Looking for a job

George Kariuki

@georgekariuki3

Message

Entry-level data scientist building end-to-end ML pipelines for business and operational impact.

Kenya

Message

What I'm looking for

I’m looking for an entry-level role where I can build production-minded ML pipelines, run strong EDA and evaluation, and turn data into operational insights—while collaborating with engineers and stakeholders.

I’m a data scientist with a BSc in Information Technology and a Data Science Certification from Moringa School. I’m skilled in Python, machine learning, and statistical analysis, and I enjoy turning messy real-world data into clear, decision-ready insights.

In my final year research project at Kenya Cooperative Creameries (KCC), I built an end-to-end ML pipeline to auto-classify and prioritise IT support tickets. I used TF-IDF with SVM, Random Forest, and LSTM models, then delivered a full-stack system with a Django REST Framework API, React.js frontend, and PostgreSQL—along with SLA windows and measurable operational metrics (MTTR and FCR).

I also develop predictive models through hands-on projects, such as a credit risk classification model using a 50,000-record dataset (with SMOTE for class imbalance) and achieving an AUC-ROC of 0.89. From telecom churn analysis to data-driven recommendations for a movie studio, I focus on rigorous EDA, careful model evaluation, and communicating results in a way stakeholders can act on.

Experience

Work history, roles, and key accomplishments

IT Ticket Prioritization ML

Kenya Cooperative Creameries (KCC)

Jan 2025 - Jan 2026 (1 year)

Built an end-to-end ML pipeline to auto-classify and prioritise IT support tickets using TF-IDF with SVM, Random Forest, and LSTM models. Designed a full-stack Django REST Framework + React.js system with PostgreSQL, defined SLA windows, and documented the API/architecture and ML pipeline.

Python TF IDF SVM Random Forest Django REST Framework React PostgreSQL Model Evaluation Data Wrangling

Telecom Churn Analysis

Moringa School

Jan 2025 - Present (1 year 5 months)

Performed churn analysis on a 7,000-customer dataset using EDA, chi-square tests, and correlation analysis to identify key churn drivers. Built and tuned Decision Tree and Random Forest classifiers (86% accuracy) and presented data-backed retention strategy recommendations.

Python Pandas EDA Chi Square Testing Decision Trees Random Forest GridSearchCV Data Visualization

Credit Risk Prediction Model

Personal Project

Jan 2025 - Present (1 year 5 months)

Developed a binary classification model to predict loan default risk on a 50,000-record dataset, using feature engineering and SMOTE to handle class imbalance. Compared Logistic Regression, Random Forest, and XGBoost and achieved an AUC-ROC of 0.89 with scorecard-ready risk-band thresholds.

Python Pandas SMOTE Logistic Regression Random Forest XGBoost Feature Engineering Class Imbalance Handling