TY - JOUR
T1 - Exploring critical drivers of global innovation
T2 - A Bayesian Network perspective
AU - Qazi, Abroon
AU - Al-Mhdawi, M. K.S.
N1 - Publisher Copyright:
© 2024 Elsevier B.V.
PY - 2024/9/5
Y1 - 2024/9/5
N2 - This study adopts a Bayesian Belief Network (BBN) methodology to explore relationships among innovation indicators within the Global Innovation Index (GII) framework using 2023 data. The analysis identifies 'research and development’, 'online creativity’, and 'knowledge creation' as pivotal factors influencing innovation outcomes. The BBN model demonstrates a predictive accuracy of 90.9%. For high-performing countries, 'information and communication technologies’, 'regulatory environment’, and 'education' are critical, whereas 'investment' shows a low performance in driving innovation excellence. In low-performing countries, 'innovation linkages' and 'research and development' are strongly associated with the low innovation performance of these countries. Sensitivity analysis highlights 'knowledge workers’, 'online creativity’, and 'institutional environment' as significant drivers, illustrating the complex nature of innovation dynamics. This study enhances our understanding of innovation within the GII framework and offers actionable insights for policymakers and stakeholders. Existing methods often rely on simplistic linear models that fail to capture the complex interdependencies among innovation indicators. This study addresses this limitation by leveraging the BBN approach to provide a better understanding of innovation dynamics.
AB - This study adopts a Bayesian Belief Network (BBN) methodology to explore relationships among innovation indicators within the Global Innovation Index (GII) framework using 2023 data. The analysis identifies 'research and development’, 'online creativity’, and 'knowledge creation' as pivotal factors influencing innovation outcomes. The BBN model demonstrates a predictive accuracy of 90.9%. For high-performing countries, 'information and communication technologies’, 'regulatory environment’, and 'education' are critical, whereas 'investment' shows a low performance in driving innovation excellence. In low-performing countries, 'innovation linkages' and 'research and development' are strongly associated with the low innovation performance of these countries. Sensitivity analysis highlights 'knowledge workers’, 'online creativity’, and 'institutional environment' as significant drivers, illustrating the complex nature of innovation dynamics. This study enhances our understanding of innovation within the GII framework and offers actionable insights for policymakers and stakeholders. Existing methods often rely on simplistic linear models that fail to capture the complex interdependencies among innovation indicators. This study addresses this limitation by leveraging the BBN approach to provide a better understanding of innovation dynamics.
UR - http://www.scopus.com/inward/record.url?scp=85196768661&partnerID=8YFLogxK
U2 - 10.1016/j.knosys.2024.112127
DO - 10.1016/j.knosys.2024.112127
M3 - Article
AN - SCOPUS:85196768661
SN - 0950-7051
VL - 299
JO - Knowledge-Based Systems
JF - Knowledge-Based Systems
M1 - 112127
ER -