Master of Data Science graduate from RMIT University
Based in Melbourne, Australia
Data Scientist / Data Analyst focused on ML, Analytics, SQL, Power BI, and Cloud
- Build end-to-end data science and analytics solutions
- Work with SQL, Python, Power BI, machine learning, and cloud tools
- Develop business-focused dashboards and predictive models
- Turn messy data into clear decisions and measurable impact
- Improved NLP model accuracy from 56% to 86% in a production-focused project
- Reduced inference latency by 80% through optimization and deployment improvements
- Identified $35K+ annual revenue leakage through analytics and dashboarding
- Built end-to-end projects across ML, Power BI, PostgreSQL, Flask, AWS, and Docker
- Python, SQL, PostgreSQL, Pandas, NumPy, Scikit-learn
- Power BI, Tableau, Excel
- Data cleaning, feature engineering, EDA, model evaluation
- Classification, Regression, NLP, Recommender Systems
- TensorFlow, Keras, ONNX, Sentence Transformers
- AWS, Docker, Flask, DynamoDB, Lambda, S3
- API integration, model packaging, deployment workflows
- Git, GitHub, Jupyter, VS Code, Linux
Jobsite (Python · Scikit-learn · Flask · NLP · Classical ML)
- Built an NLP pipeline to preprocess and transform unstructured job advertisement text using Bag- of-Words and TF-IDF feature representations to search and classify jobs based on industry domain.
- Compared multiple vectorization approaches (BOG, weighted TF-IDF, and text feature combinations) using Logistic Regression, achieving 87.9% multi-class classification accuracy.
- Built and deployed a Flask-based web application enabling job search and automated job classification for employers and job seekers, storing categorized postings through an integrated inference pipeline.
Smart Grid Household Occupancy Prediction (Python (pandas, NumPy, scikit-learn) · PostgreSQL · Matplotlib/Seaborn · Jupyter Notebook)
- Built a machine learning model to predict daytime household occupancy using Australian energy consumption data.
- Compared multiple algorithms (Logistic Regression, Random Forest, Neural Networks) using cross-validation and ROC-AUC metrics.
- Achieved 88% recall, to minimize the cost of false negatives in energy distribution.
Banking Analytics Dashboard (Data Visualisation · Story Telling · ggplot · R Programming )
- Built a banking analytics dashboard using R (ggplot, dplyr) to visually communicate Australia’s transition from cash to digital payments for non-technical stakeholders.
- Designed time-series, segmented, and comparative visualisations to highlight generational payment behavior, category-level usage patterns, and the impact of COVID-19.
- Delivered a data storytelling narrative and published the dashboard on RPubs, linking digital payment adoption to ATM and bank branch closures to support strategic and operational insight
- Microsoft PL-300 (in progress )
- AWS Certified Cloud Practitioner (CLF-C02)
- Email: [email protected]
- Phone: +61 401 044 287