Sadiq BalogunData Scientist
Professional Summary

Data Scientist with 3+ years of experience applying machine learning, data analysis, and visualisation across academia and technology sectors. Developed a data mining tool that digitised legacy graphical data with 94% accuracy and integrated a generative AI (LLaMA 4 Scout) interface—reducing query times for researchers by over 70%. Delivered cross-department Power BI dashboards that cut manual reporting by 2 hours daily and led A/B experimentation on data annotation training that improved quality by 20%.

Education
MSc Applied Data Science - Distinction, Teesside University
09/2022 – 05/2024
BSc Agricultural Engineering - 2:2, Obafemi Awolowo University
09/2011 – 09/2016
Certificates
AWS Machine Learning Engineer Associate — August 2025
Referees
Availabe upon request.
Work History
Data Scientist, University of Leeds
09/2024 – 09/2025 | Leeds, UK

Project 2: Predicting Rock Strength from Grain Size and Porosity

  • •Achieved 95% accuracy by developing an automated Python-based data mining application with a PostgreSQL backend to process research plots at scale.
  • •Engineered a natural language to SQL interface using LLM APIs and prompt optimisation, improving query accuracy to 90% and reducing researcher data retrieval time by 80%.
  • •Reduced lab testing costs by developing a predictive model for rock failure strength, achieving an R² of 0.96.
  • •Improved query performance by 40% and ensured zero data loss by designing a normalised database schema with optimised indexing.
  • •Reduced setup time by 70% and enabled reproducible deployments across research environments by containerising the Python application with Docker.

    • Project 1: Understanding Wider Determinants Associated with Looked After Children.

  • •Developed three statistical datasets by transforming nine SQL tables; created 20,000+ records, enabling predictive analysis for social care demand forecasting
  • •Leveraged predictive models for monthly children's care demand forecasting; generating data-driven insights for long-term strategic planning and optimised resource allocation for local authorities.
  • •Performed geospatial analysis identifying high-risk areas for children in care; enabled targeted interventions across 300+ geographic areas and improved resource allocation.
  • •Created data visualisations for non-technical stakeholders; directly influenced city-wide policy decisions and strategic planning initiatives.
    • Data Analyst, Hugo Technologies
    09/2020 – 09/2022 | Lagos

  • •Built and maintained 8 interactive Power BI dashboards tracking key performance indicators, reducing management decision-making time by 2 hours daily through automated reporting. across multiple departments.
  • •Led an ETL data migration solution of 1.5 million records using SQL optimisation and Python automation, improving analytical performance.
  • •Designed and executed A/B experiments to evaluate annotation team performance metrics, identifying a 20% improvement in data quality through statistical analysis and experimental controls.
  • •Led weekly stakeholder meetings, presenting performance metrics and data-driven recommendations; improved client decision-making speed and maintained 100% project alignment through consistent reporting.
  • •Collaborated with cross-functional teams to integrate analytical insights into operational processes, demonstrating ability to work with engineering and product teams.
    • Site Manager, Projects-Link Technology Ltd
    03/2018 – 08/2020 | Lagos

  • •Led a team of 20 employees, effectively managing their daily tasks, schedules, and performance to ensure the timely completion of projects.
  • •Successfully delivered high-quality projects within budget and on schedule.
  • •Optimised site operations with data-driven processes, boosting productivity by 15%.
  • •Collaborated with cross-functional teams, including engineers, architects, and contractors, to successfully deliver high-quality projects within budget and on schedule.
    • Skills
    Programming & Data Tools:  Python, PySpark, SQL, Git/GitHub, MLFlow
    Technical Skills: AI integration, Predictive analytics, Hypothesis testing, Time-series forecasting, ETL, Data visualisation, Data storytelling, Version control
    Soft Skills: Cross-functional collaboration, Communication, Problem-solving, Stakeholder management, Self-motivated
    Cloud Platform: AWS, GCP