Industrial Chemist | Data Scientist | Machine Learning & Process Optimization
Data Scientist and Industrial Chemist with 5+ years of experience in synthetic resin and coatings manufacturing. I specialize in using data analytics and machine learning to optimize industrial processes, improve product quality, and enhance operational efficiency. My work bridges chemistry, production systems, and predictive modeling to solve real-world manufacturing challenges.
I combine industrial chemistry expertise with data science to optimize manufacturing systems and drive data-informed decision-making.
I hold a Bachelor of Technology in Industrial and Applied Chemistry and have over five years of hands-on experience in synthetic resin manufacturing. My professional foundation is built on process optimization, quality control, and industrial problem-solving within ISO-compliant environments.
I transitioned into Data Science to apply analytical and machine learning techniques to real-world industrial challenges. Through self-learning, the ALX Data Science Program, I developed strong skills in Python, SQL, machine learning, statistical modeling, and data visualization.
I am particularly interested in applying data-driven solutions to industrial systems, including predictive maintenance, process optimization, demand forecasting, and quality analytics. I focus on turning production and operational data into actionable insights that improve efficiency and decision-making.
Currently, I am expanding my expertise into Data Engineering and production-level machine learning systems, with a focus on building scalable data pipelines, deploying models, and solving real-world business problems.
Synresins Kenya Ltd – Nairobi, Kenya
February 2020 – Present
Responsible for polymerization processes, quality control, and production optimization in synthetic resin manufacturing, with a focus on improving efficiency and product consistency.
Ministry of Petroleum and Mining – Directorate of Geological Surveys Laboratories | Nairobi, Kenya
July 2019 – October 2019
Conducted laboratory analysis and supported mineral processing studies, contributing to accurate material characterization and process improvement.
Machine learning classification model using Logistic Regression to distinguish between sonar signals reflected from rocks and underwater mines.
Tools: Python, Pandas, Scikit-learn
Achieved 83.4% training accuracy and 76.2% test accuracy using supervised learning techniques.
End-to-end data science pipeline transforming messy retail data into a predictive demand forecasting system with an interactive dashboard.
Tools: Python, Pandas, Scikit-learn, Streamlit
Reduced prediction error by 58% (RMSE: 38.6 → 16.3) and built a real-time forecasting dashboard for inventory decision-making.
Sharing knowledge on Data Science, Industrial Analytics, and Polymer Chemistry.
A deep dive into why I'm moving toward Polars for high-performance industrial data processing.
Read ArticleHow predictive maintenance and quality analytics are transforming the resin production landscape.
Read ArticleUsing statistical modeling to optimize synthetic resin yield and batch consistency.
Read ArticleI'm always interested in discussing new opportunities, collaborations, or projects related to data science and industrial applications. Feel free to reach out!