United States Federal Emergency Management Agency regional clustering by disaster exposure: a new paradigm for disaster response.

The Federal Emergency Management Agency (FEMA) divides the United States (US) into ten standard regions to promote local partnerships and priorities. These divisions, while longstanding, do not adequately address known hazard risk as reflected in past federal disaster declarations. From FEMA's inception in 1979 until 2020, the OpenFEMA dataset reports 4127 natural disaster incidents declared by 53 distinct state-level jurisdictions, listed by disaster location, type, and year. An unsupervised spectral clustering (SC) algorithm was applied to group these jurisdictions into regions based on affinity scores assigned to each pair of jurisdictions accounting for both geographic proximity and historical disaster exposures. Reassigning jurisdictions to ten regions using the proposed SC algorithm resulted in an adjusted Rand index (ARI) of 0.43 when compared with the existing FEMA regional structure, indicating little similarity between the current FEMA regions and the clustering results. Reassigning instead into six regions substantially improved cluster quality with a maximized silhouette score of 0.42, compared to a score of 0.34 for ten regions. In clustering US jurisdictions not only by geographic proximity but also by the myriad hazards faced in relation to one another, this study demonstrates a novel method for FEMA regional allocation and design that may ultimately improve FEMA disaster specialization and response.

Towards an AI-Driven Marketplace for Small Businesses During COVID-19.

With the introduction of new COVID-19 variants such as Delta and Omicron, small businesses have been tasked with navigating a constantly changing business environment. Furthermore, due to supply chain issues, shortages of various critical products negatively affect businesses of all sizes and industries. However, continued innovation in Computer Science, specifically in sub-fields of Artificial Intelligence (AI), such as natural language processing (NLP), has created significant value for businesses through helpful data-driven features. To this end, we propose a platform utilizing AI-driven tools to help build an effective business-to-business (B2B) platform. The proposed platform aims to automate much of the market research which goes into selecting products and platform users during times of distress while still providing an intuitive e-commerce interface. There are three primary novel components to this platform. The first of these components is the Buyer's Club (BC), which allows customers to pool resources to purchase bulk orders at a reduced cost. The second component is an automated system utilizing Natural Language Processing (NLP) to detect trending disaster news topics. Disaster topic detection can be applied to inform buyers and suppliers on adapting to changing market conditions and has been shown to match closely with Google Trends data. The third component is a regulation matching system, using a custom data set to help inform customers when purchasing products. Such guidance is necessary to comply with a regulatory environment that will be irregular for the foreseeable future.