This paper introduces an extensible framework to predict small-business closures to inform urban planners, lenders, and business owners as to factors to improve business resilience. This paper couples machine learning with two point of interest (POI) datasets and infrastructure data and uses New York State’s COVID-19 PAUSE as a stressor for investigating small-business resiliency. The study included 2537 food-related, non-chain, retail businesses across select New York City zip codes, of which 17.7% closed permanently. Macro-, meso-, and micro-levels of features included the neighborhood profile, street dynamics, and venue-specific, location-related characteristics. A Gaussian Mixture Neural Network model achieved 74.1% precision, 92.5% recall, and an 82.3% F1-score without use of financial data. High-end restaurants located further than average from public transit were most at risk for closure, while non-restaurant, food businesses in commercially diverse areas having higher-than-average social media ratings were least at risk. This paper introduces a model for timely prediction of pandemic-induced, food-related, small-business closures without reliance on private or protected financial data, and provides insights into urban design to promote small, food business survivability.
AltmanEI (1984) The success of business failure prediction models: an international survey. Journal of Banking & Finance8(2): 171–198.
2.
AminiSKeaseyK (2013) The failure of small British Initial Public Offerings on the UK Alternative Investment Market: a research note on spatial and industry effects. International Small Business Journal: Researching Entrepreneurship31: 722–733.
3.
AnselinL (1995) Local indicators of spatial association—LISA. Geographical Analysis27(2): 93–115.
4.
BaekSMohantySKGlamboskyM (2020) COVID-19 and stock market volatility: an industry level analysis. Finance Research Letters37: 101748.
5.
BeaverWH (1966) Financial ratios as predictors of failure. Journal of Accounting Research4: 71–111.
6.
BeldaPRCabrer-BorrásB (2018) Necessity and opportunity entrepreneurs: survival factors. The International Entrepreneurship and Management Journal14(2): 249–264.
7.
BelitskiMGuentherCKritikosAS, et al. (2022) Economic effects of the COVID-19 pandemic on entrepreneurship and small businesses. Small Business Economics58(2): 593–609.
8.
BereitschaftBSchellerD (2020) How might the COVID-19 pandemic affect 21st century urban design, planning, and development?Urban Science4(4): 56.
9.
BergCJCallananRJohnsonTO, et al. (2021) Vape shop and consumer activity during COVID-19 non-essential business closures in the USA. Tobacco Control30(e1): e41–e44.
10.
CabedoJDTiradoJM (2004) The disclosure of risk in financial statements. Accounting Forum28(2): 181–200.
ChenM-Y (2011) Bankruptcy prediction in firms with statistical and intelligent techniques and a comparison of evolutionary computation approaches. Computers & Mathematics with Applications62(12): 4514–4524.
13.
CrouzetNMehrotraNR (2020) Small and large firms over the business cycle. The American Economic Review110(11): 3549–3601.
14.
DandekarRBarbastathisG (2020) Quantifying the Effect of Quarantine Control in Covid-19 Infectious Spread Using Machine Learning. Cold Spring Harbor, NY: medRxiv. Available at: https://www.medrxiv.org/content/10.1101/2020.04.03.20052084v1 (accessed 30 November 2023).
15.
DesmetKWacziargR (2022) JUE Insight: understanding spatial variation in COVID-19 across the United States. Journal of Urban Economics127: 103332.
16.
DiNapoliTPJainR (2020) The Restaurant Industry in New York City: Tracking the Recovery. Albany, NY: Office of the New York State Comptroller.
17.
D’SilvaKJayarajahKNoulasA, et al. (2018) The role of urban mobility in retail business survival. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies2(3): 1–22.
18.
GaspardGKimDChunY (2019) Residual spatial autocorrelation in macroecological and biogeographical modeling: a review. Journal of Ecology and Environment43(1): 19.
HeCYangR (2016) Determinants of firm failure: empirical evidence from China. Growth and Change47(1): 72–92.
22.
HealyJJMac Con IomaireM (2019) Calculating restaurant failure rates using longitudinal census data. Journal of Culinary Science & Technology17(4): 350–372.
23.
HumphreyCJensenSTSmallDS, et al. (2020) Urban vibrancy and safety in Philadelphia. Environment and Planning B: Urban Analytics and City Science47(9): 1573–1587.
24.
JiaoJAzimianA (2021) Measuring accessibility to grocery stores using radiation model and survival analysis. Journal of Transport Geography94: 103107.
25.
JordanMIMitchellTM (2015) Machine learning: trends, perspectives, and prospects. Science349(6245): 255–260.
26.
KhmiliarОPopovychIHrysA, et al. (2020) Spatial regulation of personal behavior under conditions of the accelerating COVID-19 pandemic. Revista Inclusiones7: 289–306.
27.
KirchnerT.JiangH.GaoH., et al. (2023) Rapid surveillance of New York City healthcare center egress behaviors during the 2020 COVID-19 lockdown. Scientific Data10(1): 795.
28.
KimSWooA (2022) Streetscape and business survival: examining the impact of walkable environments on the survival of restaurant businesses in commercial areas based on street view images. Journal of Transport Geography105: 103480.
29.
LaeferDFKirchnerTJiangH (2021) Egress Behavior From Select NYC COVID-19 Exposed Health Facilities March-May 2020. New York: New York University. Available at: https://archive.nyu.edu/handle/2451/60075 (accessed 28 July 2022).
30.
LeHHVivianiJ-L (2018) Predicting bank failure: An improvement by implementing a machine-learning approach to classical financial ratios. Research in International Business and Finance44: 16–25.
31.
LeCunYBengioYHintonG (2015) Deep learning. Nature521(7553): 436–444.
32.
LeeS-AKLaeferDF (2021) Spring 2020 COVID-19 community transmission behaviours around New York City medical facilities. Infection Prevention in Practice3(3): 100158.
33.
LiHStolerJ (2023) COVID-19 and urban futures: impacts on business closures in miami-Dade county. Annals of the Association of American Geographers113(4): 834–856.
MoranPAP (1950) Notes on continuous stochastic phenomena. Biometrika37(1/2): 17–23.
37.
MouratidisK (2021) How COVID-19 reshaped quality of life in cities: a synthesis and implications for urban planning. Land Use Policy111: 105772.
38.
MuñuzuriJCortésPOnievaL, et al. (2013) Simulating the effects of pedestrianisation on urban freight deliveries. European Transport\Trasporti Europei54: 1–19.
ParkJKimB (2021) Associations of small business closure and reduced urban mobility with mental health problems in COVID-19 pandemic: a national representative sample study. Journal of Urban Health: Bulletin of the New York Academy of Medicine98(1): 13–26.
41.
RajAMukherjeeAAde Sousa JabbourABL, et al. (2022) Supply chain management during and post-COVID-19 pandemic: mitigation strategies and practical lessons learned. Journal of Business Research142: 1125–1139.
42.
ReynoldsD (2009) Gaussian mixture models. In: LiSZJainA (eds) Encyclopedia of Biometrics. Boston, MA: Springer US, 659–663. Available at: https://link.springer.com/10.1007/978-0-387-73003-5_196 (accessed 29 September 2022).
43.
SafaraF (2022) A computational model to predict consumer behaviour during COVID-19 pandemic. Computational Economics59(4): 1–14.
SedovD (2022) Restaurant closures during the COVID-19 pandemic: a descriptive analysis. Economics Letters213: 110380.
46.
SrivastavaNHintonGKrizhevskyA, et al. (2014) Dropout: a simple way to prevent neural networks from overfitting. Journal of Machine Learning Research15(1): 1929–1958.
47.
TaoJZhouL (2020) Can online consumer reviews signal restaurant closure: a deep learning-based time-series analysis. IEEE Transactions on Engineering Management70: 1–15.
48.
TensorFlow (2015) TensorFlow. Mountain View, CA: TensorFlow. Available at: https://www.tensorflow.org/ (accessed 8 September 2022).
49.
ThazhackalSSDeviVS (2018) A hybrid deep learning model to predict business closure from reviews and user attributes using sentiment aligned topic model. In: 2018 IEEE Symposium Series on Computational Intelligence (SSCI). Piscataway, NJ: IEEE, 397–404.
UzairMJamilN (2020) Effects of hidden layers on the efficiency of neural networks. In: 2020 IEEE 23rd International Multitopic Conference (INMIC). Piscataway, NJ: IEEE, 1–6.
55.
VallapuramAKNandaNKwonYD, et al. (2021) Interpretable business survival prediction. In: Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, Virtual Event Netherlands. New York, NY: ACM, 99–106. Available at: https://dl.acm.org/doi/10.1145/3487351.3488353 (accessed 28 July 2022).
56.
VogelsTPRajanKAbbottLF (2005) Neural network dynamics. Annual Review of Neuroscience28(1): 357–376.
57.
WangLWuC (2017) Business failure prediction based on two-stage selective ensemble with manifold learning algorithm and kernel-based fuzzy self-organizing map. Knowledge-Based Systems121: 99–110.
58.
WangSWangQZhaoJ (2020) Deep neural networks for choice analysis: extracting complete economic information for interpretation. Transportation Research Part C: Emerging Technologies118: 102701.
59.
WangSWangRHuangX, et al. (2023) A GIS-based analytical framework for evaluating the effect of COVID-19 on the restaurant industry with big data. Big Earth Data7(1): 37–58.
60.
YangLShamiA (2020) On hyperparameter optimization of machine learning algorithms: theory and practice. Neurocomputing415: 295–316.
YiSSAliSHRussoRG, et al. (2022) COVID-19 leads to dramatic changes in the food retail environment in New York city: may–july 2020. Journal of Immigrant and Minority Health24(1): 31–37.
63.
ZmijewskiME (1984) Methodological issues related to the estimation of financial distress prediction models. Journal of Accounting Research22: 59–82.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
