Estate price prediction system based on temporal and spatial features and lightweight deep learning model

• Published in: Applied intelligence (Dordrecht, Netherlands) Vol. 52; no. 1; pp. 808 - 834
• Main Authors: Chiu, Sheng-Min, Chen, Yi-Chung, Lee, Chiang
• Format: Journal Article
• Language: English
• Published: New York Springer US 2022; Springer Nature B.V
• Subjects: Accuracy; Artificial Intelligence; Computer Science; Data structures; Deep learning; Feature extraction; Machines; Manufacturing; Mechanical Engineering; Processes; Run time (computers); Deep learning models; Lightweight model; Spatial temporal database; Estate price prediction
• ISSN: 0924-669X; 1573-7497
• DOI: 10.1007/s10489-021-02472-6

The development of estate price prediction systems is one of the issues that researchers are paying the most attention to. A good estate price prediction system can shorten the time it takes buyers to consider estates and invigorate the estate market. Generally speaking, an estate price prediction system considers the temporal and spatial features of the estate. In addition, the estate price prediction system can also be launched online for users to make instant online queries with, which means that it needs short run time. However, most existing studies only considered either temporal or spatial features and could not consider both, thereby resulting in questionable prediction accuracy. Although deep learning may increase prediction accuracy, it does not meet the short run time requirement. We therefore presented three ideas in this study to overcome these issues: (1) designing a novel spatiotemporal data structure, the Space-Time Influencing Figure (STIF), to quantify the influence of changes in the facilities surrounding each estate on estate price, (2) designing a novel CNN-LSTM model to go with the STIFs for estate price prediction, and (3) designing a new framework to extract the most important features to estate price for certain types of estates and combining these features with a shallow RNN for modeling. The computation cost of this model is far lower than that of a CNN-LSTM model, making it suitable for practical application. Finally, we used actual estate data from Taiwan to verify that the proposed approach can effectively and swiftly predict estate prices.