Dr Stef Garasto BSc, MSc, PhD

Lecturer in Data Science

Stef Garasto is a Lecturer in Data Science at the University of Greenwich, with a focus on Natural Language Processing as well as ethics and justice in data science.

Prior to joining Greenwich, Stef worked a researcher at Imperial College London and at Nesta. As a Principal Researcher in Data Science at Nesta, they used novel sources of data and machine learning algorithms with a view to building a more resilient and inclusive labour market. This included developing measures of jobs accessibility and skill demand using a variety of datasets.
Stef obtained a PhD in Computational Neuroscience from Imperial College London. Their PhD research focused on stimulus reconstruction methods to investigate how the brain processes sensory information (specifically vision) and population coding principles.

Being passionate about using “data science for social good”, Stef also volunteers at DataKindUK to further the use of responsible data science in the UK non-profit sector.

Research / Scholarly interests

My research falls under the umbrella of applied machine learning/data science. I use computational techniques to derive insights about society and/or biological systems. Deep methodological expertise is combined with a broad variety of interests, ranging from the heart electrophysiology to media texts. I also have an interest in issues of ethics and justice surrounding algorithmic systems.

Recent publications

  • Garasto, S., Djumalieva, J., Kanders, K., Wilcock, R. and Sleeman, C., 2021. Developing experimental estimates of regional skill demand. (No.  ESCoE DP-2020-19). Economic Statistics Centre of Excellence (ESCoE) Discussion Papers.
  • Djumalieva,  J., Garasto, S.,  and Sleeman, C., 2020.  Evaluating a new earnings indicator:  Can we improve the timeliness of existing statistics on earnings by using salary information fromonline job adverts?  (No.  ESCoE DP-2020-19). Economic Statistics Centre of Excellence (ESCoE) Discussion Papers.
  • Garasto, S., Nicola, W., Bharath, A.A. and Schultz, S.R., 2019, March. Neural sampling strategies for visual stimulus reconstruction from two-photon imaging of mouse primary visual cortex. In 2019 9th International IEEE/EMBS Conference on Neural Engineering (NER) (pp. 566-570). IEEE.
  • Sorteberg, W.E., Garasto, S., Cantwell, C.C. and Bharath, A.A., 2019, April. Approximating the solution of surface wave propagation using deep neural networks. In INNS Big Data and Deep Learning conference (pp. 246-256). Springer, Cham.
  • Cantwell, C.D., Mohamied, Y., Tzortzis, K.N., Garasto, S., Houston, C., Chowdhury, R.A., Ng, F.S., Bharath, A.A. and Peters, N.S., 2019. Rethinking multiscale cardiac electrophysiology with machine learning and predictive modelling. Computers in biology and medicine, 104, pp.339-351.
  • Hakkinen,  A.,  Kandhavelu,  M., Garasto, S.,  and  Ribeiro,  A.  S.,  2014. Estimation  of fluorescence-tagged RNA numbers from spot intensities. Bioinformatics, btt766.