Project Category: Queensland Police Service

Bias Mitigation in Human in the Loop Decision Systems

About the Project

When humans label data to train AI models, their own biases and stereotypes may be reflected in the data, which consequently appear in the resulting trained models leading to unfair, biased, and non-transparent decisions. In collaboration with the Queensland Police Service (QPS), this project focuses on integrating fairness into learning algorithms used in the context of policing services and tasks and aims to observe if this leads to improved outcomes and experiences. The approach will include the development of human-in-the-loop AI, where humans help to increase transparency of automatic decision-making process, e.g., by generating natural language explanations on why a specific amount of police resources is required in a certain suburb.

This project commenced in April 2023 with the recruitment of PhD researcher Hongliang Ni, who is based at The University of Queensland and will collaborate closely with leading experts in the Queensland Police Service (QPS) to generate more transparent, fair, and trustworthy decision-support systems driven by data and controlled by humans. Through this project, Hongliang will develop novel bias tracking, management, and reduction method over the entire Artificial Intelligence pipeline: from data collection and curation to model training and deployment with end users. It is one of two projects with Queensland Police Service related to the responsible use of sensitive data assets. The other project Data as a Service Architecture commenced in October 2023.

Hongliang is supervised by CIRES Chief Investigator Associate Professor Gianluca Demartini, Centre Director Professor Shazia Sadiq, and Nick Moss, Manager, Data Services at the Queensland Police Service.

The Queensland Police Service (QPS) aims to be a data driven organisation with an advanced data analytics capability to inform decision making via legally and ethically actionable analytics. 

The QPS Organisational Insights Platform (OIP) was established as the QPS advanced data and analytics platform for tactical, operational, and strategic decision making.  A foundational building block of the OIP is the Data Lake to become the QPS centralised repository to store approved structured and unstructured data. The information resilience challenge is how to extract insights from, and the responsible use of, sensitive data assets. 

QPS are looking at this partnership opportunity with CIRES to build, protect and sustain agile data pipelines, in addition to upskilling officers, and identifying and employing potential data scientists, to position QPS as an insight driven organisation. One key measure of success will be better informed tactical, operational, and strategic decision makers who can apply resources, develop policy, procedures, and practices so that the lives of Queenslanders benefit positively. 

Data as a Service Architecture

About the Project

This project aims to develop a novel system for making efficient and effective queries and recommendations based on multi-source data from partner, the Queensland Police Service [QPS], by constructing an enterprise knowledge graph model for analysing complex objects from multiple data sources. The project will develop ranking algorithms and deep models for yielding efficient and effective data queries recommendations, which also consider the evolutionary, uncertain data, and human experts in the loop. The proposed techniques will be validated by conducting interactive experiments on the QPS data lake. The applicability of graph-based methods for generating complex network, ranking methods, and deep models for making queries and recommendations will be explored to discover relationships, rules and patterns previously unknown, and potentially useful for on-duty police officers.

This project commenced in October 2023 with the recruitment of PhD researcher Fidan Karimova at The University of Queensland. Fidan and the project team will collaborate closely with leading experts in the Queensland Police Service (QPS) to develop a prototype system to showcase the scalability, reliability, and usability of an AI-based data discovery system. Fidan is supervised by CIRES Chief Investigators Dr Rocky Chen and Associate Professor Hongzhi Yin, Affiliate Investigator Dr Wen Hua, Centre Director Professor Shazia Sadiq, and Partner Investigator from QPS Mr Nick Moss.

This is one of two CIRES projects with QPS related to the responsible use of sensitive data assets. The other project Bias Mitigation in Human in the Loop Decision Systems commenced in April 2023.

The Queensland Police Service (QPS) aims to be a data driven organisation with an advanced data analytics capability to inform decision making via legally and ethically actionable analytics. 

The QPS Organisational Insights Platform (OIP) was established as the QPS advanced data and analytics platform for tactical, operational, and strategic decision making.  A foundational building block of the OIP is the Data Lake to become the QPS centralised repository to store approved structured and unstructured data. The information resilience challenge is how to extract insights from, and the responsible use of, sensitive data assets. 

QPS are looking at this partnership opportunity with CIRES to build, protect and sustain agile data pipelines, in addition to upskilling officers, and identifying and employing potential data scientists, to position QPS as an insight driven organisation. One key measure of success will be better informed tactical, operational, and strategic decision makers who can apply resources, develop policy, procedures, and practices so that the lives of Queenslanders benefit positively.