Residential housing price index forecasting via neural networks

2023

ECON

Self Cite

PurposeForecasts of commodity prices are vital issues to market participants and policy makers. Those of corn are of no exception, considering its strategic importance. In the present study, the authors assess the forecast problem for the weekly wholesale price index of yellow corn in China during January 1, 2010–January 10, 2020 period.Design/methodology/approachThe authors employ the nonlinear auto-regressive neural network as the forecast tool and evaluate forecast performance of different model settings over algorithms, delays, hidden neurons and data splitting ratios in arriving at the final model.FindingsThe final model is relatively simple and leads to accurate and stable results. Particularly, it generates relative root mean square errors of 1.05%, 1.08% and 1.03% for training, validation and testing, respectively.Originality/valueThrough the analysis, the study shows usefulness of the neural network technique for commodity price forecasts. The results might serve as technical forecasts on a standalone basis or be combined with other fundamental forecasts for perspectives of price trends and corresponding policy analysis.

Section: Methodssupporting

confidence: 62%

Yellow corn wholesale price forecasts via the neural network

2023

ECON

Self Cite

“…In 1995 and 2005, CREIS went through audit processes by experts from the Development Research Center of the State Council, Ministry of Construction, Ministry of Land and Resources, Banking Regulatory Commission, Real Estate Association and different universities (Xu and Zhang, 2022c). Currently, CREIS periodically publishes different housing price indices that include the 100 city index, city composite index, residential index, hedonic index, office property index, retail index, villa price index, second-hand housing sales index and rental price index (Xu and Zhang, 2022l, 2023n), and has turned to be the system with the widest coverage in terms of housing markets in China (Xu and Zhang, 2022h, 2021b). Here, we use the office property index.…”

Section: Datamentioning

confidence: 99%

Office property price index forecasting using neural networks

2023

JFMPC

Self Cite

Purpose The Chinese housing market has witnessed rapid growth during the past decade and the significance of housing price forecasting has undoubtedly elevated, becoming an important issue to investors and policymakers. This study aims to examine neural networks (NNs) for office property price index forecasting from 10 major Chinese cities for July 2005–April 2021. Design/methodology/approach The authors aim at building simple and accurate NNs to contribute to pure technical forecasts of the Chinese office property market. To facilitate the analysis, the authors explore different model settings over algorithms, delays, hidden neurons and data-spitting ratios. Findings The authors reach a simple NN with three delays and three hidden neurons, which leads to stable performance of about 1.45% average relative root mean square error across the 10 cities for the training, validation and testing phases. Originality/value The results could be used on a standalone basis or combined with fundamental forecasts to form perspectives of office property price trends and conduct policy analysis.

“…In 1995 and 2005, CREIS was audited by experts from the Development Research Center of the State Council, Ministry of Construction, Ministry of Land and Resources, Banking Regulatory Commission, Real Estate Association and different universities (Xu and Zhang, 2021e, 2021f). Currently, it periodically publishes different housing price indices that include the one hundred city index, city composite index, residential index, hedonic index, office building index, retail index, villa price index, second-hand housing sales index and rental price index, and it has become the system with the widest coverage in terms of housing markets (Xu and Zhang, 2022d, 2022g). We use the one hundred city index, which became available in CREIS in 2010, and focus on the following 12 major cities: Shanghai, Beijing, Xiamen, Shenzhen, Guangzhou, Hangzhou, Ningbo, Nanjing, Zhuhai, Fuzhou, Suzhou and Dongguan, which are indexed as C1–C12 successively.…”

Section: Data and Wavelet Transformationsmentioning

confidence: 99%

House price information flows among some major Chinese cities: linear and nonlinear causality in time and frequency domains

2022

IJHMA

Self Cite

Purpose With the rapid-growing house market in the past decade, the purpose of this paper is to study the important issue of house price information flows among 12 major cities in China, including Shanghai, Beijing, Xiamen, Shenzhen, Guangzhou, Hangzhou, Ningbo, Nanjing, Zhuhai, Fuzhou, Suzhou and Dongguan, during the period of June 2010 to May 2019. Design/methodology/approach The authors approach this issue in both time and frequency domains, latter of which is facilitated through wavelet analysis and by exploring both linear and nonlinear causality under the vector autoregressive framework. Findings The main findings are threefold. First, in the long run of the time domain and for timescales beyond 16 months of the frequency domain, house prices of all cities significantly affect each other. For timescales up to 16 months, linear causality is weaker and is most often identified for the scale of four to eight months. Second, while nonlinear causality is seldom determined in the time domain and is never found for timescales up to four months, it is identified for scales beyond four months and particularly for those beyond 32 months. Third, nonlinear causality found in the frequency domain is partly explained by the volatility spillover effect. Originality/value Results here should be of use to policymakers in certain policy analysis.