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.

[1]  Ralph J. Alig,et al.  Econometric analysis of the factors influencing forest acreage trends in the southeast. , 1986 .

[2]  N. Bockstael,et al.  Spatial landscape indices in a hedonic framework: an ecological economics analysis using GIS , 1997 .

[3]  D. Glennon,et al.  Measuring the Default Risk of Small Business Loans: A Survival Analysis Approach , 2005 .

[4]  Jonathan Logan,et al.  Greening the Rust Belt: A Green Infrastructure Model for Right Sizing America's Shrinking Cities , 2008 .

[5]  Sung， Hyungun,et al.  The Effects of Homogeneous and Heterogeneous Spatial Clustering Characteristics on Retail Sales in Seoul , 2016 .

[6]  K. Chapple,et al.  Forewarned: The Use of Neighborhood Early Warning Systems for Gentrification and Displacement , 2016 .

[7]  Olgun Aydin,et al.  Using LSTM networks to predict engine condition on large scale data processing framework , 2017, 2017 4th International Conference on Electrical and Electronic Engineering (ICEEE).

[8]  Ali H. Mirza,et al.  Computer network intrusion detection using sequential LSTM Neural Networks autoencoders , 2018, 2018 26th Signal Processing and Communications Applications Conference (SIU).

[9]  V. Limsombunchai.  House Price Prediction: Hedonic Price Model vs. Artificial Neural Network , 2004 .

[10]  R. Shiller.  Arithmetic Repeat Sales Price Estimators , 1991 .

[11]  Aysu Ezen-Can,et al.  A Comparison of LSTM and BERT for Small Corpus , 2020, ArXiv.

[12]  Ayşe Soy Temür,et al.  PREDICTING HOUSING SALES IN TURKEY USING ARIMA, LSTM AND HYBRID MODELS , 2019, Journal of Business Economics and Management.

[13]  S. Ramaswami,et al.  Barriers to the advancement of modern food retail formats: theory and measurement , 2002 .

[14]  D. Reckien,et al.  Why Do Cities Shrink? , 2011 .

[15]  Sepp Hochreiter,et al.  The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions , 1998, Int. J. Uncertain. Fuzziness Knowl. Based Syst..

[16]  David G. Kleinbaum,et al.  Survival Analysis: A Self-Learning Text , 1997 .

[17]  Arvydas Jadevicius,et al.  ARIMA modelling of Lithuanian house price index , 2015 .

[18]  P. Hendershott,et al.  The Workings of the London Office Market , 1999 .

[19]  Galen Newman,et al.  Forecasting Urban Vacancy Dynamics in a Shrinking City: A Land Transformation Model , 2017, ISPRS Int. J. Geo Inf..

[20]  Lixin Zhu,et al.  Comparison of six statistical approaches in the selection of appropriate fish growth models , 2009 .

[21]  Martin Niemann,et al.  Improving performance of corporate rating prediction models by reducing financial ratio heterogeneity. , 2008 .

[22]  Douglas W. Oard,et al.  Textual Data Mining to Support Science and Technology Management , 2000, Journal of Intelligent Information Systems.

[23]  R. Atkinson.  The evidence on the impact of gentrification: new lessons for the urban renaissance? , 2004 .

[24]  U. Rajendra Acharya,et al.  A new approach for arrhythmia classification using deep coded features and LSTM networks , 2019, Comput. Methods Programs Biomed..

[25]  Yi Wang,et al.  A deep learning approach for anomaly detection based on SAE and LSTM in mechanical equipment , 2019, The International Journal of Advanced Manufacturing Technology.

[26]  J. Campbell,et al.  In Search of Distress Risk , 2006, SSRN Electronic Journal.

[27]  Francesco Piazza,et al.  Preprocessing based solution for the vanishing gradient problem in recurrent neural networks , 2003, Proceedings of the 2003 International Symposium on Circuits and Systems, 2003. ISCAS '03..

[28]  Sung-Hwan Min,et al.  Bankruptcy prediction using an improved bagging ensemble , 2014 .

[29]  John F. McDonald,et al.  Reaction of House Prices to a New Rapid Transit Line: Chicago's Midway Line, 1983–1999 , 2004 .

[30]  국내 자영업의 폐업률 결정요인 분석 (Analysis on the Determinants of Exit of Self-Employed Businesses in Korea) , 2017 .

[31]  Galen Newman,et al.  Using the land transformation model to forecast vacant land , 2016 .

[32]  Akbar Siami Namin,et al.  A Comparison of ARIMA and LSTM in Forecasting Time Series , 2018, 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA).

[33]  W. Wheaton,et al.  The Cyclic Behavior of the Greater London Office Market , 1997 .

[34]  Gordon W. Crawford,et al.  Assessing the Forecasting Performance of Regime-Switching, ARIMA and GARCH Models of House Prices , 2003 .

[35]  Marvin L. Wolverton,et al.  Neighborhood Center Image and Rents , 2002 .

[36]  Kieran Farrelly,et al.  Natural vacancy rates in global office markets , 2006 .

[37]  Nghiep Nguyen,et al.  Predicting Housing Value: A Comparison of Multiple Regression Analysis and Artificial Neural Networks , 2001 .

[38]  W. Wheaton,et al.  Vacancy Rates and the Future of Office Rents , 1988 .

[39]  Mohamed Abdel-Nasser,et al.  Accurate photovoltaic power forecasting models using deep LSTM-RNN , 2017, Neural Computing and Applications.

[40]  강정석,et al.  Corporate Default Prediction Model Using Deep Learning Time Series Algorithm, RNN and LSTM , 2018 .