Synthetic data use: exploring use cases to optimise data utility

Abstract Synthetic data is a rapidly evolving field with growing interest from multiple industry stakeholders and European bodies. In particular, the pharmaceutical starting to realise value of synthetic which being utilised more prevalently as method optimise utility sharing, ultimately an innovative response demand for improved privacy. generated by simulation, based upon mirroring properties original dataset. Here, supporting viewpoints across industry, we set out explore use cases seven key but relatable areas optimising privacy protection. We also discuss various methods can be used produce dataset availability metrics ensure robust quality datasets. Lastly, potential merits, challenges future direction within considerations this enhancing technology.