Open to opportunities

Samuel Ajagun

@samuelajagun

Message

Data Scientist and Machine Learning Engineer turning credit, churn, and fraud data into scalable models.

United Kingdom

Message

What I'm looking for

I want to build end-to-end ML products where data quality, scalability, and MLOps matter—deploying models that drive decision-making (risk, churn, and fraud) and communicating insights clearly to stakeholders.

I’m a highly motivated Data Scientist and Machine Learning Engineer who builds data-driven solutions for credit risk modeling, customer churn analysis, fraud detection, and data annotation. I apply statistical methods and machine learning across the full workflow—data collection, cleaning, feature engineering, model building, evaluation, and deployment—so teams can make better decisions with clear, evidence-based insights.

I specialize in preparing and labeling high-quality datasets, using exploratory data analysis, and developing predictive models—from machine learning to deep learning and NLP. In my recent CodeAlpha roles, I’ve collected and preprocessed large datasets, built and evaluated models for classification/regression/clustering, deployed ML using Flask/FastAPI, Docker, Streamlit, and cloud platforms (AWS/Azure/GCP), and delivered dashboards with Power BI, Tableau, Matplotlib, and Seaborn—always prioritizing scalability, efficiency, and reproducible results.

Experience

Work history, roles, and key accomplishments

Current

Machine Learning Intern

Current

CodeAlpha

Aug 2025 - Present (9 months)

Collected, cleaned, and preprocessed large datasets for analysis and ML modeling, performing EDA to identify trends and correlations. Built and evaluated classification, regression, clustering, and NLP models (TensorFlow/PyTorch), and deployed services using Flask/FastAPI, Docker, Streamlit, and cloud platforms.

Python data preprocessing scikit learn TensorFlow PyTorch NLP Model Deployment (Flask FastAPI)Docker Streamlit

Machine Learning Intern

CodeAlpha

May 2025 - Jun 2025 (1 month)

Collected and prepared high-quality datasets, building and optimizing classification and regression models with Scikit-learn and TensorFlow. Developed generative AI applications and AI agents (n8n, Vapi, Make.com), and deployed interactive outputs using Streamlit, Docker, and AWS/Azure.

Python Feature Engineering scikit learn TensorFlow Generative AI Streamlit Docker AWS Azure

Health Analyst (Intern)

General Hospital

Jun 2018 - Sep 2021 (3 years 3 months)

Analyzed health and demographic datasets to uncover risks and behavioral patterns, supporting predictive modeling and forecasting. Built dashboards and visual reports to aid decision-making and ensured compliance with HIPAA/GDPR while translating insights for stakeholders.

Data Cleaning Statistical Analysis predictive modeling Data Visualization Dashboarding Risk Assessment