
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Data Science with 1+ years in machine learning pipelines and data analysis, specializing in fintech-
Data Science graduate (Moringa School) with a Computer Science diploma (Zetech University), skilled in Python, statistical modeling, and end-to-end machine learning pipelines. Builds practical, fintech-relevant projects including a telecom churn model and a synthetic M-Pesa fraud detection pipeline, with a focus on turning raw data into clear, actionable insight. Seeking an entry-level data analyst or junior data scientist role in Kenya or remote, with particular interest in fintech.
Moringa School
Certificate · Data Science & Machine Learning
August 1, 2024 – June 30, 2025
Zetech University
Diploma · Computer Science
N/A – June 30, 2025
Telecom Customer Churn Prediction Pipeline
January 1, 2026 – June 30, 2026
Built a modular, end-to-end ML pipeline in Python to predict customer churn, splitting data cleaning, feature engineering, modeling, and evaluation into separate reusable scripts. Trained and compared classification models with scikit-learn, using matplotlib to visualize churn drivers and model performance for the team.
Medical Insurance Cost Predictor
January 1, 2025 – December 31, 2025
Built a regression model to predict medical insurance costs from demographic and lifestyle features, published as a featured case study on personal portfolio site. Created clear visualizations and write-ups to communicate model insights to a non-technical audience.
M-Pesa Fraud Detection Pipeline (Synthetic Dataset)
January 1, 2025 – June 30, 2026
Designed a synthetic M-Pesa transaction dataset to model fraud-detection scenarios relevant to Kenyan mobile money platforms. Building a logistic regression classification pipeline covering data generation, EDA, feature engineering, and model evaluation, for an active fintech-focused portfolio piece.
Google Play Store Analytics: PySpark & Tableau
January 1, 2025 – December 31, 2025
Processed and analyzed a large-scale Play Store dataset with PySpark, following the CRISP-DM framework end-to-end. Designed multi-dashboard Tableau reports with parameters, calculated fields, and cross-dashboard navigation to support stakeholder-style decision making.
Cultural Fit Analysis
The candidate's projects demonstrate a strong interest in practical, real-world applications of data science, particularly in the fintech sector (M-Pesa Fraud Detection). The diversity of projects (churn prediction, fraud detection, analytics, cost prediction) and the use of various tools (PySpark, Tableau) suggest adaptability and a willingness to explore different problem domains. The academic and personal projects align well with an entry-level Data Science role, indicating a proactive learning approach.
Soft Skills & Operational Fit
The candidate highlights problem-solving, team collaboration, communication, adaptability, and being a fast learner. Project descriptions indicate experience in team collaboration (Telecom Churn Prediction) and communicating insights, which are positive indicators for operational fit. However, without specific assessment scores for these, it's difficult to fully validate.