“…Some fundamental time series econometric models, such as the autoregressive (AR), vector autoregressive (VAR), vector error correction (VEC) and a wide spectrum of their variations and extensions, have been applied for various forecasting purposes and uses (Kim et al ., 2007; Xu and Zhang, 2021c, 2022c, 2023e; Xu, 2015, 2017a, b, c, 2018b, c, e, 2019a, b, c, 2020; Zohrabyan et al ., 2008; Cabrera et al ., 2011; Kouwenberg and Zwinkels, 2014; Webb et al ., 2016; Yang et al ., 2018; Milunovich, 2020). Recently, a wide variety of machine learning methods and algorithms, such as the random forest, regression tree, support vector regression, nearest neighbor, neural network, bagging, boosting, ensemble learning and deep learning, have been found to be useful and promising tools to various forecasting problems (Xu and Zhang, 2023) regarding house price time series data (Wang et al ., 2014; Xu and Zhang, 2023i; Park and Bae, 2015; Plakandaras et al ., 2015; Chen et al ., 2017; Liu and Liu, 2019; Huang, 2019; Li et al ., 2020; Yan and Zong, 2020; Milunovich, 2020; Pai and Wang, 2020; Ho et al ., 2021; Rico-Juan and de La Paz, 2021; Xu and Li, 2021; Embaye et al ., 2021). Particularly, neural networks have been seen in the literature to have great potential to forecast (economic/financial) time series that tend to be highly noised and chaotic (Xu and Zhang, 2021d, 2022l, n, 2023c, d, h, l; Wang and Yang, 2010; Yang et al ., 2008, 2010; Wegener et al ., 2016), including different types of house price time series (Xu and Zhang, 2021b, 2022g, i, j, k, 2023q; Wilson et al ., 2002; Taffese, 2007; Selim, 2009; Wang et al ., 2016; Abidoye and Chan, 2017; Li et al ., 2017;…”