1.  ARC-Discovery Project (DP200101374), Smart Personalised Privacy Preserved Information Sharing in Social Networks, AU$390K, 2020-2023
2.  ARC-Linkage Project (LP170100891), Reshaping superannuation practice in Australia using big data analytics. AU$416K, 2018-2021
3.  ARC-Linkage Project (LP140100937), AU$360K, 2015-2018
4. Australia Cooperative Research Centres Projects (CRC-P) grant round 7, Using AI and a hybrid ESS solution to fully integrate solar generation into the distribution system, AU$3M, 2019-2022


  •  ARC DP200101374: Smart Personalized Privacy Preserved Information Sharing in Social Networks (Jan 2020 – Dec 2022)

This project aims to create a novel and effective method for privacy protection at individual level, which is now a great concern of persons, businesses, and government agencies in this big data age. The project expects to build an automatic smart practical personalized privacy preserving system through removing the fundamental obstacles. The project will significantly advance human knowledge of privacy, and push Australia to the front line of the research field, and protect Australia better.

  • Australia Cooperative Research Centres Projects (CRC-P) round 7: Using AI and a hybrid ESS solution to fully integrate solar generation into the distribution system (Sep 2019 – Aug 2022)

Using Artificial Intelligence and hydrogen to unleash the power of solar energy will create solar farms with advanced energy storage, similar to lithium batteries and hydrogen fuel cells. UTS will provide the expertise in Artificial Intelligence (AI) for a hybrid Energy Storage System (ESS) solution to integrate solar generation fully into the distribution system. The project aims to develop a widely applicable integrated package for small-scale solar farming, focusing not just on photovoltaic technologies and solutions, but on the monitoring, control, integration and optimisation of distributed solar farming.

  • ARC-LP170100891: Reshaping Australian superannuation practice via big data analytics (Oct 2018 – Sep 2021)

This project aims to reform superannuation investment practices in Australia. Using sophisticated data analytics and machine-learning techniques, combined with economic modelling and quantitative finance. The project will try to understand the broad characteristics of Australian superannuation investors and their practice from a ‘big data’ perspective. The expected outcomes of this project are the identification of key determinants for successful superannuation behaviour to inform decision-making for better superannuation practices and policies. It is expected that the insights arising from this project will contribute to safeguarding the future of Australia’s superannuation schemes, and to better financial security at retirement.

  • Understanding Micro-Videos for Customer Profiling and Personalized Marketing (Aug 2020 – Aug 2021)

Micro-videos are gaining significant popularity at the moment, which are a new form of user-generated content captured by using easily accessible devices such as smart phones, making the number of them growing exponentially in online sharing platforms. The goal of this proposal is therefore to develop effective and efficient machine learning models to target and profile potential customers through understanding micro-videos and users’ activities. This is a industry partnership project with eBay US.

  • AI-enhanced Underwriting systems and insights of Mental Health (Aug 2019- Aug 2020)

This project aims to optimise the AI-based underwriting risk engine developed in previous project, anti-selection detection, and conduct pilot study of mental health disorder analysis and visualisation.

  • AI-enhanced Life Insurance underwriting automation and optimization for ANZ Wealth (Sep 2017 – Aug 2018)

This project aims to develop AI-based underwriting risk engine to improve current manual underwriting process in life insurance. The data-driven model provides personalised, efficient service with improved quality assurance for customers when they apply for insurance. This project is partnered with ANZ wealth.

  • Longitudinal Study of Taxpayer behavioural Analysis (Oct 2015 – Sep 2018)

This ARC-funded Linkage project is to investigate the taxpayer behavioural patterns in Australian. Specific analytics lens is developed to reveal the characteristics of interested cohorts, e.g. debtor from longitudinal point of view. This project was jointly funded by ARC and ATO.

  • Personality mining via call log analysis (May 2017 – Dec 2017)

This project is to devise a data model of big-five personality scores based on customer call centre logs. Big data analytics on textual, audio, and video data is used to train the personality analysis engine. The personality traits will create value to various business applications. This project is supported by wealth management group Colonial First State.

  • NSW Emergence Department Treatment Performance Analysis (May 2017 – Nov 2017)

This project developed data analytics and visualisation element to analyse the ED Treatment Performance across NSW.

  • Building Predictive Models for Super Guarantee Contribution (May 2016 – Dec 2016)

Predictive models for SG contribution prediction via big data analytics. This project is supported by Wealth management group Colonial First State.

  • Life Insurance Claim Pattern and Pricing Analysis in ANZ Life Insurance (Feb 2016 – Dec 2016)

This project investigated the business insight of life insurance claims based on the past years claim data. The analytical finding is used to reshape insurance products.

  • NSW-Government Analytics Engagement Framework (Mar 2016 – Jun 2016)

This project conducted site work for developing an Analytics Engagement framework for one NSW government legal service agency on fraud detection, customer acquisition, customer engagement, and retention

  • Building Deep Insights and Advanced Workforce Modelling in Aged-care Services (Oct 2015 – May 2016)

This project was conducted to forecast the staffing and skill-set demand in home-based healthcare service. Time series forecasting, operational, and predictive modelling are combined. This project is funded by Kincare Home-based services

  • Develop Deep Insights in Customer Retention (May 2015 – Dec 2015)

This project incorporated big data of customers, e.g. demography, transaction, interaction, and behaviour information into prediction of customer churn. Machine learning based prediction models were developed for various business products. This project was partnered with Colonial First State.