No abstract

No abstract

No abstract

Data is an extremely important intangible good, but official data is not always available. It may be scarce for many reasons, among which: low statistical capacities, poor funding for data and statistics, weak data dissemination and use culture. A solution to fill data gaps needs to consider that there is data made available on the web, usually coming in an unstructured way, that can be combined with innovative methods to generate relevant information. National and international organizations need to engage with new sources of data and methods considering the crisis of traditional data collection systems that cause data gaps. In this light, FAO created in 2019 the “Data Lab for statistical innovation” to fill such gaps by modernising the Organization’s statistical business, which means improving the timeliness and granularity of data collection, providing automated analysis, and capturing early warning signals. It does so through the use of cutting-edge technologies (such as web scraping, text mining, geo-spatial data analysis and artificial intelligence) and by introducing nonconventional sources of data (social media, online newspaper articles). This article summarises the experience of the FAO Data Lab and how it has been useful for the Organization to fulfil its mandate.

Within the context of Sustainable Development Goals, progress towards Target 12.3 can be measured and monitored with the Food Loss Index. A major challenge is the lack of data, which dictated many methodology decisions. Therefore, the objective of this work is to present a possible improvement to the modeling approach used by the Food and Agricultural Organization in estimating the annual percentage of food losses by country and commodity. Our proposal combines robust statistical techniques with the strict adherence to the rules of the official statistics. In particular, the case study focuses on cereal crops, which currently have the highest (yet incomplete) data coverage and allow for more ambitious modeling choices. Cereal data is available in 66 countries and 14 different cereal commodities from 1991 to 2014. We use the annual food loss as response variable, expressed as percentage over production, by country and cereal commodity. The estimation work is twofold: it aims at selecting the most important factors explaining losses worldwide, comparing two Bayesian model selection approaches, and then at predicting losses with a Beta regression model in a fully Bayesian framework.