Knowledge Agora



Scientific Article details

Title Farmer typology and implications for policy design - An unsupervised machine learning approach
ID_Doc 63398
Authors Graskemper, V; Yu, XH; Feil, JH
Title Farmer typology and implications for policy design - An unsupervised machine learning approach
Year 2021
Published
DOI 10.1016/j.landusepol.2021.105328
Abstract Within the European Union, there is currently a vivid debate about the European Green Deal with its Farm to Fork Strategy and the related future design of the Common Agricultural Policy post 2020. This paper contributes to this debate by providing a clustering of German farmers analysing objective data (N = 812) using Partitioning Around Medoids (PAM) as a crucial pre-requisite for an effective design and communication of future agricultural policies. Accordingly, German farmers can be clustered into three different groups. The conventional growers are the oldest group of farmers, showing the highest land growth rate, and are characterized by a focus on traditional and politically subsidised activities. The versatile youngsters are rather young in age and the majority of them have completed some form of higher education. Their business profile is diverse. The third group of family-based farmers has the highest shares of family support within their farming business and consists mostly of dairy farmers. Policy and communication design needs to consider all these different profiles. Especially new and innovative programs could be developed and tested together with the versatile youngsters. Furthermore, aspects ensuring an effective and economically rewarding production of agricultural goods should be taken into account to offer a perspective for the conventional growers and for food security. Moreover, the family-based farmers constitute a promising target group for rural development programs.
Author Keywords Machine learning; Partitioning Around Medoids; Agricultural policy; European Green Deal; Farm to Fork Strategy; Farmer typology
Index Keywords Index Keywords
Document Type Other
Open Access Open Access
Source Social Science Citation Index (SSCI)
EID WOS:000674650500009
WoS Category Environmental Studies
Research Area Environmental Sciences & Ecology
PDF
Similar atricles
Scroll