Research Associate
Computer Engineering Lab
School of Electrical and Information Engineering
Room 830, Building J03, Maze Cresent
University of Sydney, NSW, 2006
Australia
Phone: +(612) 9351 4135
Email: farzad.noorian@sydney.edu.au
Research Interests
Farzad’s current research involves different techniques used in hedging Foreign Exchange trading risks. His research interests include:
- Financial Engineering
- Machine learning
- Computational Intelligence
- Parallel, Distributed and Cloud Computing
Publications
- Farzad Noorian and Philip H.W. Leong. On time series forecasting error measures for finite horizon control. IEEE Transactions on Control Systems Technology, vol.25, no.2, pp. 736–743, 2017. [Code & Resources]
- Farzad Noorian, Barry Flower, and Philip H.W. Leong. Stochastic receding horizon control for short-term risk management in foreign exchange. Journal of Risk, vol. 18, no. 5, pp. 29–62, 2016. [Code & Resources]
- Farzad Noorian, Anthony M. de Silva, and Philip H.W. Leong. gramEvol: Grammatical Evolution in R. Journal of Statistical Software, vol. 71, no. 1, pp. 1–26, 2016.
- Lei Li, Farzad Noorian, Duncan J.M. Moss, and Philip H.W. Leong. Rolling window time series prediction using mapreduce. In proc. IEEE International Conference on Information Reuse and Integration (IRI), pp. 757–764, 2014.
- Farzad Noorian and Philip H.W. Leong. Dynamic hedging of foreign exchange risk using stochastic model predictive control (with errata). In proc. IEEE Conference on Computational Intelligence for Financial Engineering & Economics – (CIFEr), pp. 441–448, 2014. [Code & Resources]
- Anthony Mihirana de Silva, Farzad Noorian, Richard I. A. Davis, and Philip H. W. Leong. A hybrid feature selection and generation algorithm for electricity load prediction using grammatical evolution. In proc. IEEE 12th International Conference on Machine Learning and Applications ICMLA 2013, special session on Machine Learning in Energy Applications, pp. 211–217, 2013. [Code & Resources]
- PhD Thesis: Risk Management using Model Predictive Control
Software
R packages
- gramEvol: Context free grammar and grammatical evolution for R
- diskmemoiser: Disk memoisation for R
- quadprogpp: A fast quadratic programming solver implementation for R
Arduino Libraries
- EasyTransferPP: An Arduino library for easy transfer of structs over Serial or TWI using C++ templates
Seminars and Presentations
- Research Conversazione 2015, The University of Sydney [Presentations]
- Grammar-based Feature Generation for Time-series Prediction, NICTA SML Seminar, 2013. [Slides]
Awards
- Winner of Gecco 2013 Industrial Challenge
- Winner of Gecco 2015 Industrial Challenge
- Winner of Freelancer.com Prize in Software Engineering, Conversazione 2013 poster session
- Winner of AEMO Prize in Power Engineering (Energy Markets), Conversazione 2014 poster session