Geographical Indications (GIs), as Protected Designation of Origin (PDO)and Protected Geographical Indication (PGI), offer a unique protection scheme to preserve high-quality agri-food productions and support sustainable rural development at the territorial level. However, not all the areas with traditional agri-food products are acknowledged with a GI. Examining the Italian wine sector by a geo-referenced database and a machine learning framework, we show that municipalities which obtain a GI within the subsequent 10 year period (2002–2011) can be predicted using a large set of (lagged) municipality-level data (1981–2001). We find that the Random Forest algorithm is the best model to make out-of-sample predictions of municipalities which obtain GIs. Results show that there is a sort of optimal territorial condition characterized by the successful matching of wine-growing profession (vineyards), local actors involved (number of farmers), and physical dimension of farms (middle farms). Being in a vital economic system and the distance from major urban centers also emerges among the main relevant features in predicting the success of GIs. The methodology adopted and the evidence provided lead to policy reflections, in the light of the future Common Agricultural Policy (CAP) programming period and the scheduled reform of the GI’s quality scheme.
Resce, G., Vaquero Pineiro, C. (2022). Predicting agri-food quality across space: A Machine Learning model for the acknowledgment of Geographical Indications. FOOD POLICY, 112, 102345 [10.1016/j.foodpol.2022.102345].
Predicting agri-food quality across space: A Machine Learning model for the acknowledgment of Geographical Indications
Resce, Giuliano;Vaquero Pineiro, Cristina
2022-01-01
Abstract
Geographical Indications (GIs), as Protected Designation of Origin (PDO)and Protected Geographical Indication (PGI), offer a unique protection scheme to preserve high-quality agri-food productions and support sustainable rural development at the territorial level. However, not all the areas with traditional agri-food products are acknowledged with a GI. Examining the Italian wine sector by a geo-referenced database and a machine learning framework, we show that municipalities which obtain a GI within the subsequent 10 year period (2002–2011) can be predicted using a large set of (lagged) municipality-level data (1981–2001). We find that the Random Forest algorithm is the best model to make out-of-sample predictions of municipalities which obtain GIs. Results show that there is a sort of optimal territorial condition characterized by the successful matching of wine-growing profession (vineyards), local actors involved (number of farmers), and physical dimension of farms (middle farms). Being in a vital economic system and the distance from major urban centers also emerges among the main relevant features in predicting the success of GIs. The methodology adopted and the evidence provided lead to policy reflections, in the light of the future Common Agricultural Policy (CAP) programming period and the scheduled reform of the GI’s quality scheme.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
