Danh is keen on applying data engineering and machine learning tools to solve real-world problems and help businesses make efficient science-based decisions. He has experience collaborating with key stakeholders and acquiring domain knowledge to frame and solve business problems. Danh is passionate about turning data into actionable insights.
He sharpens his skills in full-stack data science and engineering cycles, including building data pipelines (ETL/ELT) with infrastructure as code, performing data analysis and BI reports, and developing and productionizing statistical and machine learning models. Danh has acquired strong programming (Python, SQL) knowledge and has actively contributed to several open-source projects on GitHub. He is a team player with an open mind and is eager to collaborate.
Danh is building the data platform for the Investment Data System Team at HESTA, a Super Fund with more than 1 million Australian members. Hesta invests close to $74 billion. Before that, Danh worked at the Pacific service team, Johnson Controls Australia, his tasks involved building data pipelines, developing and productionizing Dynamic Pricing models, modelling Customer churning risks on cloud, as well as performing data analysis and creating high-quality BI reports and KPI dashboards.
Danh has experience in programming, and has been a Data instructor at Monash Data Fluency, where he teaches hands-on data-related workshops with Python, Git, Bash, and High-Performance Computing to research students and staff at Monash University. He loves Data Science and Bayesian statistics, and actively contributes to open-source projects like PyMC and Aesara on GitHub. He’s worked on a Google Summer of Code project to develop a module that supports Multi-output Gaussian Processes in PyMC.
Before that, Danh was a Ph.D. researcher at Monash University, working on Machine learning for intelligent transport systems. This research focuses on understanding people’s choice behaviors when selecting their activity locations and travel modes. In this research, he applied various Machine learning methods (Bayesian methods, choice models, tree-based, and deep neural networks) with econometrics modeling approaches.