I'm a Statistics-trained Data Scientist with around 5 years of experience across business intelligence, enterprise data integration, statistical analysis, and applied machine learning. I hold an MSc in Statistics and use statistical reasoning and modern data tooling to turn complex data into decisions people can act on.
In my current BI Analyst role, I work with enterprise-scale data using Oracle SQL, Power BI, MicroStrategy, Excel, and automation, building analytical solutions and dashboards for operational and business decisions. Earlier, in enterprise data integration, I managed data mappings, transformation logic, validation, APIs, and production workflows for international clients, which gave me a solid grounding in data quality and pipeline reliability.
My data science work centres on Python, machine learning, statistical modelling, and Generative AI. My portfolio includes an end-to-end fraud and anomaly detection system built on Isolation Forest with an LLM-based explanation layer, a climate risk modelling project using multi-source environmental and geospatial data, and an AI-assisted entity matching solution using fuzzy matching. I'm also a Microsoft Certified: Fabric Data Engineer Associate, with a growing focus on scalable data and ML workflows.
I'm looking for Data Scientist, Applied Data Scientist, Risk/Analytics, and Machine Learning roles where I can combine a strong statistical foundation with hands-on ML, data engineering, and GenAI skills. I enjoy problems involving prediction, anomaly detection, model evaluation, and explainability, and I care about making results clear enough for non-technical stakeholders to use.
