Data-driven decision making for modelling covid-19 and its implications: A cross-country study.

Grounded in big data analytics capabilities, this study aims to model the COVID-19 spread globally by considering various factors such as demographic, cultural, health system, economic, technological, and policy-based. Classified values on each country's case, death, and recovery numbers (per 1000,000 population) were used to represent COVID-19 spread. Data sets also included 29 input variables for the corresponding six factors, containing data from 159 countries. The proposed model used a Multilayer Perceptron algorithm. The results show that each of the pre-mentioned factors significantly affects disease spread. Urban population, median age, life expectancy, numbers of medical doctors and nursing personnel, current health expenditure as a % of GDP, international health regulations capacity score, continent, literacy rate, governmental response stringency index, testing policy, internet usage %, human development index and GDP per capita were identified as significant. Taking early measures and adopting open public testing policies were recommended to policymakers in fighting pandemic diseases since the created scenarios on policy-based factors revealed their importance. • We propose an approach that utilizes BDA and combines multiple factors for modeling the spread of diseases globally. • This study presents a dataset of 159 countries and 29 variables to model global disease spread. • Demographic, health system, cultural, policy, technological, and economic factors are defined as input variables. • The model is tested for three output indexes: number of cases, deaths, and recoveries. • The study investigates how different COVID-19 policies impact the outcomes, using simulated policy-based variables. [ABSTRACT FROM AUTHOR]