Computational Finance
   Hybrid Systems
   Recurrent Networks
   Support Vector Machines
   Input Variable Selection
   Classification Methods

   Book Chapters
   Journal Papers
   Conference Papers

   Windale Technologies


   Contact Me
View Andrew Back's profile on LinkedIn
I am interested in developing solutions for analysing

I am currently involved in developing quantitative software for options pricing and volatility analysis. Recently I founded a company which has produced quantitative software for various companies, banks and financial institutions worldwide. I have developed models and created software for the analysis of the wholesale electricity industry. In particular, I researched, designed and developed solely from scratch, a computer simulation model in Matlab to predict the wholesale electricity prices across eastern Australian states in the National Electricity Market (NEM).

I have a degrees in engineering including a PhD which involved developing new nonlinear models for time series prediction, nonlinear modeling and control. I have a fairly extensive background in academic research, having worked in University of Queensland (Australia), RIKEN (Japan), NEC Research Institute (USA) and DSTO (Australia).

I maintain an active involvement in research where my interests include the development and analysis of nonlinear models with particular application to biomedical data and financial markets.

I am interested in developing solutions for analysing, modeling and classifying various types of data. In particular, my work has concentrated on developing new nonlinear models and algorithms in the field broadly known as datamining. The approaches I use come from a range of methods, such as classical linear systems theory, statistical techniques, signal processing, control theory, hybrid systems and nonlinear models including feedforward and recurrent neural networks.

I have obtained results in the
approximation of hybrid systems by recurrent networks, low sensitivity recurrent networks and the analysis of financial time series using independent component analysis. I am also investigating the use of support vector machines for signal classification and input variable selection techniques for efficiently modeling and analysing multivariate data with high dimensionality. Biomedical data (EEG,ECG), speech, industrial processes and multivariate financial time series are among some of the time series I've worked with.

More recently I have been working in a mathematical software company, Windale Technologies developing quantitative software for options pricing using the Black-Scholes model, Binomial model and others.

If you have any questions or comments please feel free to
email me.




Home   Research  Contact Me  Feedback  Publications

Copyright 1989-2008 Andrew Back. All Rights Reserved.