I am a PhD student at the Department of Computer Science, University of Warwick, and working under the supervision of Prof. Theo Damoulas. My research focuses on developing methodologies to advance the spatial-statistical models by quantifying uncertainty to perform inference on large-scale data. My work is funded by Engineering and Physical Sciences Research Council (EPSRC) and Nimbus Property Systems Limited. Tools and languages include GIS, Python, R, SQL, and TensorFlow.
Prior to starting the PhD, I completed an MSc with distinction in Business Analytics from the University of Warwick in 2017 and holds a BSc (Hons) in Statistics with Computer science from the University of Colombo (2012). I have completed the exams of the Chartered Institute of Management Accountants (CIMA), UK in 2011.
I have industrial experience of over seven years working at Moody’s Analytics Company for three years, providing quantitative research support to an experienced Global Asset Manager and as a data scientist at Nimbus Property Systems.
CS910 Foundations of Data Analytics
Publications & Preprints
Perera, S., Aglietti, V., & Damoulas, T. (2021). A variational Bayesian spatial interaction model for estimating revenue and demand at business facilities. arXiv preprint arXiv:2108.02594
Yeboah, G., Porto de Albuquerque, J., Troilo, R., Tregonning, G., Perera, S., Ahmed, S. A., ... & Yusuf, R. (2021). Analysis of OpenStreetMap Data Quality at Different Stages of a Participatory Mapping Process: Evidence from Slums in Africa and Asia. ISPRS International Journal of Geo-Information, 10(4), 265.
Perera, S., Damoulas, T., Davis, P., & Jarvis, S. (2019). Modelling Business Rates in England with Big Spatial Data. In Proceedings of SIGKDD ’19: International Workshop on Urban Computing, Alaska, USA.
Presented at the 8th SIGKDD International Workshop on Urban Computing, Alaska - USA (2019)
Presented at the 1st LIESMAR PhD Symposium on Geoinformatics, Wuhan University, China (2017)
s dot perera at warwick dot ac dot uk