Can machine learning improve small area population forecasts? A forecast combination approach. (July 2022)

• Record Type: Journal Article
• Authors: Grossman, Irina; Bandara, Kasun; Wilson, Tom; Kirley, Michael
• Is Part Of: Computers, environment and urban systems. Volume 95(2022)
• Publication Date: 2022-07
• Subjects: Population forecasts -- Nowcasting -- Small area population forecasting -- Forecast combinations -- Light gradient boosting model; City planning -- Data processing -- Periodicals; Regional planning -- Data processing -- Periodicals; 303.4834
• DOI: 10.1016/j.compenvurbsys.2022.101806
• Languages: English
• ISSNs: 0198-9715

Abstract

Abstract: Generating accurate small area population forecasts is vital for governments and businesses as it provides better grounds for decision making and strategic planning of future demand for services and infrastructure. Small area population forecasting faces numerous challenges, including complex underlying demographic processes, data sparsity, and short time series due to changing geographic boundaries. In this paper, we propose a novel framework for small area forecasting which combines proven demographic forecasting methods, an exponential smoothing based algorithm, and a machine learning based forecasting technique. The proposed forecasting combination contains four base models commonly used in demographic forecasting, a univariate forecasting model specifically suitable for forecasting yearly data, and a globally trained Light Gradient Boosting Model (LGBM) that exploits the similarities between a collection of population time series. In this study, three forecast combination techniques are investigated to weight the forecasts generated by these base models. We empirically evaluate our method, by preparing small area population forecasts for Australia and New Zealand. The proposed framework is able to achieve competitive results in terms of forecasting accuracy. Moreover, we show that the inclusion of the LGBM model always improves the accuracy of combination models on both datasets, relative to combination models which only include the demographic models. In particular, the results indicate that the proposed combination framework decreases the prevalence of relatively poor forecasts, while improving the reliability of small area population forecasts. Highlights: A novel combination framework for small area forecasting is presented. LGBM produce the most accurate forecasts for New Zealand SA2s. Simple average-based methods create the most accurate forecasts for Australian SA2s. Combination methods produce fewer relatively bad forecasts than individual models. The addition of LGBM to the ensemble models consistently improves forecast accuracy.