Embedded Files
Ghita Berrada
Ghita Berrada
Data Scientist | Researcher in Machine Learning and Applied Data Science
Email: berrada.ghita[at]gmail.com
Code samples:
https://gitlab.com/berradag (mainly code related to anomaly detection)https:://github.com/berradag
CV
Link to LinkedIn profile
I am a computer scientist and data scientist whose work spans machine learning, decision support systems, anomaly detection, uncertainty and responsible AI, with applications including healthcare, cybersecurity and the social sciences.
From April 2023 to September 2026, I was an Assistant Professorial Lecturer and later Assistant Professor (Education) in Data Science at the Data Science Institute (DSI) at the London School of Economics and Political Science (LSE). I convened and taught courses in data science and machine learning for multidisciplinary social science students.
I was previously a Research Associate in Health Informatics at King's College London (Sept 2019–Mar 2023) and a Research Associate in the School of Informatics at the University of Edinburgh (June 2016–June 2019). I also held an honorary appointment at the School of Health Sciences, Division of Informatics, Imaging & Data Sciences at the University of Manchester (Feb 2021–Dec 2022).
I am not a dyed-in-the-wool Bayesian though I am supposed to be one by training...
PS: In case you're wondering how my name is pronounced, just replace the "Gh" by an "R" (preferably a French "R") and you'll be close enough...
Research interests
Research interests
Broadly speaking, I am interested in "decision support systems", particularly in application domains such as healthcare or computer security. More specifically, my research revolves around questions such as the following:
How do you design systems to assist users' decision-making when the data available is highly unbalanced (i.e the classes of interest are varied and barely represented in the data), highly uncertain and barely annotated? How do you design a good system when you are interested in the anomalies rather than the (majority) "normal class"?
How do you properly evaluate such systems?
Can we design "better" decision support systems by making use of provenance data/data provenance?
How do you present the results of such decision support systems in a way that is easily understandable by a human user (e.g visualization, explanations...)?
How do we make such systems "ethical" by design and avoid their possible (negative) externalities (e.g impact on human dignity) ?
Education
Education
PhD in Computer Science, 2015
MSc in Pattern Analysis and Neural Networks, 2007
Diplôme d'ingénieur (French engineering diploma, equivalent to MSc), 2007
Google Sites
Report abuse