/* I turn messy data into usable analytics, using SQL and database design to build dashboards that inform decisions. */
Currently an Extern @PfizerProjects focus on SQL, database architecture, data cleaning, and dashboarding; externship work includes turning CSVs into an analytics database and Q4 dashboard for Breaking Games.
Turn six messy CSVs into an analytics database and a Q4 dashboard that drives real business decisions. SQL + Claude.
Built ML models to detect anomalous transactions in highly imbalanced datasets. Applied feature engineering, resampling strategies, and model evaluation techniques to optimise performance. Used explainable AI techniques to interpret predictions and support trust in model outputs.
Integrated trained models into data pipelines for downstream consumption. Experimented with multiple algorithms and hyperparameters to identify optimal solutions.
I turn messy data into usable analytics, using SQL and database design to build dashboards that inform decisions.
I am a graduate computer science student with some practical experience building data and analytics solutions. I completed a SQL and database architecture externship with Breaking Games, where I transformed messy CSVs into an analytics database and a Q4 dashboard using SQL and Claude.
Externships
Pfizer Advanced: AI-Powered Document Insights & Data Extraction Externship
Pfizer
Experience
Data science placement
Legal and General · From: 07/2023 To: 08/2024
Education
University of Hertfordshire
B.Sc. in Computer Science · Class of 2025
Skills
✅ Verified by Extern
Turn six messy CSVs into an analytics database and a Q4 dashboard that drives real business decisions. SQL + Claude.
The work converted six raw CSV sources into an analytics-ready SQLite database and a consolidated project document. It inventoried each source, ran exploratory and production SQL, documented five instant-answer queries with SQL text and results, designed a dim_product and product performance aggregation, and built a denormalized dashboard_metrics table plus a static HTML dashboard showing five
I produced an analytics-ready SQLite dataset from six CSVs, documented five instant-answer SQL queries with SQL text and results, created a dim_product and product performance aggregation with holiday reorder recommendations, calculated CTR/CPC/ROI from $37K Meta spend and assembled a Q4 ad allocation plan plus a bot-filtering proposal to re-evaluate cart abandonment.
Built ML models to detect anomalous transactions in highly imbalanced datasets. Applied feature engineering, resampling strategies, and model evaluation techniques to optimise performance. Used explainable AI techniques to interpret predictions and support trust in model outputs.
Integrated trained models into data pipelines for downstream consumption. Experimented with multiple algorithms and hyperparameters to identify optimal solutions.