Using machine‐learning methods in meta‐analyses: An empirical application on consumer acceptance of meat alternatives DOI Creative Commons
Jiayu Sun, Vincenzina Caputo, H. Gerry Taylor

et al.

Applied Economic Perspectives and Policy, Journal Year: 2024, Volume and Issue: 46(4), P. 1506 - 1532

Published: May 27, 2024

Abstract Meta‐analyses are widely used in various academic fields, including applied economics. However, the high labor intensity involved paper searching and small sample sizes remain two dominant limiting factors. We conducted a meta‐analysis of studies on consumer preferences for plant‐based lab‐grown meat alternatives using machine‐learning techniques at both data collection analysis phases. demonstrated that machine learning reduces workload manual title‐abstract screen phase by 69% accounting 24% total collection. also found improves out‐of‐sample prediction accuracy 48–78 percentage points when compared to econometric model. Notably, we showed integrating can improve predictive performance methods, thereby improving their predictions. Our empirical findings further revealed demand is higher among younger consumers, especially products displayed benefit information.

Language: Английский

Using machine‐learning methods in meta‐analyses: An empirical application on consumer acceptance of meat alternatives DOI Creative Commons
Jiayu Sun, Vincenzina Caputo, H. Gerry Taylor

et al.

Applied Economic Perspectives and Policy, Journal Year: 2024, Volume and Issue: 46(4), P. 1506 - 1532

Published: May 27, 2024

Abstract Meta‐analyses are widely used in various academic fields, including applied economics. However, the high labor intensity involved paper searching and small sample sizes remain two dominant limiting factors. We conducted a meta‐analysis of studies on consumer preferences for plant‐based lab‐grown meat alternatives using machine‐learning techniques at both data collection analysis phases. demonstrated that machine learning reduces workload manual title‐abstract screen phase by 69% accounting 24% total collection. also found improves out‐of‐sample prediction accuracy 48–78 percentage points when compared to econometric model. Notably, we showed integrating can improve predictive performance methods, thereby improving their predictions. Our empirical findings further revealed demand is higher among younger consumers, especially products displayed benefit information.

Language: Английский

Citations

3