Skip to content
View franciswairagu's full-sized avatar

Block or report franciswairagu

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
franciswairagu/README.md

Hi there πŸ‘‹ I'm Francis Wairagu

I'm a Data Scientist and Machine Learning Engineer from Kenya passionate about turning data into intelligent, practical solutions.

My work spans data science, machine learning, deep learning, recommendation systems, natural language processing, and AI-powered applications. I enjoy taking problems from raw data and exploration all the way to modeling, evaluation, and deployment.

I'm particularly interested in building systems that solve real-world problems, rather than treating machine learning as just a modeling exercise.


πŸš€ About Me

  • πŸ“Š Data Scientist with hands-on experience across the end-to-end data science lifecycle
  • πŸ€– Experienced in Machine Learning and Deep Learning
  • 🧠 Interested in AI, NLP, recommender systems, and intelligent applications
  • 🐍 Python developer focused on data-driven and AI-powered solutions
  • πŸ—„οΈ Comfortable working with SQL, data pipelines, feature engineering, and large datasets
  • πŸ“ˆ Passionate about model evaluation, optimization, and turning predictions into useful products
  • πŸ‡°πŸ‡ͺ Building technology to solve real-world problems in Kenya and beyond

πŸ› οΈ Tech Stack

Languages

  • Python
  • SQL

Data Science & Machine Learning

  • Pandas
  • NumPy
  • Scikit-learn
  • XGBoost
  • LightGBM
  • CatBoost

Deep Learning & AI

  • TensorFlow
  • Keras
  • PyTorch
  • Neural Networks
  • Natural Language Processing
  • Transformers
  • Embeddings

Recommendation & AI Systems

  • Recommendation Systems
  • Content-Based Filtering
  • Collaborative Filtering
  • Hybrid Recommendation Systems
  • Semantic Search
  • RAG / Retrieval-Augmented Generation
  • Skill Matching & Ranking

Data Visualization

  • Matplotlib
  • Plotly
  • Tableau

Databases & Data Engineering

  • PostgreSQL
  • SQL
  • Data Cleaning & Transformation
  • ETL / Data Pipelines
  • Web Scraping
  • API Data Collection

Tools & Development

  • Git & GitHub
  • Jupyter Notebook
  • VS Code
  • Linux
  • Anaconda
  • REST APIs

πŸ“‚ Featured Projects

πŸ’Ό JobPulse β€” Job Market Intelligence Platform

An end-to-end job market intelligence and career recommendation platform focused on helping job seekers understand the market and discover relevant opportunities.

The platform combines:

  • Multi-source job data collection
  • Data cleaning and normalization
  • Job market analytics
  • Machine learning
  • NLP and semantic matching
  • Skill extraction and normalization
  • Career recommendations
  • Skill-gap analysis
  • AI-powered assistance

The long-term goal is to bridge the gap between what employers are looking for and what job seekers currently have, helping people understand not only which opportunities fit them, but also which skills they need to develop.


πŸ’° Financial Risk Prediction

Built and evaluated machine learning models for financial risk prediction using:

  • Feature engineering
  • Model comparison
  • Hyperparameter optimization
  • XGBoost
  • LightGBM
  • CatBoost
  • ROC-AUC
  • Log Loss

Focused on selecting models based on meaningful predictive performance rather than relying solely on accuracy.


🎬 Movie Recommendation System

Developed a recommendation engine using content-based and collaborative filtering techniques to generate personalized movie recommendations.

The project explored:

  • Similarity-based recommendations
  • User preferences
  • Feature engineering
  • Recommendation ranking
  • Evaluation of recommendation approaches

πŸ€– Machine Learning Portfolio

A collection of end-to-end machine learning projects covering:

  • Classification
  • Regression
  • Recommendation Systems
  • Feature Engineering
  • Exploratory Data Analysis
  • Data Visualization
  • Model Selection
  • Hyperparameter Tuning
  • Model Evaluation
  • Predictive Modeling

🧠 Areas of Expertise

Data Science
    β”œβ”€β”€ Data Analysis
    β”œβ”€β”€ Data Cleaning
    β”œβ”€β”€ Feature Engineering
    └── Data Visualization

Machine Learning
    β”œβ”€β”€ Classification
    β”œβ”€β”€ Regression
    β”œβ”€β”€ Ensemble Models
    β”œβ”€β”€ Model Optimization
    └── Model Evaluation

Deep Learning
    β”œβ”€β”€ Neural Networks
    β”œβ”€β”€ Computer Vision
    β”œβ”€β”€ NLP
    └── Representation Learning

AI Systems
    β”œβ”€β”€ Recommendation Systems
    β”œβ”€β”€ Semantic Search
    β”œβ”€β”€ RAG
    β”œβ”€β”€ Embeddings
    └── Intelligent Applications

🎯 What I'm Building

I'm focused on turning my data science and AI skills into production-oriented applications.

My interests include:

  • πŸ€– Applied AI
  • 🧠 Machine Learning & Deep Learning
  • πŸ”Ž NLP and Semantic Search
  • 🎯 Recommendation Systems
  • πŸ“Š Data & Business Intelligence
  • βš™οΈ ML Systems and Pipelines
  • πŸ‡°πŸ‡ͺ Technology solving African problems

πŸ“« Connect With Me


"Data is only valuable when it becomes understanding, and understanding becomes action."

Pinned Loading

  1. jobpulseKe jobpulseKe Public

    Jupyter Notebook 1 1

  2. financial-loan-risk financial-loan-risk Public

    Jupyter Notebook 1

  3. Clustering---recommendation-system Clustering---recommendation-system Public

    Datavines Analytics; three projects included, kNN modeling, Recommendation system and Market segmentation using Clustering

    Jupyter Notebook 1

  4. Telco-Customer-Insights-Retention-Analysis Telco-Customer-Insights-Retention-Analysis Public

    Customer churn analysis using Python, uncovering retention drivers and business insights for a telecom company.

    Jupyter Notebook 1

  5. beijing-air-quality-prediction-using-LSTM beijing-air-quality-prediction-using-LSTM Public

    Jupyter Notebook 1