Increasing the effectiveness of quantitative verification. The ability to analyse the performance of complex systems and protocols is a vital part of the development of large-scale computer applications. Methods that improve the effectiveness of the analysis task would increase the competitiveness of the software industry, and would attract future development work (in complex systems) to Australia. The results of this project will have a direct influence on currently available design tools; the ....Increasing the effectiveness of quantitative verification. The ability to analyse the performance of complex systems and protocols is a vital part of the development of large-scale computer applications. Methods that improve the effectiveness of the analysis task would increase the competitiveness of the software industry, and would attract future development work (in complex systems) to Australia. The results of this project will have a direct influence on currently available design tools; the fact that Australian institutions will be (in part) responsible for key theoretical results in this growing field will strengthen Australia's position worldwide as an international centre for computer science.Read moreRead less
Inference for Hawkes processes with challenging data. The Hawkes processes are statistical models for the analysis of high-impact event sequences, such as bushfires, earthquakes, infectious diseases, and cyber attacks. When the times and/or marks are missing for some events or when the data is otherwise incomplete, it is challenging to fit these models and perform diagnostic checks on the fitted models. This project aims to develop novel statistical methods to fit these models in the presence of ....Inference for Hawkes processes with challenging data. The Hawkes processes are statistical models for the analysis of high-impact event sequences, such as bushfires, earthquakes, infectious diseases, and cyber attacks. When the times and/or marks are missing for some events or when the data is otherwise incomplete, it is challenging to fit these models and perform diagnostic checks on the fitted models. This project aims to develop novel statistical methods to fit these models in the presence of incomplete data and to check the goodness-of-fit of the fitted models. The expected outcomes include publications documenting these methods and software packages implementing them. The primary benefits include the advancement of statistical methodology and the training of junior research personnel. Read moreRead less
Bayesian Inference for Multivariate Hierarchical Regression Models. This project will develop Bayesian methodology for analysing multivariate regression models. The distribution of each measurement can be discrete or continuous, with the dependence between measurements obtained through the correlation matrix of a Gaussian copula. Model parsimony is obtained by identifying zero elements in the correlation matrix or its inverse and by variable selection on the regression parameters. The results wi ....Bayesian Inference for Multivariate Hierarchical Regression Models. This project will develop Bayesian methodology for analysing multivariate regression models. The distribution of each measurement can be discrete or continuous, with the dependence between measurements obtained through the correlation matrix of a Gaussian copula. Model parsimony is obtained by identifying zero elements in the correlation matrix or its inverse and by variable selection on the regression parameters. The results will be applied to solve problems in finance, health management and marketing. In all these fields multiple observations are often taken per individual or time period and the models need to incorporate measures of dependence and uncertainty.Read moreRead less
Stochastic Methods for Dynamic Risk Management. In today's environment of intense competitive pressures, volatile economic conditions, rising bankruptcies, and increasing levels of consumer and commercial debt, an organization's ability to effectively monitor and manage its credit risk can mean the difference between success and survival. The improvement of dynamic risk management systems is also an essential part of the new regulatory Capital Adequacy Proposal Basel II in which risk-sensitive c ....Stochastic Methods for Dynamic Risk Management. In today's environment of intense competitive pressures, volatile economic conditions, rising bankruptcies, and increasing levels of consumer and commercial debt, an organization's ability to effectively monitor and manage its credit risk can mean the difference between success and survival. The improvement of dynamic risk management systems is also an essential part of the new regulatory Capital Adequacy Proposal Basel II in which risk-sensitive capital requirements for credit portfolios and internal models of credit risk are advocated. The goal of the project is to develop novel stochastic methods for managing of credit risk and to bring theoretical innovations developed within the project to practical implementations. Read moreRead less
Investment Approaches and Applications in Financial Markets: Evolutionary Kernel Based Subset Time-Series Using Semi-Parametric Approaches. The project will develop new investment assessments based on subset time-series modeling. Innovative evolutionary kernel smoothing algorithms using semi-parametric approaches will be introduced. The project will make three important applications of this modeling in financial markets: a) benchmarking and evaluation of inflation-indexed bonds; b) evaluation of ....Investment Approaches and Applications in Financial Markets: Evolutionary Kernel Based Subset Time-Series Using Semi-Parametric Approaches. The project will develop new investment assessments based on subset time-series modeling. Innovative evolutionary kernel smoothing algorithms using semi-parametric approaches will be introduced. The project will make three important applications of this modeling in financial markets: a) benchmarking and evaluation of inflation-indexed bonds; b) evaluation of the performance of global diversified investment funds; and c) prediction to provide early warning of the emergence of destabilising deflation or inflation. These three applications will lead to improved risk management practices and investment performance. Recursive algorithms will provide new statistical methods to study investment asset price movements and market volatility.
Read moreRead less
Investment approaches and opportunities in renewable energy and financial resource markets, using semi-parametric approaches to evolutionary subset time-series lattice-ladder modelling. The project findings will help Australian exporters and importers understand and manage energy and resource price risks more effectively. The investment community will benefit through selecting optimal asset allocations and enhancing value to investors. It will also benefit many other agencies, particularly in th ....Investment approaches and opportunities in renewable energy and financial resource markets, using semi-parametric approaches to evolutionary subset time-series lattice-ladder modelling. The project findings will help Australian exporters and importers understand and manage energy and resource price risks more effectively. The investment community will benefit through selecting optimal asset allocations and enhancing value to investors. It will also benefit many other agencies, particularly in the service industries. It is not well recognised that in developed countries, including Australia, the financial service and related sectors account for more than 60 percent of economic activity and employment, so it is critical that more sophisticated statistical methods be established, and practical applications conducted, in order to advance the understanding of complexity management in the financial service and related sectors.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE160100999
Funder
Australian Research Council
Funding Amount
$295,020.00
Summary
Applying forward-backward stochastic differential equations to optimisation. This project intends to develop new ways to solve optimisation problems that are currently difficult to solve because of their complexity and size. In particular, forward–backward stochastic differential equations (FBSDEs) are a new technique that is showing ways to solve problems for which there is yet to be a solution. This project's focus will be on problems that cannot use existing software because the decision-maki ....Applying forward-backward stochastic differential equations to optimisation. This project intends to develop new ways to solve optimisation problems that are currently difficult to solve because of their complexity and size. In particular, forward–backward stochastic differential equations (FBSDEs) are a new technique that is showing ways to solve problems for which there is yet to be a solution. This project's focus will be on problems that cannot use existing software because the decision-making processes require intensive consideration of all possible outcomes in the modelled environment. In comparison to previous optimisation methods, the FBSDE approach is easier to work with and much more informative. The project's main potential applications are multiplayer games with mean-field interaction and financial markets with partial information.Read moreRead less
Technology-Driven and Scalable Regression Methodology, Computing and Theory. Regression is a mainstay of data analysis, statistics, machine learning and data science but is in continual need of enhancement in the face of technological change. Scalability and flexibility for the handling of non-linear signals are fundamental to the practical utility of new regression methodology. Several streams of research aimed at confronting data from specific technologies as well as generic types of data are ....Technology-Driven and Scalable Regression Methodology, Computing and Theory. Regression is a mainstay of data analysis, statistics, machine learning and data science but is in continual need of enhancement in the face of technological change. Scalability and flexibility for the handling of non-linear signals are fundamental to the practical utility of new regression methodology. Several streams of research aimed at confronting data from specific technologies as well as generic types of data are proposed. The project is to be networked with researchers in the United States of America and aims to have Australia-based researchers providing leadership in terms of methodological, theoretical, computational and software development.Read moreRead less
Overseeing the internet: new paradigms of network measurement. Like the electricity network, the internet is a core infrastructure, and so must be reliable and efficient. A gap in bandwidth supply is like a blackout in terms of lost business and productivity. This project will provide the measurement breakthroughs to ensure that network behaviour can be accurately and comprehensively monitored.
Discovery Early Career Researcher Award - Grant ID: DE140100993
Funder
Australian Research Council
Funding Amount
$293,520.00
Summary
Mathematics of importance: The optimal importance sampling algorithm for estimating the probability of a black swan event. Rare event simulation and modelling is critical to our understanding of high-cost hard-to-predict events such as nuclear accidents, natural disasters, and financial crises. Quantitative analysis of such high-impact events demands the accurate estimation of the probability of occurrence of such rare events. In realistic models this probability is very difficult to estimate, ....Mathematics of importance: The optimal importance sampling algorithm for estimating the probability of a black swan event. Rare event simulation and modelling is critical to our understanding of high-cost hard-to-predict events such as nuclear accidents, natural disasters, and financial crises. Quantitative analysis of such high-impact events demands the accurate estimation of the probability of occurrence of such rare events. In realistic models this probability is very difficult to estimate, because exact simple analytical formulas are not available and the existing estimation methods fail spectacularly. There is an urgent need for new efficient methodology. This project develops a new Monte Carlo method that will be able to estimate reliably and accurately rare-event probabilities. Read moreRead less