Using deep learning neural networks to predict the knowledge economy index for developing and emerging economies

作者：

Highlights：

• Inconsistency of the knowledge economy (KE) measures remains a vexing problem.

• World Bank’s KE index (KEI) is a useful tool for measuring the knowledge economy.

• KEI is often missing for developing countries due to lack data on which it is based.

• A deep learning neural network was trained to predict KEI, even with missing data.

• The relative prediction error for the countries for which KEI is available is 2.99%

摘要

•Inconsistency of the knowledge economy (KE) measures remains a vexing problem.•World Bank’s KE index (KEI) is a useful tool for measuring the knowledge economy.•KEI is often missing for developing countries due to lack data on which it is based.•A deep learning neural network was trained to predict KEI, even with missing data.•The relative prediction error for the countries for which KEI is available is 2.99%

论文关键词：Machine deep learning neural networks,Developing economies,Emerging economies,Knowledge economy,Knowledge economy index,World Bank

论文评审过程：Received 23 May 2020, Revised 2 June 2021, Accepted 28 June 2021, Available online 3 July 2021, Version of Record 15 July 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115514