A novel GDP prediction technique based on transfer learning using CO2 emission dataset

•A transfer learning based novel GDP prediction method using CO2 emission data.•It can estimate GDP even when macroeconomic data of a nation is unavailable.•Simulations consider CO2 emission data of four economically heterogeneous nations.•Results are comparatively presented employing three well-known regression methods.•Capable of predicting the missing GDP values of isolated and war-torn countries.