10/15/2026 updated
BL
100 % available
Data Analyst | Python, SQL, Machine Learning & Dashboard Development
Nairobi, Kenya
Worldwide
Diploma in Data ScienceAbout me
I'm a data scientist with an extensive experience in Python programming. I am a quick learner and adept at scientific thinking,field data collection and presentation. I am skilled at reporting,creation of machine learning platforms and Automation
Sql Data WarehouseMicrosoft Analysis ServicesAnalytic ApplicationsData AnalysisFinancial Data AnalysisBig DataStatic Program AnalysisSignals IntelligenceDatabasesData ArchitectureData ControlData Definition LanguageData DiscoveryData Display DebuggersData Fusion
Python Programming
Proficiency in Python with libraries such as Pandas, NumPy, Scikit-learn, TensorFlow, and Keras for data analysis, machine learning, and predictive modeling.
SQL & Database Management
Strong SQL skills covering query optimization, joins, and stored procedures for efficient data retrieval and management.
Dashboard Development
Hands-on experience building interactive dashboards using Tableau, Streamlit, and Folium for operational and impact reporting.
Advanced Excel
Advanced Excel skills including pivot tables, macros, and Power Query for data processing and reporting.
Predictive Modeling & Forecasting
Application of predictive modeling and forecasting techniques using Prophet and ARIMA for time-series analysis.
Machine Learning Models
Experience with machine learning models including XGBoost, RandomForest, and CNN+LSTM for classification and prediction tasks.
Anomaly Detection & Trend Analysis
Expertise in anomaly detection and trend analysis to identify irregularities and patterns in complex datasets.
ETL Pipeline Development
Development and automation of ETL pipelines for efficient data extraction, transformation, and loading.
Data Cleaning, Validation & Transformation
Thorough data cleaning, validation, and transformation processes to ensure data quality and integrity.
Feature Engineering & Dataset Augmentation
Application of feature engineering and dataset augmentation techniques such as SMOTE and jitter to improve model performance.
Time-Series & Geospatial Analytics
Analysis of time-series and geospatial data to derive actionable insights for decision-makers.
Proficiency in Python with libraries such as Pandas, NumPy, Scikit-learn, TensorFlow, and Keras for data analysis, machine learning, and predictive modeling.
SQL & Database Management
Strong SQL skills covering query optimization, joins, and stored procedures for efficient data retrieval and management.
Dashboard Development
Hands-on experience building interactive dashboards using Tableau, Streamlit, and Folium for operational and impact reporting.
Advanced Excel
Advanced Excel skills including pivot tables, macros, and Power Query for data processing and reporting.
Predictive Modeling & Forecasting
Application of predictive modeling and forecasting techniques using Prophet and ARIMA for time-series analysis.
Machine Learning Models
Experience with machine learning models including XGBoost, RandomForest, and CNN+LSTM for classification and prediction tasks.
Anomaly Detection & Trend Analysis
Expertise in anomaly detection and trend analysis to identify irregularities and patterns in complex datasets.
ETL Pipeline Development
Development and automation of ETL pipelines for efficient data extraction, transformation, and loading.
Data Cleaning, Validation & Transformation
Thorough data cleaning, validation, and transformation processes to ensure data quality and integrity.
Feature Engineering & Dataset Augmentation
Application of feature engineering and dataset augmentation techniques such as SMOTE and jitter to improve model performance.
Time-Series & Geospatial Analytics
Analysis of time-series and geospatial data to derive actionable insights for decision-makers.
Experience
Professional experience0 - 5 years
Freelancer since2022
Languages
EnglishFluent
Project history
Built a real-time dashboard comparing ride prices across Nairobi routes using Python, SQL, and Streamlit. Applied anomaly detection and trend analysis, quantifying commuter savings (95.2% of routes cheaper on Bolt).
Developed a genomic surveillance dashboard analyzing 3,850+ viral sequences across 28 countries using Python, SQL, Tableau, and Biopython. Applied lineage classification and visualized transmission hotspots to support public health decision-making.
Collected, cleaned, and validated program data to track KPIs and identify anomalies in conservation operations. Collaborated with cross-functional teams to enhance data collection and reporting accuracy, supporting sustainability goals.