The Honours in Quantitative Data Science is intended for students who have completed the Quantitative Data Science stream in program 3959, the Bachelor of Data Science and Decisions. It is also open to other students from other programs with a suitable mix of undergraduate courses.
Below you can find some specific information about Quantitative Data Science Honours.
For more general info about doing Honours in Quantitative Data Science, see the Honours Page.
Honours Coordinator – Quantitative Data Science
Dr Clara Grazian
Email: c.grazian@unsw.edu.au
Phone: 9385 7475
Office: Rm 2056, Red Centre (Centre Wing)
If you have any questions about the Honours year, please don't hesitate to contact the Honours Coordinator.
Quantitative Data Science Project Areas
The following are suggestions for possible supervisors and honours projects in Quantitative Data Science. Other projects are possible, and you should contact any potential supervisors to discuss your options.

Extreme value theory
 Bayesian neural networks
 Deep learning
 Machine learning
 Earth and climate data science
 Spatiotemporal data analysis
 Inference with incomplete data
 Statistical computation

Approximation properties of neural networks
 Nonparametric and semiparametric density estimation
 Nonparametric and semiparametric regression, in particular binary regression
 Functional data analysis
 Bayesian statistics
 Clustering
 Spatiotemporal modelling
 Applications in genomics, cybersecurity, ecology, finance
 In collaboration with the Garvan Institute: Datadriven approaches for determining the rate of somatic mutation in individual cells
 For some examples of my current projects, have a look at my page: https://research.unsw.edu.au/people/drclaragrazian
Clara Grazian and Shane Keating
 In collaboration with Spiral Blue, Detecting maritime vessel anomalies using kmeans clustering
 Optimization based decisionmaking under data uncertainty
 Datadriven robust optimization
 Global optimization and data classification
 Social network analysis
 Analysis of blockchain data
 Statistical computing
 Burden of disease
 Appropriate disease burden methods
 Dependence measures
 Neuroimaging genetics
 Data science for IoT
 Optimisation methods in machine learning
 Optimisation under data uncertainty

Making sense of naturalistic driving study data
 Inference about expectiles
 Optimal capital allocation
 Projection methods for machine learning
 (Higherorder) Voronoi diagrams for data analysis
 Conic programming and semidefinite optimisation for data science
Moninya Roughan (cosupervisor)
 Oceanography
 Big data and time series
 Correlated variables
Amandine Schaeffer (cosupervisor)
 Environmental drivers of marine heatwaves
 Understanding biological productivity in the ocean: statistical model from insitu glider observations
 Bayesian inference
 Computational statistics
 Variational methods
 Likelihoodfree/indirect methods
 Symbolic data analysis
 Extreme value theory
 Developing mathematical methods of topological data analysis
 Applications of topological data analysis for genetic and clinical data
 Analysis of large spatial datasets
 Highdimensional data analysis
 Simulationbased inference
 For more, see UNSW EcoStats projects ideas