Data Science & Business Analytics
Researchers in Data Science and Business Analytics seek to examine and exploit the myriad promises of big data.
A concerted interest is in utilising and improving data-driven methods, statistical analysis, machine learning, and analytics techniques to extract meaningful insights and inform organisational decision-making. For example, an enduring interest is in forecasting and predicting potential relationships between variables and outcomes of concern so that organisations can better chart their future and achieve their goals.
This interest is intertwined with the fundamental big data challenges, e.g., entity resolution, missing value imputation, high-dimensional clustering, and models for transfer learning.
What We Do
Develop and test predictive models to yield actionable insights for addressing a variety of business and societal problems.
Create big data analytics tools and solutions that enable organisations to collect, process, analyse, and visualise data effectively.
Advance knowledge in managing and governing data for privacy and security.
Sub Areas
- Big Data Analytics
- Causal Reasoning
- Data Engineering
- Deep Learning
- Machine Learning
- Optimisation
- Predictive Analytics
- Privacy and Ethics of Data Management
Our Research Projects
Decoding Persuasion on Crowdfunding Platforms
This research proposes a novel prediction framework based on persuasion theory to enhance crowdfunding success predictions. It aims to identify persuasive elements in project descriptions and improve the prediction accuracy so as to provide guidance for crowdfunding project initiators. The study integrates computational methods and deep learning to not only boost prediction performance but also offer interpretable insights, contributing to information systems and crowdfunding design.
Investigation on Digital Platforms and Human-machine Co-behavior Through AI, Empirical and Experimental Methods
This proposal investigates the impact of digital technologies on consumer behavior across e-commerce and social media platforms. Focusing on voice AI in shopping, filter bubbles in recommender systems, and social features affecting search volume, the project aims to provide valuable insights and address key questions in these domains.
- Machine Learning, Predictive Analytics
Understanding Online Contribution: Impact Evaluation and Crowd Wisdom Extraction
With the massive amount of online contributions shaping individual and organizational decision-making, this project delves into utilizing and understanding this valuable resource. By combining econometrics and natural language processing, the research seeks innovative insights to leverage these vast information pools and assess their impacts on commerce and society.
- Big Data Analytics
Academic Integrity Post-COVID-19: Multimodal Online Assessment Cheating Detection
Cheating cases are on the rise in academia, especially during the shift to remote learning. Using a blend of user studies and machine learning (ML) with multimodal features, this project aims to develop a robust ML model for detecting and identifying cheating patterns in various online assessment contexts.
- Machine Learning
Quantifying the Impact of Privacy Technologies (PETs) on Firms
Consumers' adoption of privacy enhancing technologies creates data analytics challenges to firms that rely on data to support their business models. This project seeks to develop conceptual and methodological frameworks to quantify the impact that such technologies will have on firms' analytics capabilities and business value.
- Privacy and Ethics of Data Management
Our Research Groups
Garbage Can Lab
The Garbage Can Lab (https://garbcan.com/) conducts research focused on better understanding today's complex socio-technical world and developing solutions that create impact. Inspired by the Garbage Can Model of Organizational Choice (Cohen et al. 1972), our research group can best be described as an organized anarchy with problematic preferences, unclear technology and fluid participation.
