Transforming data into insights and impact.
Nimrod is a Data Scientist passionate about uncovering actionable insights from complex data. He specializes in machine learning, data visualization, and storytelling with data. His goal is to bridge the gap between raw data and meaningful decision-making by building intelligent systems and intuitive dashboards.
He has hands-on experience in developing predictive models, conducting deep exploratory analysis, and building dashboards that drive business performance. With a background in Computer Science, He bring a structured and results-driven approach to solving real-world problems.
His technical stack includes Python (with libraries such as Pandas, NumPy, Plotly, Matplotlib, and Seaborn), SQL, Power BI, Excel, and Jupyter/Colab notebooks. He is skilled in data cleaning, visualization, model development (classification, regression, clustering), and working with APIs and ETL pipelines.
He is certified in Data Science by ALX Africa. This program equipped him with practical, project-based experience and reinforced his ability to work collaboratively, think critically, and build solutions that add value.
Designed an interactive Power BI dashboard to analyze access to clean water in underserved regions for a fictional Country. Used data on water sources, population distribution, and access coverage to highlight disparities and opportunities for intervention. Implemented filters for region, population, and time span to make insights dynamic and actionable.
Impact: Provided a visual tool for NGOs and government partners to plan water infrastructure more effectively.
Skills: Excel, Power BI, DAX, PowerQuery
View on GitHubDeveloped a comprehensive sales performance dashboard using Superstore data. Tracked profit margins, customer segments, sales by region, and product category trends. Added dynamic filters and time slicers to give users flexible views for strategic planning.
Impact: Enabled sales teams to identify high-performing categories and optimize marketing spend.
Skills: Power BI, DAX, PowerQuery
View on GitHubPerformed a deep dive into e-commerce platform data to identify fraud patterns. Applied statistical tests and machine learning techniques to uncover unusual review activity, suspicious delivery patterns, and seller behavior anomalies. Used clustering and anomaly detection to classify risk levels for sellers.
Impact: Helped stakeholders identify bad actors and reduce fraud risk in cross-border marketplaces.
Skills: Python (Pandas, Scikit-learn, Matplotlib), SQL
View on GitHub