The proposed setting–Development Science Framework (DSF), views each SDG as a source of highly correlated Big Data attributes and seeks to explore their interactions in a predictive, spatio-temporal context. For example, the relationships among SDGs 13, 14 & 15 on human livelihood, reflected by SDGs 1 through 7, are particularly intriguing and modelling their dynamics can provide answers to general questions in the form of What Works Across Countries and Sectors? The relationships among attributes describe the invariant conditions that epitomise the meaningfulness of the concept which DSF learns from available data. DSF adopts first principles approach, treating SDGs as sub-projects, driven by the well-documented relationship between knowledge & development in time and space. It focuses on trust, interdisciplinarity, authoritative data, knowledge transfer, resources, tools & techniques. Analogous to Eleanor Roosevelt’s view on where universal rights begin, it takes a bottom-up approach to the universal agenda 2030, seeking real knowledge on indicators from "...small places, close to home–so close and so small that they cannot be seen on" the World Bank SDG Atlas. Its main objectives are therefore to map and deliver knowledge about clusters of individual societies on that global map, their disparate neighborhoods, activities, achievements and influencing factors, based on indicators deriving from relevant and authoritative data from various sources, including grey literature and citizen science. Its implementation strategy is for three pilot DSF SDG monitoring nodes to be established in three African countries with known socio-economic heterogeneity, in order to provide a clear baseline for the project. To effectively support agenda 2030 at the country level, the project requires a guarantee that policy makers affecting each monitoring node, are in full agreement with Open Data Initiative (ODI) agenda.
Key Words: Big Data, Citizen Science, Concept Learning, Culture, Grey Literature, ICT, IoT, SDGs