Each country/region has implemented some non-pharmaceutical interventions (NPIs),such as school closure, workplace closure, restriction of gatherings, and stay-at-home requirement,to control COVID-19 epidemic. It is important to analyze the association between the NPIsand COVID-19 incidence and to estimate the impact of each of the NPIs against COVID-19 forthe future policy-making. Although the impact potentially differs depending on country/regionfeatures (e.g. society, economy, life style), existing works for analysis of COVID-19 transmissiongrowth and control according to NPIs and country/region features are done separately, and noanalysis of the impact of each NPIs with respect to country/region features has been done asof yet. In this paper, we extract exhaustively combination of NPIs and country/region featuresassociated with COVID-19 incidence using "Wide Learning" developed by Fujitsu Laboratories,and propose hypotheses for impact of the NPIs against COVID-19 with respect to country/regionfeatures as well as comparing our findings with findings on the existing analysis of the impact ofNPIs against COVID-19.
