Data Scientist
I build predictive models, analytics dashboards, and data workflows that turn messy research and business data into decisions people can act on.
Current focus
M.Sc. Data Science at MAHE
Predictive modelling, statistical consulting, Power BI dashboards, and applied machine learning for health, energy, and research data.
Selected work
Automated mapping of research titles and abstracts to UN Sustainable Development Goals using TF-IDF, supervised classifiers, clustering, and similarity scoring.
Applied computer vision workflow for automated IBD severity scoring and polyp detection, connecting medical imaging with decision support.
Open repositoryAnalysed appliance-level electricity consumption, identified AC and refrigerator as major cost drivers, and built dashboards plus monthly cost forecasts for behaviour-based savings.
Open repositoryConverted manufacturing scrap and cost data into an operational dashboard showing trends, material-wise losses, and waste-reduction opportunities for engineering teams.
Experience
Engineered Power BI dashboards across production, quality control, and inventory systems, performed EDA on industrial datasets, and developed a 3-month scrap-generation forecast.
Graduate study focused on applied data science, predictive modelling, statistics, and research-oriented analytics.
Built foundations in analytics, programming, business intelligence, and communicating findings from structured data.
Capabilities
Python, Pandas, NumPy, Scikit-learn, R, SQL, predictive modelling, statistical analysis.
Power BI, DAX, Pivot Tables, interactive dashboards, Excel, executive reporting.
ETL pipelines, data cleaning, validation, normalisation, reproducible project structure.
Scientific communication, study design support, sample size calculation, team coordination.
Contact