Richard V.

🎓 BSc Physics, Particle Physics (University of Groningen) 💻 Expert in Python, Power BI, Excel, MATLAB, HPC and API pipelines 📊 Experienced in API data extraction, data cleaning, visualization, ML modelling Recently, I built an end-to-end Python pipeline for extracting, cleaning, and analysing ~300k publications from the OpenAlex API, generating clean, analysis-ready datasets and visualizations that summarize top concepts and publication trends. [See full project and GitHub in Portfolio Projects] ════ Who Am I? ════ Hi, I’m Richard. I recently completed a BSc in Physics with a specialization in Particle Physics, where I gained hands-on experience analysing complex datasets and solving abstract, high-level problems. I’ve worked on everything from noisy detector data to molecular parity violation research, translating raw data into clear, reproducible insights. I help clients turn raw, messy data into clean, structured datasets ready for analysis and visualization. With a BSc in Physics (Particle Physics) and experience handling large-scale datasets, I specialize in API data extraction, automated data cleaning, exploratory analysis, and machine learning modelling. ════ What I Do (Services) ════ ✔️ API Data Extraction & Automation Collect data from APIs, web sources, or databases Handle large datasets, pagination, and automated pipelines Return clean, structured data in CSV, Parquet, or requested formats ✔️ Data Cleaning & Pre-Processing Interpolate missing data, remove noise, normalize datasets Validate results using multiple methods for robustness Prepare datasets optimized for analysis or ML applications ✔️ Exploratory Data Analysis & Feature Engineering Analyse patterns, trends, or correlations Extract and engineer features for further modelling Deliver results in interpretable, ready-to-use formats ✔️ Data Visualization & Reporting Python, Excel, or Power BI dashboards Reports designed for any audience from non-technical to scientific. Clear, reproducible, and ready for presentation ✔️ Machine Learning & Statistical Modelling Regression: Linear, Polynomial, Logistic, Regularized, Random Forest Clustering: K-Means, DBSCAN, Hierarchical Classification: Logistic Regression, Decision Trees, Random Forest, Gradient Boosting Custom ML workflows tailored to your data and goals Open to taking flexible ML method requests at negotiable rates, providing high-quality, reproducible work while expanding my skillset ════ How I Work ════ 1️⃣ Plan & Understand Goals I take time to understand your objectives, discuss options, and outline deliverables, timelines, and milestones. 2️⃣ Frequent Updates & Transparency You’ll receive clear, regular updates. Questions and challenges are addressed promptly (within 24 hours). 3️⃣ Reliable, Reproducible Results Projects are delivered on time, tested, documented, and maintainable for future use. 4️⃣ Post-Delivery Support I provide ongoing guidance and answer questions for several months after project completion, ensuring smooth adoption and fully functional, reliable solutions. ════ Deliverables You Can Expect ════ Clean, optimized datasets (CSV, Parquet, or requested format) Automated, ready-to-use, reproducible pipelines in Python or Jupyter Notebooks Custom dashboards and visual reports Full documentation and optional post-delivery support