Farhana Agufa

Completed end-to-end machine learning and analytics projects including data acquisition, preprocessing, modeling, deployment, and reporting. Improved predictive model performance by 40% and built ETL pipelines, REST API endpoints, and Plotly Dash dashboards to support analytics and forecasting.

Trained and supervised 50+ annotators across image, text, audio, video, and LiDAR annotation projects. Increased task success to 96% and improved dataset consistency and training efficiency through structured coaching, quality audits, and remote-first coordination.

Streamlined administrative and academic coordination by preparing examinations, managing records, and overseeing financial documentation. Supported remote school operations through virtual administrative duties, document preparation, and coordination of academic materials.

Worked as a Cyber Attendant and IT Trainer at Muzdalifah Cyber in Nairobi.

Worked as a Data Annotation Specialist for Remotasks (remote).

Worked as a Distributor for 4-Life Research Company in Nairobi.

Worked as an Accounts & Finance Intern at Milimani Law Courts.

Activities and societies: Python Fundamentals Core Data Analysis Libraries Data Wrangling & Cleaning Statistics for Data Analysis SQL (usually paired with Python) Data Visualization (Advanced) Exploratory Data Analysis (EDA) Sampling in Python Hypothesis Testing in Python

Graduated with the Associate Data Analyst in Python career track from DataCamp, building core Python and data analysis skills: cleaning, transforming, and aggregating data with Pandas and NumPy, applying data visualization techniques using Matplotlib and Seaborn, writing efficient Python functions for data manipulation, and analyzing data through real-world projects

Activities and societies: Introduction to SQL Intermediate SQL Joining Data in SQL Data Manipulation in SQL PostgreSQL Summary Stats and Window Functions Functions for Manipulating Data in PostgreSQL Introduction to Statistics Exploratory Data Analysis in SQL Data-Driven Decision Making in SQL Understanding Data Visualization Data Communication Concepts

Graduated with the Associate Data Analyst in SQL career track from DataCamp, building core SQL and data analysis skills: querying, joining, and aggregating data, using window functions and subqueries, applying PostgreSQL functions, and analyzing data through real-world projects like student mental health and motorcycle sales.

Activities and societies: Intermediate Importing Data in Python Preprocessing for Machine Learning in Python Developing Python Packages Machine Learning for Business Introduction to SQL Intermediate SQL Joining Data in SQL Introduction to Git Intermediate Git

Graduated with the Data Scientist in Python career track from DataCamp: cleaned, transformed, and visualized data with Pandas, Matplotlib, and Seaborn; wrote efficient Python functions and packages; ran statistical analysis and hypothesis tests; built ML models with scikit-learn; and queried SQL databases using Git for version control.

Activities and societies: Data Viz w/Matplotlib, Functions, Python Toolbox, Categorical Data, Importing Data, Cleaning Data, Dates & Times, Writing Functions, Regression w/statsmodels, Experimental Design, Supervised Learning (scikit-learn), Unsupervised Learning, Tree-Based ML Models — all in Python

"Graduated with the Associate Data Scientist in Python career track from DataCamp: cleaned and transformed data with Pandas, built visualizations with Matplotlib and Seaborn, wrote efficient Python functions, performed statistical analysis and hypothesis testing, and built machine learning models with scikit-learn through real-world projects."

Activities and societies: "Linear Classifiers, XGBoost, Cluster Analysis, Dimensionality Reduction, Time Series ML, Feature Engineering (ML & NLP), Model Validation, Hyperparameter Tuning, NLP (Python & spaCy), Deep Learning w/ PyTorch (Intro & Intermediate), Image Processing, PySpark (Intro & ML), Winning Kaggle.

Graduated with the Data Scientist in Python career track from DataCamp: cleaned, transformed, and visualized data with Pandas, Matplotlib, and Seaborn; wrote efficient Python functions and packages; ran statistical analysis and hypothesis tests; built ML models with scikit-learn; and queried SQL databases using Git for version control.

Completed an Accounting Technicians Diploma (ATD). The diploma is accredited by KASNEB and is equivalent to Part I of the CPA qualification.