I am a research scientist and data analyst with a passion for transforming complex datasets into actionable insights. My expertise spans from machine learning and data visualisation to environmental monitoring and electrochemical sensor development. Iβve led various data-driven projects on environmental science, helping organizations make informed decisions through accurate and reliable data models.
In my professional journey, Iβve developed predictive models, including algorithms for customer churn prediction and sales forecasting, leveraging Python, SQL, and Power BI. In addition to my work in data science, I have applied advanced material chemistry techniques in electrochemical sensor development, integrating both scientific research and data analytics.
Throughout my academic and professional career, Iβve been dedicated to teaching and mentoring students, particularly in data analysis and environmental monitoring.
- Data Science & Analysis: Python (Pandas, NumPy, Scikit-learn), SQL
- Data Visualization: Power BI, Matplotlib, Seaborn, Excel
- Machine Learning: Predictive Modeling, Data Cleaning, Churn Prediction
- Environmental Monitoring: Water Treatment, Pollutant Detection, Electrochemical Sensors
Welcome to my data portfolio! Here, I document a summary of my projects in the data field.
| Project Link | Completion Date | Tools | Project Description |
|---|---|---|---|
| π§ Environmental Pollutant Analysis of LCMS and GCMS Datasets | 2024 | Python, Pandas, Seaborn, Matplotlib | Conducted advanced data analysis of neonicotinoid pollutant concentrations across multiple sites, creating interactive geospatial visualisations to map distribution. |
| π Neonicotinoid Concentration Analysis in Freshwater Bodies | 2024 | Python, Monte Carlo Simulation | Performed multi-year analysis of neonicotinoid levels in UK freshwater bodies using Python; developed predictive models with Monte Carlo Simulation to forecast concentrations and assess future risks. |
| Project Link | Area | Project Description | Libraries |
|---|---|---|---|
| π§ Environmental Pollutant Analysis of LC-MS Data | Data Analysis & Visualization | Advanced data analysis of neonicotinoid pollutant concentrations; created interactive geospatial visualizations. | Pandas, Seaborn, Matplotlib |
| π Neonicotinoid Concentration Analysis in Freshwater Bodies | Predictive Modeling | Developed predictive models to forecast pollutant concentrations and assess future risks. | Monte Carlo Simulation |
| Publication | Description |
|---|---|
| π An Electrochemical Screen-Printed Sensor Based on Gold-Nanoparticle-Decorated Reduced Graphene OxideβCarbon Nanotubes Composites for the Determination of 17-Ξ² Estradiol | Musa, A.M., Kiely, J., Luxton, R., & Honeychurch, K.C. (2023). Biosensors, 13(4), 491. |
| π Graphene-Based Electrodes for Monitoring of Estradiol | Musa, A.M., Kiely, J., Luxton, R., & Honeychurch, K.C. (2023). Chemosensors, 11(6), 337. |
| π Recent Progress in Screen-Printed Electrochemical Sensors and Biosensors for the Detection of Estrogens | Musa, A.M., Kiely, J., Luxton, R., & Honeychurch, K.C. (2021). TrAC Trends in Analytical Chemistry, 139, 116254. |
| π€ Water Silent Hormone Monitoring: A Novel Electrochemical Sensor for On-Site Detection of Estradiol in Water | Musa, A. (2023). Presented at Sensing in Water 2023. |
British Airways, Boston Consulting Group, Cognizant, Commonwealth Bank, Forage | 2024
- Completed job simulations involving data management skills.
- Applied predictive modeling techniques in various data science contexts.
- Optimized data-driven decision-making.
GSK Digdata Step Up Career Challenge - Clinical Trial Data Analysis | 2024
- Utilized machine learning models to predict patient treatment response in the Miraculon-B clinical trial studies data.
Please feel free to explore the projects and activities detailed above. If you have any questions or would like to collaborate, don't hesitate to reach out!