An online service platform turning unstructured data into structured meta-data enriched machine-readible formats. Existing datasets from a wide variety of data management software can be uploaded, validated, classified and combined.
Validation suggestion will based on Natural Language Processing (NLP) and user- indicated field selections. Irregularities such as duplicates can be accepted/rejected and amended online or downloaded and locally amended.
It will also possible to validate using combined datasets and find overlapping project activities or certifications.
Validated data can be downloaded and processed locally, or further processed with tools Farm Data Pods.
Where schemas such as IATI or neutral alignment tools such as UTZ First Mile Farm Data exist, data operators should have the tools to enrich existing datasets with such data classifications:
- Data sets can be mapped and enriched with data classifications from frameworks such as IATI, Utz First Mile, industry specific tools and Schema.org, the latter being widely used by for instance Google and thousands of open source data providers;
- Data Raccoon allows for classifying data to match with Sustainable Development Goal indicators;
- Classification allows for data combinations as well as interconnectivity and interoperability, see Tool E.
Data Raccoon will suggest comparable third party datasets, such as for instance with Open Data or datasets from peer organisations. This can help to compare the performance of projects or businesses with similar initiatives.