Economic forecasting with an agent-based model

We develop the first agent-based model (ABM) that can compete with benchmark VAR and DSGE models in out-of-sample forecasting of macro variables. Our ABM for a small open economy uses micro and macro data from national accounts, sector accounts, input–output tables, government statistics, and census and business demography data. The model incorporates all economic activities as classified by the European System of Accounts (ESA 2010) and includes all economic sectors populated with millions of heterogeneous agents. In addition to being a competitive model framework for forecasts of aggregate variables, the detailed structure of the ABM allows for a breakdown into sector-level forecasts. Using this detailed structure, we demonstrate the ABM by forecasting the medium-run macroeconomic effects of lockdown measures taken in Austria to combat the COVID-19 pandemic. Potential applications of the model include stress-testing and predicting the effects of monetary or fiscal macroeconomic policies. © 2022 The Author(s)

Economic forecasting with an agent-based model

We develop the first agent-based model (ABM) that can compete with benchmark VAR and DSGE models in out-of-sample forecasting of macro variables. Our ABM for a small open economy uses micro and macro data from national accounts, sector accounts, input–output tables, government statistics, and census and business demography data. The model incorporates all economic activities as classified by the European System of Accounts (ESA 2010) and includes all economic sectors populated with millions of heterogeneous agents. In addition to being a competitive model framework for forecasts of aggregate variables, the detailed structure of the ABM allows for a breakdown into sector-level forecasts. Using this detailed structure, we demonstrate the ABM by forecasting the medium-run macroeconomic effects of lockdown measures taken in Austria to combat the COVID-19 pandemic. Potential applications of the model include stress-testing and predicting the effects of monetary or fiscal macroeconomic policies.

Data mining and socio-spatial patterns of COVID-19: geo-prevention keys for tackling the pandemic

A geographic perspective is essential in tackling COVID-19. This research study is framed in the collaboration project set up by the University of Cantabria, the Valdecilla Hospital Research Institute (IDIVAL) and the Regional Government of Cantabria. The case study is the Santander functional urban area (FUA), which is considered from a multi-scale perspective. The main source is the daily records of micro-data on COVID-19 cases and the methodology is based on ESRI geotechnologies, and more specifically on a tool called SITAR (a Spanish acronym which stands for Fast-Action Territorial Information System). The main goal is to analyse and contribute to knowledge of the spatial patterns of COVID-19 at neighbourhood level from a space-time perspective. To that end the research is based on data mining methods (3D bins and emerging hot-spots) and exploratory geo-statistical analysis (Global Moran's Index, Nearest Neighbourhood and Ordinary Least Square analyses, among others). The study identifies space-time patterns that show significant hot-spots and demonstrates a high presence of the virus at building level in neighbourhoods where residential and economic uses are mixed. Knowing the spatial behaviour of the virus is strategically important for proposing geo-prevention keys, reducing spread and balancing trade-offs between potential health gains and economic burdens resulting from interventions to deal with the pandemic.

The Neighborhood Contagion Focus as a Spatial Unit for Diagnosis and Epidemiological Action against COVID-19 Contagion in Urban Spaces: A Methodological Proposal for Its Detection and Delimitation.

The concept of neighborhood contagion focus is defined and justified as a basic spatial unit for epidemiological diagnosis and action, and a specific methodological procedure is provided to detect and map focuses and micro-focuses of contagion without using regular or artificial spatial units. The starting hypothesis is that the contagion in urban spaces manifests unevenly in the form of clusters of cases that are generated and developed by neighborhood contagion. Methodologically, the spatial distribution of those infected in the study area, the city of Málaga (Spain), is firstly analyzed from the disaggregated and anonymous address information. After defining the concept of neighborhood contagion focus and justifying its morphological parameters, a method to detect and map neighborhood contagion focus in urban settings is proposed and applied to the study case. As the main results, the existence of focuses and micro-focuses in the spatial pattern of contagion is verified. Focuses are considered as an ideal spatial analysis unit, and the advantages and potentialities of the use of mapping focus as a useful tool for health and territorial management in different phases of the epidemic are shown.