Commercial Vacancy Prediction Using LSTM Neural Networks

Previous studies on commercial vacancy have mostly focused on the survival rate of commercial buildings over a certain time frame and the cause of their closure, due to a lack of appropriate data. Based on a time-series of 2,940,000 individual commercial facility data, the main purpose of this research is two-fold: (1) to examine long short-term memory (LSTM) as a feasible option for predicting trends in commercial districts and (2) to identify the influence of each variable on prediction results for establishing evidence-based decision-making on the primary influences of commercial vacancy. The results indicate that LSTM can be useful in simulating commercial vacancy dynamics. Furthermore, sales, floating population, and franchise rate were found to be the main determinants for commercial vacancy. The results suggest that it is imperative to control the cannibalization of commercial districts and develop their competitiveness to retain a consistent floating population.

Automated summary

This study used a time-series analysis of 2.94 million individual commercial facility data to demonstrate the feasibility of using LSTM for predicting trends in commercial districts and identified sales, floating population, and franchise rate as the main determinants for commercial vacancy. The results suggest the importance of controlling cannibalization of commercial districts and enhancing their competitiveness to maintain a consistent floating population.