Built an analytics pipeline to test whether Australian macro-economic indicators — wage growth, construction cost inflation, and interest rate cycles — can predict general insurance claim severity before the insurer's loss account catches up. End-to-end: ABS + RBA + APRA ingestion, lead-lag correlation analysis, regularised regression, and a four-page Streamlit dashboard with live stress-test scenario controls.
A six-model machine learning benchmark on 10,000 bank customers — investigating not just which algorithm wins, but how to meaningfully improve recall on a real-world imbalanced dataset using SMOTE, sample weighting, and threshold tuning.
Tweedie regression pipeline estimating Pure Premium across 677k+ motor insurance policies — with reactive Streamlit dashboard, model evaluation, and feature importance analysis.
Comprehensive HR analytics dashboard visualising workforce demographics, salary trends, and performance insights using Tableau and Python-generated data.
Explore Australia Wildfire Dashboard—an interactive app using Dash and Plotly. Analyse historical wildfire data, trends, fire intensity, and key metrics across regions with visual, insightful tools.
Analysed Ayusy YouTube channel using EDA and YouTube API to uncover insights on video duration, titles, and engagement. Findings helped shape data-driven strategies to boost reach and performance
Interactive dashboard built using Python, Streamlit, and Plotly to analyse insights from the 2024 Stack Overflow Developer Survey. Explores trends in salary, roles, languages, and geography.
End-to-end SQL Server data warehouse & analytics solution showcasing robust ETL pipelines data modeling, and interactive dashboards, demonstrating skills in data engineering and business intelligence.