Food and Agriculture Organization of the United Nations
    FAO Data Lab

    Filling gaps of statistical data

    The Data Lab collects data at the national (eventually filling any potential gaps of the National Statistical Systems) and sub-national (usually not collected by the FAO) levels to meet the need for more granular and more timely data in contexts where very little information is available, such as least developed countries, countries that lack territorial access to the sea, small island developing states, countries currently facing a food crisis, and highly populated countries.

    The strategy for filling the data gaps consists mainly in the use of non-traditional sources, such as datasets, data catalogues on the web, and textual resources containing data. The methodology used is characterised by a blend of big data solutions (such as web scraping, crowdsourcing, etc.) and text-mining techniques (extracting data from documents).   

    The final objective of such activities is having more timely and detailed data that can support decision-making (and thus improving livelihood and food security levels for rural people in developing countries), monitoring progress under various SDGs, and monitoring food value chains. This can be done by collecting and analysing data, disseminating useful information and improving coordination with resource partners.

    So far, this area of work has covered:

    Ag productionAgricultural production data at national and sub-national level: the Data Lab collects agricultural production data by means of artificial intelligence and text-mining in contexts where little data are available. Such data are then summed up in order to create an overview of the national level, and validated against the information contained in FAOSTAT. This process allows the Data Lab to fill data gaps, when needed. 
    FLWFood loss and waste data from non-conventional sources: the Data Lab scrapes from the world wide web all the publications containing data and information on food losses and waste (reports, studies, articles from various sources), and then analyses the results and models data with specific statistical methods. Through a manual revision and a further refinement, the scraped values are fed into to the FAO FLW Database
    Food pricesFood prices: The Data Lab monitors daily food prices to warn about possible anomalous dynamics, by means of analytical and visual tools. Moreover, based on daily prices and other high frequency indicators we nowcast official food consumer price indices.