2010 年人口普查的总人口数进行比较时，阿拉巴马大学商业和经济研究中心在 2001 年使用的 CCM 比基本的多县 ANN LSTM 模型产生了更准确的结果。只有当我们使用单县模型或代理预测者的经验和个人判断对潜在经济预测时，ANN 模型的结果有所改善。结果表明预报员的经验和判断对 CCM 和难度的重要性，但并非不可能用可用数据代替这些见解。