Syed (Ali) Rizvi

DPhil Student, Engineering, Machine Learning Research Group

DPhil Candidate at the Department of Engineering, Machine Learning Research Group.

Supervisor: Prof. Steve Roberts

Ali is currently conducting his research on volatility prediction for FX data, especially at scales where market microstructure becomes prominent, using Bayesian non‐parametrics ‐ in particular warped Gaussian processes and Student‐t processes.  

In the coming year Ali’s research focus will be on using heteroskedastic Student‐t processes and comparing their performance against traditional econometric approaches, like GARCH. Ali is also looking at Gaussian processes (GPs) with expressive closed form kernels, based on spectral density decomposition and their application to quantitative finance. He want to combine GPs with mixed‐norm loss functions for modelling the heavy tails of financial market returns, to research if gains are made in the prediction of volatility outliers.  

Ali is also interested in using Multi‐input Gaussian processes and multi‐input Student‐t processes to use weather data in tandem with the more traditional data streams to study any gains in forecasting improvement for FX volatility.

Before coming to Oxford, Ali worked for a few years as an Instrumentation Engineer at a fertilizer company in Pakistan. Ali did his undergraduate in Electronics Engineering from National University of Sciences and Technology, Pakistan. 

Further interests: Data mining, Large scale data analysis, Electronic trading, Artificial Intelligence.   

Working Paper

Rizvi, S., van Heerden, E., Salas, A., Nyikosa, F., Roberts, S., Osborne, M. and Rodriguez, E. (2017). Identifying sources of discrimination risk in the life cycle of machine intelligence applications under new European Union regs.
Rizvi, S.A.A., Roberts, S.J., Osborne, M.A., and Nyikosa, F. (2017). A novel approach to forecasting financial volatility with Gaussian process envelopes.
Rizvi, S.A.A., Roberts, S.J., Osborne, M.A. and Nyikosa, F. (2017). Predicting dynamic renyi entropy using gaussian processes to estimate financial information flows.