Aim of study: A real-time monitoring and prediction system for Huelva strawberry (Spain) price is proposed, based on data from the Andalusian Observatory of Agrifood Prices (AOAP) of the Regional Ministry of Agriculture, Fisheries, Water, and Rural Development of the Government of Andalusia, Spain. This system can support farmer decisions to increase their revenues and accelerate digitalization adoption aiming at improving equity and sustainability of the agrifood value chain. Area of study: Huelva province (Spain) is leading Europe’s strawberry sales from January to April and the sector is highly relevant in economic and development terms for this territory. Material and methods: Analysis of AOAP data and value chain of the strawberry sector, development of a statistical predictive model and monitoring real-time surveillance system to create the seed of a dashboard to support farmer market decisions, in the context of artificial intelligence predictive models and data space requirements. Main results: AOAP includes important sectoral data under a reasonable governance model that can be a starting point to develop useful decisions support tools. The developed predictive price model based on traditional tools allows for maximizing farmer revenue and thus becomes a framework to build transdisciplinary knowledge joining the agricultural domain expertise and the artificial intelligence tools in parallel with the needed big data and data spaces development. Research highlights: 1) The proposed predictive and monitoring system can improve the farmer’s position in the value chain and thus it can also be useful to foster the adoption of digital tools by farmers. 2) Predictive systems require a huge amount of data that is not currently available. AOAP have some interesting characteristics as starting point for a data space that can contribute to fill this gap.
Lucena-Cobos et al. (Wed,) studied this question.