An official website of the United States government
Abstract—Periods of unique economic distress such as the COVID-19 pandemic can be quite difficult for small businesses. Challenges acquiring the supplies necessary to adhere to safety regulations created in the wake of such events can introduce stress on these businesses. This is further exacerbated when supply chains have slowed down, leading to global shortages from most large suppliers. This paper proposes a platform to aid such businesses in procuring COVID-19 related supplies such as Personal Protective Equipment (PPE) from one another, leveraging advanced data acquisition, integration, and Natural Language Processing (NLP) methods. With the pandemic end in sight, the platform described in this paper can be reused for other emergencies such as hurricanes, floods, among others. The proposed platform supports business transactions within a Buyer’s Club (BC), keyword-based sourcing of new businesses to join the platform, and matching products to relevant regulations using greater-than-word length encoding, helping businesses comply with the ever-changing regulatory landscape. Index Terms—COVID-19, Disaster, Natural Language Processing, Data Acquisition, Data Retrieval, User Interfaces
more »
« less
This content will become publicly available on June 5, 2025
Modeling food-related business closure in select New York City communities using multi-scale and spatial features
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.
more »
« less
- PAR ID:
- 10512439
- Publisher / Repository:
- SAGE Publications
- Date Published:
- Journal Name:
- Environment and Planning B: Urban Analytics and City Science
- Volume:
- 52
- Issue:
- 1
- ISSN:
- 2399-8083
- Format(s):
- Medium: X Size: p. 247-264
- Size(s):
- p. 247-264
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Disruptions, such as closures of businesses during pandemics, not only affect businesses and amenities directly but also influence how people move, spreading the impact to other businesses and increasing the overall economic shock. However, it is unclear how much businesses depend on each other during disruptions. Leveraging human mobility data and same-day visits in five US cities, we quantify dependencies between points of interest encompassing businesses, stores and amenities. We find that dependency networks computed from human mobility exhibit significantly higher rates of long-distance connections and biases towards specific pairs of point-of-interest categories. We show that using behaviour-based dependency relationships improves the predictability of business resilience during shocks by around 40% compared with distance-based models, and that neglecting behaviour-based dependencies can lead to underestimation of the spatial cascades of disruptions. Our findings underscore the importance of measuring complex relationships in patterns of human mobility to foster urban economic resilience to shocks.more » « less
-
The mass deployment of energy storage and distributed energy resources has become a major goal across several states in the United States. However, the viability and reality of such a goal in New York City has been put in question as possible financial burdens and execution risks are still unclear, while policies and regulations are still not fully settled. This paper provides a foundational overview of the Lazard LCOS study with emphasis on forward states which have successfully implemented mass deployment of energy storage technologies. “Adders” are related to the practicality in deploying these systems in a highly regulated and densely populated urban area such as New York City. It also discusses details on the typical financial structure/incentives that support the policies and regulations that allow for achieving these clean energy goals. Furthermore, many states have begun to focus on alternative battery technologies rather than just Li-ion, and as such, New York State is following suit. Utilizing several similar works that have begun to touch on these considerations individually and various accredited resources, this paper discusses “adders” for New York City (and New York State as a whole) as they develop similar approaches that are unique to them and offers helpful conclusions and recommendations to achieve their deployment goals.more » « less
-
Abstract Background The Coronavirus Disease 2019 (COVID-19) pandemic warranted a myriad of government-ordered business closures across the USA in efforts to mitigate the spread of the virus. This study aims to discover the implications of government-enforced health policies of reopening public businesses amidst the pandemic and its effect on county-level infection rates. Methods Eighty-three US counties (n = 83) that reported at least 20 000 cases as of 4 November 2020 were selected for this study. The dates when businesses (restaurants, bars, retail, gyms, salons/barbers and public schools) partially and fully reopened, as well as infection rates on the 1st and 14th days following each businesses’ reopening, were recorded. Regression analysis was conducted to deduce potential associations between the 14-day change in infection rate and mask usage frequency, median household income, population density and social distancing. Results On average, infection rates rose significantly as businesses reopened. The average 14-day change in infection rate was higher for fully reopened businesses (infection rate = +0.100) compared to partially reopened businesses (infection rate = +0.0454). The P-value of the two distributions was 0.001692, indicating statistical significance (P < 0.01). Conclusion This research provides insight into the transmission of COVID-19 and promotes evidence-driven policymaking for disease prevention and community health.more » « less
-
Introduction: Fruit and vegetable (FV) consumption can be a protective factor for chronic diseases, but few studies have investigated the association between FV consumption and health risks for chronic disease in the context of the food and nutrition assistance system. The aim of this study was to assess the association between FV consumption and the prevalence of hypertension, type 2 diabetes mellitus, and body mass index (BMI) among food pantry users in small- to mid-sized metropolitan communities in the northeastern United States. Methods: We used data from three health surveys conducted among residents of communities in upstate New York to construct a predictive model of food pantry use. We then applied the model to a regional subset of SMART Behavioral Risk Factor Surveillance System (BRFSS) data collected in the northeastern United States to identify potential food pantry users. We examined the associations between FV intake and diabetes, hypertension, and BMI through univariate and multivariate logistic and linear regressions. Additionally, we investigated food pantry use as a potential modifier of these associations.Results: The analysis dataset included 5,257 respondents, of which 634 individuals (12.06%) were estimated to be food pantry users. Vegetables consumption was associated with decreased odds of hypertension and lower BMI, regardless of food pantry use. Fruits consumption was associated with decreased odds of diabetes regardless of food pantry use. The association between fruit consumption and BMI was modified by the use of food pantry. Among food pantry users, consumption of fruits was associated with a higher BMI, while among food pantry non-users, it was associated with a lower BMI.Conclusion: The overall protective effect of increased FV consumption on chronic disease risks suggest that increasing FV availability in food pantries may not only alleviate hunger but also contribute to better health. Further research is needed to elucidate what is driving the discrepant association between fruit consumption and BMI among food pantry users and non-users.more » « less
